W2009: Integrated Systems Research and Development in Automation and Sensors for Sustainability of Specialty Crops

(Multistate Research Project)

Status: Inactive/Terminating

Project Menu

SAES-422 Reports

Annual/Termination Reports:

[09/09/2014] [11/03/2015] [11/16/2016] [11/13/2017] [11/17/2018]

Date of Annual Report: 09/09/2014

Report Information

Annual Meeting Dates: 07/23/2014 - 07/24/2014
Period the Report Covers: 10/01/2013 - 09/01/2014

Participants

Changying Li, UGA, cyli@uga.edu

Filip To, Msstate, fto@abe.msstate.edu

Qin Zhang, WSU, qinzhang@wsu.edu

Stavros Vougioukas, UCDavis, svougioukas@ucdavis.edu

Mark Siemens, U of Ariz, siemens@cals.arizona.edu

Joseph Dvorack, Univ Kentucky, joe.dvorak@uky.edu

Loren Gautz, u of Hawaii, lgoutz@hawaii.edu

David Slaughter, UC Davis dcslaughter@ucdavis.edu

Clark Seavert, Oregon State, Clark.Seavert@oregonstate.edu

Reza Ehsani, U of Florida, ehsani@ufl.edu

Raj Khosla, Colorado State, raj.khosla@colostate.edu

David Lee, U of Florida, wslee@ufl.edu

Ning Wang, Oklahoma State Univ, ning.wang@okstate.edu

Brief Summary of Minutes

Room Location: BIG SUR B
Start Time: 8:00 AM, July 24, 2014.
Meeting Adjourned at 3:30 PM
Chair: Changying Charlie Li, University of Georgia
Vice Chair: Raj Khosla, Colorado State
Secretary: Filip To, Mississippi State University

The technical tour was provided by the ICPA meeting in the afternoon (1-6 PM) of July 23rd. The participants were provided the opportunity to visit Orchard crops (Almonds and Walnuts) in Arbuckle and tomato field in Woodland, as well as the Robotics and Automation Lab in UC Davis/Bio. and Agr. Eng. Dept.

Announcements of Deadlines
Annual Report Due date: 60 days after the meeting. It must be submitted to regional leader (administrator) 30 days prior to due date, a deadline for members to submit reports to committee chair for compilation. Specific dates: Reports were to be sent to Charlie Li by August 11 for compilation; W-2009 reports to be sent to Jim Moyer (regional administrator) by August 25; W-2009 reports due September 24 to national administrator.

Settings
NCERA-180 and W-2009 Combined meeting was conducted in the morning for discussion of common interest for two hours and then separated for discussion specific to each committee. Video teleconference presentation by Dr. Daniel Schmoldt, National Program Leader of National Institute of Food & Agriculture (NIFA), USDA was conducted in the combined meeting. Contents included updated information from USDA and congressional appropriations of various mandatory and discretionary programs of 2014 and 2015. Electronic copies of presentation slides were distributed to members.

Joint Discussions
Arrangement of Technical Tour in conjunction with the meeting was determined to be an important component of the meeting and should be continued.

Update from members about ASABE events
A new group was formed for safety standard related to agricultural robotics. The following ASABE technical committees are involved in this effort: IET318 (mechatronics, PM-48 (specialty crop), PM 58 (ag. automation).

Next year ASABE will be in Louisiana.

CIGR congress in Beijing, Sept 2015, including Smart Agriculture Symposium, Automation Tech for Off Road Equipment. International forum for Precision Agriculture.

Separate meeting rooms were used for NCERA-180 and W-2009 at 10:30 AM.

W-2009 related events:

Aug 2014, International Horticulture Conference in Brisbane (Symposium of Mechanisation, Precision Horticulture, and Robotics in Fruit and Vegetable Production), Australia.

2nd international symposium on mechanical harvesting of specialty crops will be held in Washington State in September 2015.

9th International Symposium on Fruit, Nut and Vegetable Production Engineering (Frutic Italy 2015) will be held in Milan, Italy on May 19-22, 2015.

2015 European conference in Precision Agriculture will be in Israel.

AETC in Louisville KY 2014, farm industry show, 2015 will be on Feb 9-10 in Louisville, Kentucky again.

Election of Officers for 2015:
Chair Elect: Raj Khosla, Colorado State
Vice Chair: Filip To, Mississippi State University
Secretary: Stavros Vougioukas, U.C. Davis

Decision for 2015 W-2009 meeting:
The meeting will be held at Washington State University at Prosser, Date: Sept 13-16, in conjunction with the Mechanical Harvest Symposium. A Technical Tour will be arranged in the morning of September 16th (Wednesday) and business will be on Wednesday afternoon or Thursday Morning.

Station Reports:
The remainder of the time was used for oral presentations and updates from each station. All members in attendance presented updates and will submit annual reports to the Chair for compilation.

Individual State Reports can be found on the W-2009 Homepage (when NIMSS is fixed) at: http://lgu.umd.edu/lgu_v2/homepages/attachs.cfm?trackID=15436 Meeting was adjourned at 3:30PM.

Minutes Attachment:

W-2009 - State Reports for July 2014 Mtg.pdf

Accomplishments

Members of W2009 have produced several outcomes resulting from number of research activities. The research areas are broadly classified as: (1) specialty crop management (thinning, processing, disease detection & chemical application), (2) mechanical harvesting (including harvest assist), and (3) specialty crop postharvest handling, quality and safety. (1) Specialty crop management During 2014, an automated machine for thinning lettuce developed at the University of Arizona was further developed so that it could thin unwanted plants and spot apply insecticides to saved crop plants in the same pass. The automated thinning machine was also modified so that it could be used as an intra-row and inter-row weeding machine. Study results in lettuce showed that automated weeding followed by hand weeding significantly reduced overall labor requirements. In California, 3D spatial location data for more than 10,000 fruits (pears and clingstone peaches) while on the tree were collected. These data would help growers verify the effectiveness of their pruning and thinning strategies. A collaborative research project was conducted at the University of Central Florida and citrus research and education center of the University of Florida to develop a robust ground and aerial crop health monitoring system that could detect and map crop stress in citrus and strawberry production systems. This project has accomplished the following goals: 1) Developed an innovative ground based robotic system with autonomous capabilities to help monitor and analyze a strawberry field for diseases in close-proximity by taking spectral imaging and collecting leaf samples throughout the field; 2) Developed an octocopter to help monitor and analyze a strawberry field rapidly and relay the suspected area coordinates to the ground robot; 3) Developed the first version of disease detection sensor, which could be applied on both the aerial- and ground-based platforms. In addition, the following projects were conducted in Florida: 1) A novel technique was developed to detect immature green citrus in tree canopy under natural outdoor conditions; 2) Using polarized filter and narrow band imaging technique, a portable machine vision system was developed to detect the citrus greening symptomatic leaves; 3) Another machine vision system was developed to detect dropped citrus fruit on the ground along with a GPS receiver. It can count the number of fruit and estimate mass of the fruit with an accuracy of 89%; 4) A prototype laser weeding system was developed to kill in-row weeds using machine vision and a set of lasers to demonstrate the concept. In Iowa, a new set of plant detection algorithms based on 3D point cloud data analysis were developed for robotic non-chemical weeding. A new generation prototype of an automated intra-row mechanical weeder is under development. A robotic vehicle that is equipped with auto-steer system and a rig of six stereo camera heads has been developed for high-throughput plant phenotyping using robotic technologies. A series hybrid drivetrain for agricultural machinery was tested in Kentucky. The drivetrain was constructed using a diesel engine, a generator, a battery pack and electric traction motors. The traction motors were connected to a dynamometer and the drivetrain was tested at various loads. Two small scale autonomous ground vehicle test platforms were constructed from 1/10th scale RC model vehicles. This system will be used to test control methods and multiple-vehicle coordination algorithms for accomplishing field operations. Testing was also performed on tablet-based location services. In Oklahoma, various projects were carried out to improve pecan production efficiency and sustainability. For instance, pecan yield measurement technique was established by using backscattered terrestrial microwave sensing. Wireless image sensor network was used for monitoring the population of pecan weevils. A 1/4-scale robot was fabricated and tested for selectively thinning peach blossoms in Pennsylvania. In the lab, using simulated peach blossoms at random positions, the heuristic thinning algorithm accurately controlled the robotic arm and end effector performance, reaching the goal of removing at least 95% of target blossoms. Automated pruning project was carried out as well. Pruning of both apples and grapes, once thought to be a mysterious blend of art and science, has been described by a set of rules. Apple pruning rules developed through this project have been published at http://extension.psu.edu/plants/tree-fruit/news/2013/renewal-pruning-for-high-density-apple-plantings. In Washington, various research activities were performed including precision canopy and water management based on both light penetration and orchard micro-climate measurements, automated cane-berry canopy management, effective canopy or target zone chemical delivery technologies, and in-orchard sensing technologies for various automated agricultural operations. (2) Mechanical harvesting (including harvest assist) A low-cost harvest-assist device for apple orchard platforms was designed and fabricated in Pennsylvania. The device had four main components: receiver (where pickers placed the apples), two transport tubes, manifold, and distributor (which distributed the apples into a standard bin). Field tests will be performed in October 2014. Ergonomic and efficiency studies comparing the harvest assist device with standard ladder and basket picking began in 2014. Development of mechanical harvesting technologies for fresh market fruit has been one of major focuses for the WSU research team. A few generations of sweet cherry harvesting prototypes have been designed, fabricated and tested in both research and commercial orchards from 2009 to 2013. Repeated field trials verified that the tree training will play a big role in the effectiveness of mechanical harvest; harvesting efficiency varied from only 50% of hand picking on traditional tree canopy to 10 times faster from “Y-trellis” fruiting wall trees. The WSU team also worked on fresh market apple harvesting concepts. Pattern shaking, linear shaking and twisting mechanisms were evaluated to detach fruit from stem. Effectiveness of these systems depended on apple variety. Mechanical-assist technologies were also extensively studied to improve the harvesting efficiency in fresh market apple harvest. Four different platforms, including mobile carrier and pneumatic fruit conveyer, were tested in commercial orchards. Economic and safety analysis of using such platforms were also performed. The mechanical-assist technology developments also included the study of a robotic solution for bin handling in high density apple and cherry orchards to improve both the worker efficiency and safety in orchards. (3) Specialty crop postharvest handling, quality and safety. An optical flow cell and automated maturity measurement system using color were developed for use in official inspection by the California Processing Tomato Inspection Program. This system provides tomato growers and processors with new tools needed for precise and unbiased assessment of tomatoes at harvest to facilitate accurate determination of market value. In Georgia, a multimodal machine vision system was developed for quality inspection of onions. The system integrates hyperspectral, color, 3D, and X-ray imaging technologies to evaluate multiple onion quality properties nondestructively, such as diameter, volume, and density. This multimodal machine vision system was also able to detect defective onions (Burkholderia cepacia and Pseudomonas viridiflava infected) more effectively (84.21%) than using a single sensor (78.95% and lower). Blueberry packing lines were evaluated using the Berry Impact Recording Device (BIRD). Six replicates were tested through the packing line before and after five transition points were padded using Poron padding sheet and impacts were recorded at the transition points. The biggest impacts occurred at the beginning and end of the line. The impact level was reduced significantly at these transition points after padding. Green bean coffee heat treatment facility was reconfigured in Hawaii, which helps control the coffee berry borer (CBB). Dielectric spectroscopy and X-ray imaging were used to estimate quality of in-shell pecans. Optical sensors and algorithms were developed to predict plant N status for nitrogen management. Output: The W2009 members collectively published about 65 research papers, the majority of which were published in well-recognized, peer reviewed journals. The research outputs have been summarized in these publications. In addition, significant contributions were made through workshops, conferences, field demonstrations, online materials, extension materials, etc. The growers and other stakeholders are involved in these projects with significant contribution in terms of knowledge and other inputs. Numerous students and researchers have been trained in these areas of research. The research stations will continue to work on their specific projects that contribute towards the goals of this project.

Publications

1. Fennimore, S.A., B. D. Hanson, L. M. Sosnoskie, J. B. Samtani, A. Datta, S. Z. Knezevic, and M. C. Siemens. 2013. Chapter 9: Field Applications of Automated Weed Control: Western Hemisphere. In Automation: The Future of Weed Control in Cropping Systems, 151-169. S.L. Young and F.J. Pierce, eds. Dordrecht: Springer Science+Business Media. 2. Aksenov, A. A., A. Pasamontes, D. J. Peirano, W. Zhao, A.M. Dandekar, O. Fiehn, R. Ehsani and C. Davis. 2014. Detection of Huanglongbing Disease Using Differential Mobility Spectrometry. Analytical Chemistry. 86(5):2481-2488. 3. Arikapudi, R., Durand-Petiteville, A., Vougioukas, S. (2014). Model-based assessment of robotic fruit harvesting cycle times. ASABE Annual Intl. Meeting; Paper Number 1913999, Montreal, Quebec, Canada. 4. Bansal, R., W. S. Lee, and S. Satish. 2013. Green citrus detection using Fast Fourier Transform (FFT) leakage. Precision Agriculture 14(1): 59-70. <a href="http://dx.doi.org/10.1007/s11119-012-9292-3.">http://dx.doi.org/10.1007/s11119-012-9292-3. </a> 5. Bao, Y., A. D. Nakarmi, L. Tang. 2014. Develooment of a filed phenotyping robotic system for sorghum biomass yield component traits characterization. ASABE Paper No. 141901199, St. Joseph, MI: ASABE.' 6. Baugher, T.A., P.H. Heinemann, J.S. Schupp, and K.M. Lewis. 2013. Innovations in peach thinning. Compact Fruit. 46(3):23-25. 7. Blossom thinning device for fruit trees. Applied Engineering in Agriculture. 29(2): 155-160. 8. Caplan, S., B. Tilt, G. Hoheisel, T. Baugher. 2014. Specialty crop growers’ perspectives on adopting new technologies. HortTechnology 24: 81-87. 9. Choi, D., W. S. Lee, R. Ehsani, and A. Banerjee. 2013. Detecting and counting citrus fruit on the ground using machine vision. ASABE Paper No. 131591603. St. Joseph, Mich.: ASABE. 10. Du, X., Chen, D., Zhang, Q., Scharf, P.A., Whiting, M.D. (2013). Response of UFO (upright fruiting offshoots) on cherry trees to mechanical harvest by dynamic vibratory excitation. Transactions of the ASABE. 56(2): 345-354. 11. Dvorak, J., Hasani, H. 2014. Testing of Tablet-Based GPS Systems. ASABE Paper No. 141922411. St. Joseph, Mich.: ASABE Engineering.114(3): 344–350. 12. Farangis Khosro, A., Rehal, R., Fathallah, F., Wilken, K., Vougioukas, S. (2014). Sensor-based Stooped Work Monitoring in Robot-aided Strawberry Harvesting. ASABE Annual Intl. Meeting; Paper Number 1913911, Montreal, Quebec, Canada. FL. pp. 263-294. 13. Garcia-Ruiz, F., S. Sankaran, J. M. Maja, W. S. Lee, J. Rasmussen, and R. Ehsani. 2013. Comparison of two aerial imaging platforms for identification of Huanglongbing infected citrus trees. Computers and Electronics in Agriculture 91: 106-115. http://dx.doi.org/10.1016/j.compag.2012.12.002 14. Hanna, H. M., B. L. Steward, and K. A. Rosentrater. 2014. Evaluation of mechanized row cover establishment for cantaloupe and summer squash. ASABE Paper No. 141894433. St. Joseph, Mich.: ASABE. 15. Hardin, J. A., C. L. Jones, P. R. Weckler, N. O. Maness, J. W. Dillwith, and R. D. Madden. 2013. Rapid in situ Quantification of Leaf Cuticular Wax Using FTIR-ATR. Transactions of the ASABE, 56(1): 331-339. 16. Hardin, J. A., P. R. Weckler, and C. L. Jones. 2013. Microwave Backscatter Response of Pecan Tree Canopy Samples for Estimation of Pecan Yield in situ Using Terrestrial Radar. Computers and Electronics in Agriculture. 90 (2013): 54-62. 17. He, L., Arikapudi, R., Khosro Anjom, F., Vougioukas, S. (2014). Worker Position Tracking for Safe Navigation of Autonomous Orchard Vehicles Using Active Ranging. ASABE Annual Intl. Meeting; Paper Number 141913710, Montreal, Quebec, Canada. 18. He, L., Zhang, Q., Charvet, H. (2013). A knot-tying for robotic hop twining. Biosystems Engineering.114(3): 344–350 19. He, L., Zhou, J., Du, X., Chen, D., Zhang, Q., Karkee, M. (2013). Energy efficacy analysis of a mechanical shaker in sweet cherry harvest. Biosystems Engineering, 116(4): 309-315. 20. Jadhav, U., L. R. Khot, R. Ehsani, V. Jagdale, J. K. Schueller. 2014. Volumetric mass flow sensor for citrus mechanical harvesting machines. Computers and Electronics in Agriculture. 101: 93-101. 21. Jiang, Yu and C. Li. A Push-broom based Hyperspectral Imaging System for Cotton Trash Identification. ASABE Paper No: 141898244. Montreal, Quebec Canada. July 13-16, 2014. 22. Karkee, M., Steward, B. Kruckeberg, J. (2013). Agricultural infotronic systems. In: Zhang, Q., 23. Katti, A. R., W. S. Lee, and C. Yang. 2013. Laser weeding system for elimination of in-row weeds. In Proceedings of the 5th Asian Conference on Precision Agriculture (ACPA), June 25-28, 2013, Jeju, Korea. 24. Khedher Agha, M. K., W. S. Lee, C. Wang, R. W. Mankin, N. Bliznyuk, and R. A. Bucklin. 2013. Determination degrees of insect infestation in triticale seed using NIR spectroscopy. ASABE Paper No. 131592957. St. Joseph, Mich.: ASABE. 25. Khedher Agha, M. K., W. S. Lee, R. A. Bucklin, A. A. Teixeira, and A. Blount. 2013. Equilibrium moisture content equation for triticale seed. ASABE Paper No. 131620333. St. Joseph, Mich.: ASABE. 26. Lee, W. S. 2013. Book review: N. Kondo, M. Monta, and N. Noguchi, Agricultural robots - mechanisms and practice, Corona Publishing Co., Ltd. Tokyo, Japan, 2011, xii + 348 pp., ISBN: 978-4-87698-553-1. Journal of Biosystems Engineering 38(2): i. 27. Li, C., P. Yu, F. Takeda, G. Krewer. 2013. A miniature instrumented sphere to understand impacts created by mechanical blueberry harvesters. HortTechnology. 23(4): 425-429. 28. Li, H., W. S. Lee, and K. Wang. 2013. Airborne hyperspectral imaging based citrus greening disease detection using different dimension reduction methods. ASABE Paper No. 131592802. St. Joseph, Mich.: ASABE. 29. Li, H., W. S. Lee, and K. Wang. 2013. Spectral mixture analysis based citrus greening disease detection using satellite image of Florida. In Proceedings of the 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). 25-28 June 2013, Gainesville, Florida, USA. 30. Li, H., W. S. Lee, K. Wang, R. Ehsani, and C. Yang. 2013. ‘Extended spectral angle mapping (ESAM)’ for citrus greening disease detection using airborne hyperspectral imaging. Precision Agriculture. <a href="http://dx.doi.org/10.1007/s11119-013-9325-6.">http://dx.doi.org/10.1007/s11119-013-9325-6. </a> 31. Li, J. and L. Tang. 2013. Machine Vision-based Indirect Estimation of the Position and Attitude of Mobile Robots. ASABE Paper No. 131620769, St. Joseph, MI: ASABE. 32. Li, J. and L. Tang. 2013. Real-time Plant Recognition for Robotic Weeding Using a 3D ToF Sensor. ASABE Paper No. 131620787, St. Joseph, MI: ASABE. 33. Li. H, W. S. Lee, K. Wang, R. Ehsani, and C. Yang. 2014. Extended spectral angle mapping (ESAM) for citrus greening disease detection using airborne hyperspectral imaging. Precision Agriculture 15:162-183 34. Liaghat, S. *, Ehsani, R., Mansor, S.B., Shafri, H.Z.M., Meon, S., Azam, S.H.M.N. and Noh, N.M.2014. Early detection of basal stem rot disease (Ganoderma) in oil palms based on hyperspectral reflectance data using pattern recognition algorithms. International Journal of Remote Sensing, 35:10, 3427-3439. 35. Liaghat, S., S. Mansor, R. Ehsani, H.Z.M. Shafri, S. Meon and S. Sankaran. 2014. Mid-infrared spectroscopy for early detection of basal stem rot disease in oil palm. Computers and Electronics in Agriculture 101: 48-54. 36. Mathanker, S. K., P. R. Weckler, N. Wang. 2013. Thz Applications In Food And Agriculture: A Review, Transactions of the ASABE. 56(3): 1213-1226. 37. He, L., Zhou, J., Du, X., Chen, D., Zhang, Q., Karkee, M. (2013). Energy efficacy analysis of a mechanical shaker in sweet cherry harvest. Biosystems Engineering, 116(4): 309-315. 38. Nakarmi, A. D. and L. Tang. 2014. Within-Row spacing sensing of maize plants using 3D computer vision. Biosystems Enngineering PP. 54-64 DOI Information: 10.1016/j.biosystemseng.2014.07.001 39. Pierce, F.J. (eds). Agricultural Automation Fundamentals and Practices, CRC Press, Boca Raton, 40. Pourreza, A., W. S. Lee, E. Raveh, R. Ehsani, and E. Etxeberri. 2014. Citrus greening disease detection using narrow band imaging and polarized illumination. Transactions of the ASABE. 57(1): 259-272. 41. Pourreza, A., W. S. Lee, E. Raveh, Y. K. Hong, and H. J. Kim. 2013. Identification of citrus greening disease using a visible band image analysis. ASABE Paper No. 131591910. St. Joseph, Mich.: ASABE. 42. Saber, M., W. S. Lee, T. F. Burks, G. E. MacDonald, and G. Salvador. 2013.An automated mechanical weed control system for organic row crop production. ASABE Paper No. 131593595. St. Joseph, Mich.: ASABE. 43. Schupp, J., T. Auxt Baugher, P. Heinemann, E. Winzeler, T. Kon and M. Schupp. 2013. Labor efficient apple and peach production. Compact Fruit 46(2):17-19. 44. Siemens, M.C. Robotic weed control. 2014. In Proc. 66th Annual California Weed Science Society 66: 76-80. Salinas, Calif.: California Weed Science Society. 45. Slaughter, D.C., (2014). Standardization and Automation in Official Maturity Grading of Processing Tomato. ASABE Annual Intl. Meeting; Paper Number 1900557, Montreal, Quebec, Canada. 46. Takeda, F., G. Krewer, C. Li, D. MacLean, and J. W. Olmstead. 2013. Techniques for increasing machine-harvest efficiency in southern highbush and rabbiteye blueberries. HortTechnology. 23(4): 430-436. 47. Taufik Ahmad, M., L. Tang, B. Steward. 2013. Chapter 7: Automated Mechanical Weeding. Automation: The Future of Weed Control in Cropping Systems. S. L. Young and F. J. Pierce (eds). Springer. P 125 – 138. 48. Toledo, O. M., B. L. Steward, L. Tang, and J. Gai. 2014. Techno-economic analysis of future precision field robots. ASABE Paper No. 141903313. St. Joseph, Mich.: ASABE. 49. Tu, X. Y. and L. Tang. 2013. Robust Navigation Control of an Autonomous Agricultural Robotic Vehicle. ASABE Paper No. 131620548, St. Joseph, MI: ASABE. 50. Wang, M. (2013). A Hand-Held Mechanical Device for Target Blossom Thinning in Sweet Cherry. Ph.D. Dissertation, Washington State University. 51. Wang, M., Wang, H., Zhang, Q., Lewis, K.M., Scharf, P.A. (2013). A hand-held mechanical blossom thinning device for fruit trees. Applied Engineering in Agriculture. 29(2): 155-160. 52. Wang, N. 2013. Challenges and opportunities of nondestructive sensing technology in food and agricultural applications. The 9th International Workshop on Nondestructive Quality Evaluation of Agricultural, Livestock, and Fishery Products. November 19-22, 2013. Taipei, Taiwan. (Invited) 53. Wang, W. and C. Li. 2014. Size estimation of sweet onions using consumer-grade RGB-depth sensor. Food Engineering. 142: 153–162. 54. Wang, Weilin and C. Li. A multimodal quality inspection system based on 3D, hyperspectral, and X-ray imaging for onions. ASABE Paper No: 141900673. Montreal, Quebec Canada. July 13-16, 2014. 55. Wang, Weilin. A multiple sensor system for quality inspection of onions and investigation of onion optical properties. Ph.D. Dissertation. University of Georgia. December, 2014. Athens, Georgia. 56. Wei-jiunn, J., Lewis, G., Hoachuck, J., Slaughter, D., Wilken, K., Vougioukas, S. (2014). Vibration-reducing Path Tracking Control for a Strawberry Transport Robot. ASABE Annual Intl. Meeting; Paper Number 1914011, Montreal, Quebec, Canada. 57. Xu, Rui, Changying Li, Fumiomi Takeda, and Gerard Krewer. Measuring Impacts of Blueberries during Transportation and Packing. ASABE Paper No: 141898243. Montreal, Quebec Canada. July 13-16, 2014. 58. Yang, C., W. S. Lee, and P. Gader. 2013. Band selection of hyperspectral imagery for the classification of blueberry fruit maturity stages and leaf. ASABE Paper No. 131593276. St. Joseph, Mich.: ASABE. 59. Yang, C., W. S. Lee, P. Gader, and H. Li. 2013. Hyperspectral band selection using Kullback-Leibler divergence for blueberry fruit detection. In Proceedings of the 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). 25-28 June 2013, Gainesville, Florida, USA. 60. Yu, P., C. Li, F. Takeda and G. Krewer. 2014. Visual bruise assessment and analysis of mechanical impact measurement in southern highbush blueberry. Applied Engineering in Agriculture. 30(1): 29-37. 61. Yu, P., C. Li, F. Takeda, G. Krewer, G. Rains, and T. Hamrita. 2014. Evaluation of rotary, slapper, and sway blueberry mechanical harvesters for potential fruit impact points using a miniature instrumented sphere. Comput. Electron. Agr. 101:84–92. 62. Zhang, Q., Pierce, F.J. (2013). Agricultural Automation Fundamentals and Practices. CRC Press, Boca Raton, FL. (397p). 63. Zhang, Q., Shao, Y., Pierce, F.J. (2013). Agricultural infotronic systems. In: Zhang, Q., Pierce, F.J. (eds). Agricultural Automation Fundamentals and Practices, CRC Press, Boca Raton, FL. pp. 41-62. 64. Zhao, Z., P.H. Heinemann, J. Liu, J.R. Schupp, and T.A. Baugher. 2014. Design, fabrication, and testing of a low-cost apple harvest-assist device. ASABE Paper No. 141839738. American Society of Agricultural and Biological Engineers. 13 pp. 65. Zhou, J., He, L., Zhang, Q., Du, X., Chen, D., Karkee, M. (2013). Evaluation of the Influence of Shaking Frequency and Duration in Mechanical Harvesting of Sweet Cherry. Applied Engineering in Agriculture, 29(5): 607-612.

Impact Statements

The geo-referenced location data of fruits in tree canopies and the tree branch geometries will be used to perform model-based machine design for tree fruit mechanized harvesting. The potential impact is reduced dependence on manual labor for fresh market fruit harvest
The development of an accurate, automated system for determination of color and maturity in processing tomato will directly impact tomato growers and processors by providing a cost-effective and accurate system of characterizing the stage of development and subsequent quality of the harvested fruit. Well mature tomato fruit have superior flavor and lycopene content. By ensuring that harvested tomatoes are mature, the health benefits of adding lycopene to the diet and the pleasure of consuming flavorful food can be delivered to consumers in the final processed tomato product.
The multisensor-based system can evaluate both external and internal quality parameters of onions, and provided a base for the further development of fully automated robotic system for onion quality inspection. The system and methods developed from this project are also potentially applicable to quality inspection of other agricultural products.
The low operating cost ? approx. $20 per lot ? will encourage compliance with the coffee berry borer (CBB) quarantine of Hawaii County. Compliance should delay, if not prevent, the movement of CBB coffee farms on the other islands of the State of Hawaii. Savings and increased markets will be experienced for Hawaii County coffee producers shipping to the high population and high tourist activity islands of Oahu and Maui.
Automated non-chemical weeding could achieve good weed control efficacy mechanically at substantially lower power levels than previously considered. Such technology has potential for broad impact as it opens the way to the development of smaller autonomous, mechanical weeding systems. Small robotic weeding system for specialty crops may substantially lower energy costs for producers.
Development of a series hybrid drivetrain allows combining the simplicity, controllability and efficiency of electric motors with the energy density of liquid fuels. It also permits operation of the internal combustion (IC) engine at its most energy efficient point. A further benefit is the decoupling of the power source from the ground drive.
In Oklahoma, native pecan production accounts for about 90 percent of the state?s crop. Accurate estimates of pecan yields prior to harvest are critically important for both production management decisions and marketing. Producers continually seek methods to improve orchard management, including nitrogen fertilization. Rapidly escalating nitrogen (N) costs have made this a high priority among pecan producers nationwide.
A few devices have been validated in extensive field trials in commercial orchards/farms in Washington. It includes, but not limited to, hand-held mechanical blossom thinners, orchard harvest labor management systems, high-density orchard light penetration measurement system, robotic twining machine for hop production, and site-specific precision irrigation control system for apple orchard. Among them, the technology of hand-held blossom thinning device and orchard harvest labor management system has been made available to local equipment fabricators for promoting the commercialization of research outcomes as useful tools for growers.

Date of Annual Report: 11/03/2015

Report Information

Annual Meeting Dates: 09/17/2015 - 09/18/2015
Period the Report Covers: 10/01/2014 - 09/01/2015

Participants

Vougioukas, Stavros G (svougioukas@ucdavis.edu) University of California, Davis

Changying Li (cyli@uga.edu), College of Engineering, University of Georgia

Harald Scherm, College of Agricultural and Environmental Sciences, University of Georgia

Jinru Chen, College of Agricultural and Environmental Sciences, University of Georgia

Heinemann, Paul (hzh@psu.edu) Pennsylvania State

Schupp, James (jrs42@psu.edu) Pennsylvania State

Baugher, Tara (tab36@psu.edu) Pennsylvania StateBr>
Liu, Jude (jxl79@psu.edu) Pennsylvania State (attended 2015 project meeting)

Gallardo,Karina (karina_gallardo@wsu.edu) Washington State University

Lewis, Karen (kmlewis@wsu.edu) Washington Cooperative Extension

Karkee, Manoj (manoj.karkee@wsu.edu) Washington State University

Khot, Lav (lav.khot@wsu.edu) Washington State University;
Mo, Changki

Taylor, Matthew

Zhang, Qin (qinzhang@wsu.edu) Washington State University

Hollinger, Geoffrey (Oregon State University)

Brief Summary of Minutes

The meeting started at 8:30 am.

Professor Raj Khosla was acting president. In the beginning the attendees introduced themselves.

Administrative Advisor Jim Moyer spoke first about the WSU College of Agriculture, Human, and Natural Resources and the Department of Biological Systems Engineering. He proposed that the committee communicate achievements with Deans, Directors of Ag Experimental Stations and NIFA. He also stressed the importance of administrative work, i.e., reporting and highlighting the impacts of projects so that research money is justified for.

Raj Khosla concurred and added that papers and other types of impact should be included in the reports. Reports are due 60 days after the meeting in the same format as last year, but the President would like to have them in advance to work on them. Professor Clark Sievert commented on how some results on the economics of platforms came much earlier and it took 4-5 years for growers to adopt and on how they improved the life of workers, which is something that cannot be translated into monetary units.

REPORTING

1. Renfu Lu

Research Update on: a) Nondestructive Quality Assessment for Horticultural Products. Three area of focus: Sensor development; Property Characterization; Model/Algorithm Development. B) Field sorting of apples in the field: bin handling and sorting based in machine vision.

2. Daniel Guyer (delivered by Renfu Lu)

Report covered the following topics: Optimization of Computer Tomography (CT) Imaging for quality of specialty crops. Detection of fiber in carrots and asparagus, late blight in potato tubers, cherries, chestnuts, pineapple and cucumber. Over-the-row tart cherry harvester development.

3. Mark Siemens

He reported on the progress done on a precision intra-row weeding machine (SCRI project 2014) and an automated intra-row cultivator.

4. Clark Sievert

He reported on the commercialization of precision farming technologies and talked about web-based ag economics tools (AgBiz Logic company); UAV Technologies; Telemetry of data to AgBiz Logic; and economic study of mechanical harvesting of tree fruits.

5. Paul Heinemann (delivered by Jude Liu)

The report covered the design, testing, and improvement of a low-cost harvest assist platform. Efficiency and ergonomics (RULA – Rapid Upper Limb Assessment) were also discussed.

6. Qin Zhang

Delivered a summary of the CPAAS presentations. Commented on some technologies that are ready for commercialization but due to small market size it has been challenging to find commercial partners. Also, the smaller size of the Departments dictates tight collaboration with complementary capabilities. Discussion included how we should include extension activities in our reporting as well as in future proposals.

7. Loren Gautz

Report on latest results on Kava juice preparation and Cacao seed micro-fermentation.

8. Filip To.

Reported on crops, poultry and wildlife at Mississippi State. Topics: Rice intermittent irrigation; Poultry hatching improvement; Feral Swine.

9. Mike Delwiche (presented by Stavros Vougioukas)

Wireless sensing and actuation technology. Company was formed for commercialization.

10. David Slaughter (presented by Stavros Vougioukas)

Hyperspectral imaging for fungi detection in almonds.

11. Stavros Vougioukas

Report on mechanization for specialty crops. Presentation covered an instrumented cart for yield mapping of strawberries during manual harvesting and new results on model-based design using tree geometries and fruit locations acquired via digitization.

BUSINESS ITEMS

Election of Secretary.

Renfu Lu was unanimously voted Provisional Secretary. Once he officially joins the Working Group he will become Secretary.

Selection of location for next year.

Arizona was unanimously voted as the location for the next meeting. Time will be scheduled at a later time.

The group will receive a reminder from Raj’s secretary about the reports.

Qin Zhang suggested the formation of common interest groups within the Working Group to form “Sub-Committees” with the aim of collaborative work on new proposals, etc.

ANNOUNCEMENTS

Qin Zhang announced the 2016 AgriControl IFAC conference, which will take place in Seattle and is organized by WSU.

The meeting ended at 1 pm.

Accomplishments

Arizona A multi-state SCRI project was initiated to develop a precision weeding machine for controlling intra-row weeds at the centimeter level scale of accuracy. The machine will use a machine vision system for plant detection and herbicidal spray to kill weeds. A test stand was developed to evaluate the suitability of various spray assemblies for delivering herbicidal materials. One spray assembly was identified that shows great promise for meeting the design criteria. At travel speeds of 2 mph, droplet size was less than 7 mm diameter and non-target drift was less than 10%. Future work includes researching how to improve system performance and identify other suitable assemblies. A project was also initiated to determine the feasibility of using commercially available robotic cultivators in U.S. vegetable production. These cultivators are designed to remove both inter-row and intra-row weeds. Five studies were conducted in California and Arizona. Study results showed that in fields where weed pressure was high, weeding labor requirements and total weeding costs were reduced by 29-45% and 12-20% ($11-18 /acre) respectively. An extensive outreach effort about these findings and potential for this technology was made by making presentations at meetings (2), hosting field days (3) and conducting on-farm demonstrations (10). California Short-term Outcomes: Yield maps were created for several bed rows of a strawberry field using a novel instrumented picking cart. An expected outcome is the adoption of such carts by growers to understand yield spatial variability in their fields. Outputs: A paper was presented at the ASABE Intl. Meeting, at New Orleans about the instrumented cart. Activities: A physics-based simulator was developed to model the drop of fruits and their interception in the context of shake-and-catch mechanical harvesting. An instrumented cart was designed, built and tested to monitor strawberry harvesting speed and produce spatial yield maps for manually harvested strawberries. A motion sensor was developed that fits in a strawberry picker’s glove and records picking motions. Milestones: Fruit fall simulator debugged and functional – December 2015. Field-testing of strawberry yield-monitoring cart with glove motion sensor– November 2015. Georgia: A multimodal machine vision system integrating hyperspectral, 3D, and X-ray imaging sensors was developed to evaluate quality factors of onions holistically and nondestructively. A LabVIEW program was developed to acquire color images, spectral images, depth images, X-ray images of onions, and measure the weight of onions. With the multimodal data collected, algorithms were developed to accurately measure the weight (RMSE = 3.6 grams), diameter (RMSE = 1.7 mm), volume (RMSEP = 16.5 cm3), and density (RMSE = 0.03 gram/cm3) of onions, as well as to correctly classify 88.9% healthy and defective onions. This work demonstrated the efficacy of a multimodal imaging system to non-destructively evaluate both external and internal quality parameters of onions, which is also applicable to quality inspection of other agricultural products in packing houses. The optical properties (absorption coefficient ?a, scattering coefficient ?s, and scattering anisotropy g) of onion tissues were investigated using both a single wavelength (633 nm) and a broad spectrum (550-1650 nm). Based upon the measured optical properties of healthy and diseased onion tissues, Monte Carlo simulation was conducted to model the light propagation in multi-layer onion tissues in healthy, Botrytis neck rot and sour skin infected onions. This work could help develop more effective spectroscopic imaging method for onion quality sensing. A customized gas sensor array system consisting of seven Metal Oxide Semiconductor (MOS) sensors was developed to detect onion postharvest diseases in storage. These MOS sensors were enclosed in a specially designed Teflon chamber equipped with a gas delivery system to pump volatiles from the onion samples into the chamber. The electronic circuit comprised of a microcontroller, non-volatile memory chip, and trickle-charge real time clock chip, serial communication chip, and parallel LCD panel. User preferences are communicated with the on-board microcontroller through a graphical user interface developed using LabVIEW. Three features were extracted from the sensor responses and three baseline correction methods were employed to correct the sensors’ responses. The gas sensor array was tested in two separate experiments with two treatments (control and sour skin infected bulbs). The best performance (85%) was achieved by using the support vector machine model when the data collected from an independent experiment were used for validation. Dr. Li received a major research grant from USDA NIFA competitive grant program Specialty Crop Research Initiative in September 2014. As the Project Director, Dr. Li leads a multidisciplinary team from 10 institutions to develop innovative sensing technologies and semi-mechanical harvesting technologies for fresh market blueberries. The team will develop a high-throughput phenotyping system using imaging techniques to help select blueberry cultivars for mechanical harvestability. An affordable and efficient mechanical harvest-aid system will be designed and fabricated as an alternative to over-the-row harvesters to replace hand harvesting. To adopt mechanical harvest-aid technology, the harvested fruit must have less bruising and better quality for the fresh-market and longer shelf life. Therefore, it is critical to use advanced sensor technologies to understand the mechanical impacts encountered by the fruit during the process of harvesting and postharvest handling and use the information to improve harvesters and packing lines. Finally, microbial contamination has been a top concern for growers and consumers. The team will investigate the potential microbial contamination in both blueberry fruit and mechanical harvesters and determine critical control points along the harvest and postharvest chain with the new harvest system. The second generation BIRD sensor (BIRD II) was developed and tested in multiple packing lines in the US. The BIRD II sensor has a size of 21 mm in diameter and weight of 3.9 g, which was reduced by 17% in size and 50% in weight compared to BIRD I. The sensor was able to measure accelerations up to 346g at a maximum frequency of 2 KHz. Universal Serial Bus (USB) was used to directly connect the sensor with the computer, removing the interface box used previously. A LabVIEW based PC software was designed to configure the sensor, download, and process the data. The calibration tests showed that the accuracy of the sensor was between -1.76 to 2.17g and the precision was between 0.21 to 0.81g. Dynamic drop tests showed the BIRD II had smaller variance in measurements than BIRD I. In terms of size and weight, BIRD II is more similar to an average blueberry fruit than BIRD I, which leads to more accurate measurements of the impacts for blueberries. Hawaii: The Hawaii Experiment Station has concentrated its activities on cacao bean fermentation and kava beverage preparation. The cacao bean fermentation is in support of small (less than 100 kg chocolate per year) tree to bar grower/processors and variety trials in Hawaii. Both require processing of cacao beans from a few pods at a time. Small (200g to 20kg) lots of beans have substantial edge effects for temperature and moisture loss. Microbial growth is affected by these edge effects results in low quality chocolate from highly variable fermentations. We have developed a system using single use plastic bags in a temperature and humidity controlled insulated box. Freezers, refrigerators, or coolers can serve as the insulated box. An electric heater with a ramp controller (a simple controller with set point adjusted every 8hr can also be used) brings the box to 48°C over a 48hr period and lowers it to ambient again in 72-96hr. Humidity is brought to saturation at the required temperature by bubbling air through at least 30cm water column at the box temperature. Kava beverage is traditionally prepared by macerating below ground plant parts in water. Our studies using sequential fractional factorials to determine the gradient and line searches on the gradient found that we could substantially increase the amount of beverage prepared from a given quantity of below ground plant parts. On average 45% of the available active kavalactones can be extracted, a significant improvement over the method commonly used by commercial purveyors of a kava beverage. The recommended method for water extraction of kavalactones is to: use 1.5 ml of 37 °C water per gram of fresh or fresh frozen kava root and stump (Add 4 ml per gram of dried kava powder to first repetition); put in blender of sufficient power to maintain 16000 rpm under the load of the quantity of kava beverage being prepared; blend for 90 s; press liquid from blended infusion; repeat the preceding steps 3 times. Iowa: In the past year, we have been developing innovative solutions to address some of the technical challenges in sensing, automation, and mechanization of specialty crop production. Specifically, we have been developing new sensing systems for crop detection and characterization, a design of the actuation system for intra-row weed control, mechanism for cucurbit row cover establishment, and yield monitor technologies for specialty crops. Cucurbit mechanized row cover establishment: During the past year, an ASABE paper was presented on field evaluation of multi-row cover structures for cucurbit crops. Undergraduate students did an economic comparison of row cover versus chemical pest management strategy for cucurbits and evaluated operation of a mechanized tunnel layer for row covers in two different soils. Yield monitor technologies for specialty crops: Research activities have focused on the development of yield monitoring technologies for bulk harvested crops such as sugarcane, energy cane, and specialty crops which currently do not have any available yield monitoring tools. Basic research has been conducted on sensor characterization and in-field performance of yield monitoring systems in broad environmental conditions. Robotic weed control: A new set of plant detection algorithms based on 3D and 2D morphology and color have been developed and are currently under evaluations using field images of different plant species of different growth stages. The design of our dual pivoting arm mechanism has been refined and both electric and hydraulic drives were incorporated for prototyping and further field testing. High-throughput plant phenotyping using robotic technologies: Robotic vehicles that are equipped with auto-steer system, stereo cameras, NIR-converted RGB cameras, and ToF 3D sensors have been developed and deployed in field for collecting images from corn and sorghum plants. Image processing algorithms with GPU accelerated parallel computation have been under development. Kentucky: The autonomous diesel/electric hybrid tractor was tested in the field pulling a finger weeder for intra-row cultivation in growing vegetable corn. Power measurements were made during this finger weeding operation to determine ultimate energy requirements for a machine. It consumed approximately 4 kW and maximum energy requirements based on 5 acres per single operation would be only 20 kWh. The autonomous navigational accuracy of the system was also tested according to ISO 12188-2. Max cross-track (XTR) error was just under 25 cm, while mean and median XTR were between 10 and 13 cm depending on speed. The system was also tested as an autonomous harvest aid. It was capable of autonomously traveling to a field, driving along the field and returning to a packing shed on an organic farm. Travel speeds could be controlled to 0.1 m/s or 1 m/s, and this navigation was possible even without RTK corrected GPS locations. Michigan: Toward multi-state project objectives 2, 5, and 6: Continued progress was made in moving forward on a project for over-the-row (OTR) systems for tart cherry production. The concept of canopy shaking for harvest has been demonstrated under this multi-state in previous years and the project this year focused on a harvester from a new commercial equipment manufacturing collaborator in addition to continued evaluation of plant structure systems and plant materials. Trial and research plant growth plots being developed and studied for dwarfing for the purpose of OTR production were evaluated for yield and canopy harvest compatibility. Harvest was conducted with an unmodified self-propelled OTR blueberry canopy spindle shaker harvester. Several replicated plant development/structure trials are in their third and fourth year after planting and this year produced encouraging yields, even with poor fruit set in some locations, as well as encouraging response to maintaining dwarfing size to accommodate the harvester over the life of the orchard. Toward objective 6: A new commercial collaborator was identified and participated in the harvest evaluation studies as well as the collaboration on a multi-state USDA-NIFA-AFRI proposal, which is currently pending. We await more substantial funding for this sub-project to theoretically and empirically study fruit detachment dynamics, however, the harvester system as it currently exists (unmodified) quite successfully removes fruit with a high level of efficiency and quality. Toward objectives 1 and somewhat 4: Computed tomography (CT), and in some cases coupled with parallel studies of hyperspectral imaging and spectroscopy, were implemented to study internal characteristics/defects of carrots, asparagus, and chestnuts which are not detectable by any current commercial technology. CT under this project, and as published in the noted associated articles, has demonstrated very encouraging results in detecting, and even sorting into classes, various defects and undesirable internal characteristics. Such have included woody and gelatinous fiber in carrots, fibrous/stringy material in asparagus, as well as physiological and microbial disorders in chestnuts. The basic research related to this study has gone very well, however, the establishment of collaboration with potential technology development remains a challenge and goal. Thus, the focus over the past has been on broadening the application potential and consequently improving the attractiveness for such development. Toward objectives 1 and 4: A proposal was developed and submitted to and internal MSU program (Project GREEEN) to synergistically study the potential of CT as a tool in better quantifying, and overall understanding, the identification and development of the very detrimental and broadly impacting disease of potato late blight. The proposal was funded, however, the accompanying and more substantial partner proposal with USDA-ARS was not funded and thus the study did not move forward at this point. Penn state: Apple harvest assist: A low-cost harvest-assist device for apple orchard platforms was designed and fabricated. The device had four main components: receiver (where pickers placed the apples), two transport tubes, manifold, and distributor (which distributed the apples into a standard bin). Field testing utilizing a redesigned distributor reduced downgrading of apple quality to 5%. Ergonomic analysis showed that the time spent by pickers in awkward positions, which can lead to stress injuries, was significantly reduced by utilizing the harvest-assist unit. The most hazardous positions, high picking on a ladder, were completely eliminated, as well as all other operations associated with picking from ladders. Further funding from the College of Ag Sciences at Penn State and the Penn State Research Foundation helped to provide market analysis and IP development for the project. Grower surveys showed that small operations (50 acres or less) were more inclined to have interest in such a device if the platform and harvest-assist device total cost was less than $35,000. A patent application was submitted for the harvest-assist device, and discussions with potential licensees has continued. Automated pruning: Studies with tall spindle apple canopies have indicated that pruning rules may not need to be overly complicated to adequately describe optimal pruning. Preliminary results suggest that the number of primary branches emanating from the trunk may be the most important factor, while including additional detail such as secondary, tertiary or quaternary branching patterns adds considerable complexity but may not add significant benefits. Research is continuing to determine the optimum severity of pruning, and these data will be used in algorithms to determine optimal pruning points. An additional study with apple trees trained to a vertical axis tree form indicated that pruning trees according to a set of rules had similar effects as pruning by orchard crews or researchers. The rural sociologists at Penn State made progress on completing the interviews that will inform the future survey design. Currently, they have traveled to 4 states to conduct interviews with apple and wine-grape growers: NY Apple: 9 NY Grape: 6 PA Apple: 9 PA Grape: 5 WA Apple: 7 CA Apple: 7 CA Grape: 2+ Total: 45+ They also interviewed one agribusiness representative who serves fruit growers in Canada and the US, and conducted a small survey of 40 California wine-grape growers. Although the exact operating characteristics of an autonomous apple pruner are unknown, the minimum operating characteristics of such a machine can be estimated. For example, ground speed can be estimated if additional assumptions about the length of the operating season are made. If it is assumed that such a machine could be operated for 12 weeks per season, the minimum speed required to justify the purchase of a $120,000 machine would vary from a low of 2.7 feet per minute to 12.6 feet per minute depending on the pruning cost per tree. If such a machine could be developed that could operate at ground speeds of 4-6 feet per minute, it would be economical for a wide range of high-density plantings. Washington: Development of mechanization and automation technologies for specialty crops production has been one of major focuses for the WSU research team. In the past year the team has focused on conducting the following researches on, but not limited to: (1) human-machine collaboration for robotic harvesting of fresh market apples; (2) shaking and catching harvesting of fresh market apples; (3) robotic bin management system in tree fruit orchards; (4) robotic weeding for vegetable production, and (5) heat treatment-based technologies for prolonging productivity of HLB-infected citrus trees. As those projects are all under different phases of studies, a few prototyping technologies or research platforms, ranged from robotic end-effectors to mobile platforms, have either been designed, fabricated or tested in field, with associated software and/or algorithms been developed, in the past reporting cycle from July 2014 to September 2015 for respective projects. In addition, the team has also completed a few project specific research activities, such as study of basic physics of apple hand-picking and robotic picking, experimental study of fruit bruising during harvest process, and conceptual study on developing “machine-friendly” tree training structures supporting mechanized production. A theoretical and empirical economic model to assess the impact of various factors on the net revenues of using mechanical harvesters and hand labor to harvest blueberries has also been developed. A few key outcomes from those research projects include, again not limited to, knowledge on (1) fruit grasping patterns and forces in harvesting apples, which is useful for scientists and engineers to design and develop effective end-effectors to achieve bruise-free grasping patterns for robotic picking, (2) optimal combination of shaking frequency and amplitude for harvesting different apple varieties, (3) type of catching mechanism and optimal catching angle which will be critically useful for developing bruising-free shake and catch harvesting system, and (4) a multi-robot bin management simulation tool which can be used to plan and control the implementation of bin management robots in orchards. Other research activities performed by the team include automated irrigation management for specialty crops, wireless sensor network and/or clouds computing based in-orchard labor management systems research, development, extension education and commercialization supports. What opportunities for training and professional development has the project provided? The WSU team formed a trans-disciplinary research and extension team, consisting of engineers, computer scientists, horticulturists, economists and extension specialists, who are affiliated with the WSU Center for Precision and Automated Agricultural Systems (CPAAS). A total of 12 Ph.D. or M.S. graduate students in agricultural and biological engineering, and agricultural economics have worked under the supervision of WSU PIs. PIs, Post-docs, students and scholars interacted frequently to discuss the progresses, address challenges and lay out future tasks and activities. Students and scholars carried out most of the day-to-day research activities including data collection and analysis. Students were also supervised for research paper writing, presentation and publications. The team has also collaborate with local community colleges to provide their students opportunities to gain technology awareness, and even participating in research activities, in our specialty crop automation research. In addition, WSU CPAAS has hosted a few bilateral and multilateral research and education collaborations which allowed us to send more than a dozen person-times of graduate students and faculty members to universities in Australia, China, Germany, Italy, Japan, and New Zealand and to host over 20 person-times students and faculty members from Australia, Brazil, China, Finland, India and Nepal either for internship training, collaborative research, or academic exchanges. How have the results been disseminated to the communities of interest? Developed systems/devices were demonstrated at 2015 CPAAS open house and presented our research outcomes to over 200 growers, researchers, and other stakeholders in this event. The research team has also conducted more than two dozen field trials using developed technologies or prototypes were conducted in various collaborating commercial orchards/farms, allowing growers and field workers have an opportunity to closely observe the research activities conducted by our team. Many of those research results have been presented via journal and trade magazine articles, TV interviews and local newspaper converges since last report. The impact of all specialty crop automation research project is very significant. It could help specialty growers to achieve their production goal of increasing the yield through more efficient production management and implementation. For example, the shake and catch harvesting technology study could potentially help to reduce human labor dependency at least 50% through increasing the harvest productive while controlling the bruising rate of harvested fruit at an acceptable level for fresh consumption market. Similarly, the robotic harvest solution being studied in this project, if been fully developed and proved, has the potential to achieve a 25% cheaper than currently available industrial robotic arms while meeting necessary design specifications to harvest apples and other similar fruit crops. Human-machine collaboration in apple identification have led to identification accuracy of >95% in both day and night time operation, which is an acceptable level for commercial robotic harvesting. Integration of robotic arm, end-effector and vision system is underway. It could possibly achieve the goal of reducing the field labor force in apple harvesting by 80% while reducing or maintaining the harvest time and cost around the same level. Reduced labor use will also proportionally reduces the hazards to worker and insurance claims for the industry. What do you plan to do during the next reporting period to accomplish your project goals? WSU team will continue to work on all involved objectives of this multi-state project, through technology development, research prototype design, fabrication, and field validation tests, as well as the studies on technology adoption and economic models.

Publications

Arizona None to report. California: Farangis Khosro, A., Rehal, R., Vougioukas, S. (2015). A Low-Cost, Efficient Strawberry Yield Monitoring System. ASABE Annual Intl. Meeting; Paper Number 152189408, New Orleans, USA. Georgia: Chugunov, S. and C. Li. 2015. Monte Carlo simulation of light propagation in healthy and diseased onion bulbs with multiple layers. Computers and Electronics in Agriculture. 117: 91-101. DOI:1016/j.compag.2015.07.015. Xu, R., F. Takeda, G. Krewer, and C. Li. 2015. Measure of mechanical impacts in commercial blueberry packing lines and potential damage to blueberry fruit. Postharvest Biology and Technology. DOI: 10.1016/j.postharvbio.2015.07.013. Wang, W. and C. Li. 2015. A multimodal machine vision system for quality inspection of onions. Journal of Food Engineering. DOI: 10.1016/j.jfoodeng.2015.06.027. Konduru, T., G. Rains, and C. Li*. 2015. Detecting sour skin infected onions using a customized gas sensor array. Journal of Food Engineering. 160: 19-27. DOI: 10.1016/j.jfoodeng.2015.03.025. Chugunov, S. and C. Li. 2015. Parallel implementation of inverse adding-doubling and Monte Carlo multi-layered programs for high performance computing systems with shared and distributed memory. Computer Physics Communications. DOI: 10.1016/j.cpc.2015.02.029. Xu, Rui; Li, Changying. 2015. Development of the Second Generation Berry Impact Recording Device (BIRD II). Sensors 15, no. 2: 3688-3705. Konduru, T., G. Rains, and C. Li. 2015. A customized metal oxide semiconductor-based gas sensor array for onion quality evaluation: system development and characterization. Sensors. 15, 1252-1273. Hawaii: Gautz, L. D.; Li, R and Bittenbender, H. C. Preparing Kava: Optimizing kavalactone extraction in water. Proceedings of Kava Science Conference, Jul 25-26, 2015, Chaminade University of Honolulu, 3140 Waialae Ave, Honolulu HI 96816 Iowa: Darr, M. J., H. Herman, and D. Corbett. 2013. Yield Measurement and Base Cutter Height Control for a Harvester. Patent Application Serial No. 14/527,152. Publication No. US 2015/0124054 A1. Hanna, H.M., B. L. Carlson, B. L. Steward, and K. A. Rosentrater. 2015. Evaluation of multi-row covers and support structure for cantaloupe and summer squash. ASABE Paper No. 152182687. St. Joseph, Mich.: ASABE. Gai, J., L. Tang, and B. L. Steward. 2015. Plant recognition through the fusion of 2D and 3D images for robotic weeding. ASABE Paper No. 152181371. St. Joseph, Mich.: ASABE. Schramm, M. W., H.M. Hanna, M.J. Darr, S.J. Hoff, and B. L. Steward. 2015. Measuring surface wind velocity changes. ASABE Paper No. 152182041. St. Joseph, Mich.: ASABE. Polk, D.N., K. A. Rosentrater, H. M. Hanna, B. L. Steward. 2015. Factors affecting cucurbit production. ASABE Paper No. 152184825. St. Joseph, Mich.: ASABE. Steward, B. L., L. Tang, and S. Han. 2015. A design framework for off-road equipment with automation. In Proc. of the 2015 Conference on Autonomous and Robotic Construction of Infrastructure, Ames, Iowa, June 2-3, pp. 180-196. Han, S. F., B. L. Steward, and L. Tang. 2015. Intelligent Agricultural Machinery and Field Robots. In Precision Agriculture Technology - Past, Present, and Future. CRC Press: Boca Raton, Florida, USA. Bao, Yin; Tang, Lie; Schnable, Patrick S.; and Salas Fernandez, Maria G. 2015. GPU-based Parallelization of a Sub-pixel Highresolution Stereo Matching Algorithm for Highthroughput Biomass Sorghum Phenotyping. ASABE Paper No. 152188089. St. Joseph, Mich.: ASABE Lu, H., L. Tang, S. A. Whitham. 2015. Development of an automatic maize seedling phenotyping platform using 3D vision and industrial robot arm. ASABE Paper No. 152189844, St. Joseph, MI. Lu, Hang. 2015. Development of a Robotic Platform for Maize Functional Genomics Research. Graduate Theses and Dissertations. Iowa State University. Kentucky: Precision in Practice. Successful Farming. April 2015. Research on the location accuracy of common mobile devices featured in a nationwide farm industry magazine. (Note: This is one of the largest farm magazines. Not a research publication.) Michigan: Donis-González, I.R., Guyer, D.E, Kavdir, I, Shahriari, D., and Pease, A. 2015. Development and applicability of an agarose-based tart cherry phantom for computer tomography imaging. J. Food Measurement and Characterization. 9:290-298. DOI 10.1007/s11694-015-9234-7. Rady, A.M., Guyer, D.E. 2015. Evaluation of Sugar Content in Potatoes Using NIR Reflectance and Wavelength Selection Techniques. Postharvest Biology and Technology. 103:17-26. Rady, A.M., Guyer, D.E., Lu, R. 2015. Evaluation of Sugar Content of Potatoes Using Hyperspectral Imaging. Journal of Food Bioprocess and Technology. 8(5):995-1010. Donis-González, I.R., Guyer, D.E., Chen R., & Pease, A. 2015. Evaluation of undesirable fibrous tissue in processing carrots using Computed Tomography (CT) and structural fiber biochemistry. J. of Food Engineering. 153:108-116 Rady, A.M., Guyer, D.E. 2015. Utilization of Visible/Near-Infrared Spectroscopic and Wavelength Selection Methods in Sugar Prediction and Potatoes Classification. Journal of Food Measurement and Characterization. Vol 9:Issue1:20-34 Rady, A.M., Guyer, D.E. 2015. Rapid and/or Non-Destructive Quality Evaluation Methods for Potatoes: A Review. Computers and Electronics in Agriculture 117:31-48. Rady, A.M. 2015. Evaluation of physiological status of potato tubers using spectroscopic and hyperspectral imaging systems. PhD Dissertation, Michigan State University. Penn state: Zhao, Z., P.H. Heinemann, J. Liu, J.R. Schupp, and T.A. Baugher. 2014. Design, fabrication, and testing of a low-cost apple harvest-assist device. ASABE Paper No. 141839738. American Society of Agricultural and Biological Engineers. 13 pp. Washington: US Patent: De Kleine, M., Ye, Y. and Karkee, M. (2015). Harvesting machine for formally trained orchards. US Patent. Application Filed. Journal Articles Ampatzidis, I., Vougioukas, S.G., Whiting, M.D., & Zhang, Q. (2014). Applying the machine repair model to improve efficiency of harvesting fruit. Biosystems Engineering. 120: 25-33. Cui, D., Zhang, Q., Li, M., Slaminko, T., & Hartman, G.L. (2014). A method for determining the severity of sudden death syndrome in soybeans. Transactions of the ASABE. 57(2): 671-678. Kang, F., Li, W., Pierce, F., & Zhang, Q. (2014). Investigation and improvement of targeted barrier application for cutworm control in vineyards. Acta Horticulturae. 57(2): 381-389. Karkee, M., Adhikari, B., Amatya, S., & Zhang, Q. (2014). Identification of pruning branches in tall spindle apple trees for automated pruning. Computers and Electronics in Agriculture. 103: 127-135. Li, L., Peters, R.T., Zhang, Q., Zhang, J., & Huang, D. (2014). Modeling apple surface temperature dynamics based on weather data. Sensors, 14: 20217-20234. Ma, S. M. Karkee, P.A. Scharf, and Q. Zhang, 2014. Sugarcane harvester technology: a critical overview. Applied Engineering in Agriculture, 30(5): 727-739. Shao, Y., Tan, L., Zeng, B., & Zhang, Q. (2014). Canopy pruning grade classification based on fast Fourier transform and artificial neural network. Transactions of the ASABE. 57(3): 963-971. Silwal, A., Gongal, A., Karkee, M. (2014). Apple Identification in Field Environment with Over-The- Row Machine Vision System. Agricultural Engineering International: Agric Eng Intl (CIGR Journal), 16(4): 66-75. Zhou, J., He, L., Zhang, Q., & Karkee, M. (2014). Effect of excitation position on fruit removal efficiency and damage in mechanical harvesting of sweet cherry. Biosystems Engineering. 125: 36-44. Conference Papers Davidson, J.R., Mo, C., Silwal, A., Karkee, M., Li, J., Xiao, K., Zhang, Q., Lewis, K. (2015). Human-Machine Collaboration for the Robotic Harvesting of Fresh Market Apples. IEEE International Conference on Robotics and Automation (ICRA) Workshop on Robotics in Agriculture. Seattle, WA. Davidson, J.R., Mo, C. (2015). Mechanical Design and Initial Performance Testing of an Apple-Picking End-Effector. ASME International Mechanical Engineering Congress and Exposition. Houston, TX. Accepted for publication Gongal, A., Amatya, S., Karkee, M., Zhang, Q., & Lewis, K.M. (2014). Identification of Repetitive Apples for Improved Crop-Load Estimation with Dual-Side Imaging. 19th World Congress of the International Federation of Automatic Control. Silwal, A., Gongal, A., Karkee, M. (2014). Apple Identification in Field Environment with Over-The- Row Machine Vision System. Proceedings of the 6th Automation Technology for Off-road Equipment Conference (ATOE); 15-19 September; Beijing, China. Silwal, A., Karkee, M., Zhang, Q. (2015). A hierarchical approach of apple identification for robotic harvesting. American Society of Agricultural and Biological Engineers (ASABE) annual international meeting, Paper #: 152167504; 26-29 July; New Orleans, USA. Ye,Y., L. Yu, Q. Zhang. 2014. Wheel-slip control on an intelligent “bin-dog” system in natural orchard environments. In proc. of 6th Automation Technology for Off-road Equipment Conference (ATOE). September 16-19, 2014, Beijing, China. Zhang, Y., Ye, Y., Wang, Z., Taylor, M.E., Hollinger, G.A. and Zhang, Q. (2015). Intelligent In-Orchard Bin-Managing System for Tree Fruit Production. In: Proceedings of the Robotics in Agriculture workshop (ICRA), May 2015, Seattle, WA. Other Publications Book Review: Zhang, Q. (2014). Book Review: Precision Agriculture for Grain Production Systems. Computers and Electronics in Agriculture, 100, 159. Student Theses/Dissertations: Published DeKleine, M. (2014). Semi-automated End-effector Concepts for Localized Removal and Catching of Fresh-market Apples in Fruiting Wall Orchards. PhD Dissertation, Washington State University. Gongal, A. (2014). Improved Apple Crop-load Estimation with an Over-the-Row Machine Vision System. MS Thesis, Washington State University. Zhang, J., (2014). Development and Application of a Novel System for Measuring Canopy Light Interception in Planar Orchards. Washington State University. Zhou, J., (2014). Vibratory Harvesting Technology Research for Fresh Market Sweet Cherry. Washington State University. Zhang, Y. (2015). Multi-Robot Coordination: Applications in Orchard Bin Management and Informative Path Planning. MS Thesis, Oregon State University.

Impact Statements

Developed new knowledge and technologies for precision intra-row weeding. Determined the feasibility of using commercially available robotic weeding machines in U.S. vegetable production and disseminated the findings to several hundred individuals via various outreach means.
The geo-referenced location data of fruits in tree canopies and the tree branch geometries are being used in conjunction with a physics-based simulator to design canopy-penetrating fruit catching systems that for shake-and-catch mechanized harvesting. The potential impact is reduced dependence on manual labor for fresh market fruit harvesting.
Instrumented picking carts can lead to improved understanding of strawberry yield spatial variability and hence better management.
The automation technology in the packing line can help reduce the high labor costs for onion packers and shippers, which accounts for 50% of the operation costs in a typical packing house.
The disease detection and management technologies could mitigate storage losses (50% in some years).
This project has been reported and featured in various news outlets such as the Georgia Public Broadcasting, Southern Farm Press, and the homepage of the UGA website. The project website has been visited regularly by stakeholders with more than 2000 hits per month. A total of 66 publications were generated by the research team so far and 21 students/postdocs/technicians were provided the training opportunity.
The affordable scale-neutral harvest aid system will significantly improve harvest efficiency, reduce labor-related harvest costs, improve fruit quality and reduce ground loss, resulting in significant economic and social benefits to blueberry growers of all farm sizes, as well as to consumers.
The advanced sensor technologies will aid in accelerated breeding programs for machine harvestable fruit and improve the harvest aid system and postharvest handling process, benefiting growers, packers, and shippers. A critical understanding of the dynamics of potential microbial contamination in the new harvest system will help prevent food borne diseases and create social and environmental benefits to both consumers and the blueberry industry.
Cacao variety trials and small growers have been limited by the lack of effective fermentation techniques. The industry is expanding rapidly due to the implementation of our techniques in some form.
Optimum extraction for kava beverage preparation makes beverage purveyors more profitable by lowering cost per serving. Kava is consumed for its anxiolytic effects by a large number of persons in the United States. There is a growing demand for kava that can be met with full use of the available plant material. The number of servings per gram of below ground plant parts was increased 900%.
The research innovations developed at ISU show promise in providing yield monitoring technologies to a range of machine harvested specialty crops and underserved agricultural products with accurate yield mapping. This yield monitor development work provides critical infrastructure to these agricultural products and will serve as the foundation of site specific recommendations.
The robotic weeding technology development work at ISU is aiming at an ultimate mechanical weeding approach that can control weeds within crop rows. The success of this research effort will produce a profound impact to vegetable production industry. The high-throughput field-based phenotyping system and robotic indoor phenotyping system have potential to revolutionize the current practices in plant sensing and trait characterization.
The autonomous diesel/electric hybrid tractor was demonstrated at the Mechanization for Specialty Crops Field Day held by Kentucky Extension. As it was not a commercial product they could use, attendees could not directly apply the information to their operations, but it did generate a lot of interest, questions and discussion in how they could integrate autonomous and electrical power into their operations.
The tart cherry industry is challenged with economic, and to some degree environmental, sustainability and this project addresses such by working toward development of a revolutionized production approach which brings trees into production at a younger age, potentially increases yield per acre, and improves fruit quality which all work toward positively impacting the economic returns over the life of an orchard.
Commodities reaching the marketplace must have consistent high quality and new defect sensing technology capable of detecting internal quality characteristics, such as studied under this project, are needed to maximize consumer acceptability and optimize utilization.
Injury potential due to ladder falls was completely eliminated. Time spent in awkward postures that indicate stresses on the pickers were reduced from 65% of picking time to 43% of picking time, and the most dangerous postures (stretching to pick apples) were also greatly reduced. Harvest efficiency (defined as apples harvested per second) was increased by 50% utilizing the harvest-assist device compared to conventional ladder harvest.
Modes of project outreach will include expected scientific papers, as well as patents and publications in the trade and popular press. In addition, there will be frequent communication with manufactures, growers and the people who will be using the automated equipment, as well as sets of standards, used to convey the design concepts learned to a wide audience of engineers and technicians.
WSU faculty has participated in drafting a handbook on blueberry production. The handbook contains information on production quantities worldwide, international trade, United States domestic production, prices and per capita consumption. The handbook contains important background information to understand the blueberry market.

Date of Annual Report: 11/16/2016

Report Information

Annual Meeting Dates: 09/20/2016 - 09/21/2016
Period the Report Covers: 10/01/2015 - 09/30/2016

Participants

Mark Siemens, University of Arizona;
David Slaughter, University of California, Davis;
Loren D. Gautz, University of Hawaii at Manoa;
Joseph Dvorak, University of Kentucky;
S. D. Filip To, Mississippi State University;
Jude Liu, Pennsylvania State University;
Qin Zhang, Washington State University;

Brief Summary of Minutes

The annual meeting started a visit to Bard Date Farm to observe date harvesting operation and harvesting equipment, followed by a complete tour of DATEPAC palm date processing (West) and packing (East) plants, and a tour of the Yuma County Water Users Association headquarters. The activities of the day was concluded with a tour of the University of Arizona Yuma Agricultural Research Center with a demonstration of an automated in‐row weeding machine (ROBOVATOR) using fluorescent paint to mark/trace crop plants. The tours of Bard Date farm and DATEPAC West plant were guided by Mr. Dave Manscheim, manager of Bard Date Co. The tour of DATEPAC East plant was guided by Hector Medina, Production Manager of DATEPAC LLC. Tour of Yuma County Water Users Association was given by Tom Davis, Manager. Tour of the UA Yuma Ag research and demonstration were given by Dr. Mark Siemens.

The venue of the business meeting was Holiday Inn Express, 2044 S Avenue 3 E, Yuma, AZ. Members Present were: Dr. Filip To, Mississippi State University, Dr. Mark Siemens, University of Arizona, Dr. Joseph Dvorak, University of Kentucky, Dr. Qin Zhang, Washington State University, Dr. David Slaughter, U.C. Davis, Dr. Loren Gautz, University of Hawaii, and Dr. Jade Liu, Penn State University (via teleconference).

The business meeting started with an updates from USDA‐NIFA, provided by Dr. Daniel Schmoldt, National Program Leader, Presented Remotely via teleconference. It followed by the states report. Seven universities (Mississippi State University, Penn State University, University of Arizona, University of California Davis, University of Kentucky, University of Hawaii, and Washington State University) provided a report presentation at the annual meeting.

An officer election was held during the business meeting to elect the Vice Chair and Secretary for 2017. Dr. Renfu Lu, USDA ARS of Michigan State University was elected unanimously as the 2017 Vice Chair and Dr. Joe Dvorak was elected unanimously as the Secretary of W2009 for 2017. The current Vice Chair, Dr. Stavros Vougioukas, will automatically become the Chair for 2018 (effecting after the 2017 meeting).

After consulted with Dr. Jude Liu, the committee voted unanimously to hold the 2017 meeting in Pennsylvania with the specific site to be determined.

Accomplishments

Short-term Outcomes: (1) The AZ Station is working on developing precision weeding machines for controlling intra-row weeds at the centimeter level scale of accuracy. The current machine system utilizes a machine vision system for plant detection and herbicidal spray to kill weeds; (2) The CA team performed a simulation study on linear fruit reachability in high-density, trellised pear trees which used a linear only motion to reach the fruits intending to harvest fruit on certain architecture trees using simple telescopic robotic arms; (3) ) CA team has also developed an automated fruit quality and food safety inspection system for processing tomatoes which could automatically prepare a deaerated tomato juice sample, and present the sample to a sensor suite for measuring color, soluble solids content, and pH; (4) To inform engineers on how to select branches to cut in intensive apple orchards, PSU Station has developed simplified sequential pruning rules for producing the highest crop value for Gala; (5) WA Station developed a robotic end-effector based on the dynamics of human hand during manual apple picking which is expected to be around 25% cheaper than currently available industrial robotic arms; (6) WA Station used human-machine collaboration in apple identification and led to identification accuracy of >98% in both day and night time operation. It could help a robotic system achieved a harvesting efficiency of >90%. Outputs: (1) The multi-state team has collectively published at least 27 peer reviewed journal articles with at least 10 more in press, presented over 20 papers at various international professional conferences. At least three graduate students completed their studies from relevant research; (2) UC Davis has developed a picking bag that uses load cells, a GPS and an Arduino microcontroller to record and store fruit weight data; (3) The FL team developed a system for heat treatment of HLB infected trees under field condition using steam as the heat source; (4) The Hawaii Station did an engineering economic analysis of the value of a mechanical harvester for 3 to 100 acres. All of these size farms can economically justify a mechanical harvester with the current technology. (5) The Pennsylvania Station has designed and fabricated a low-cost harvest-assist device for apple orchard platforms, and tested in commercial chards. Activities: (1) AZ station made an outreach effort to educate stakeholders about the feasibility of using commercially available robotic cultivators in vegetable production to remove inter- and intra-row weeds; (2) A demonstration heat pump dehumidifier powered dryer has been constructed by Hawaii Station to show potential energy savings well as performing drying at temperatures that protect the quality of the products; (3) The Michigan station under this project continues as a project for over-the-row systems for tart cherry production. Milestones: (1) An instrumented bag being prototyped and used in apple harvest experiments (CA); (2) A simulator being developed for fruit reachability debugged and functional assessment (CA); (3) A commercial equipment manufacturer has participated in the over-the-row harvest evaluation studies as a critical step of making the research outcomes usable to stakeholders; (4) WA team built a self-propelled harvesting research platform for shake-and-catch mass harvesting of fresh-market apple. This research platform has been used in 2016 harvesting studies conducted in WA commercial apple orchards; (5) A WA-OR joint team conceptualized and fabricated an autonomous bin in-orchard management robot. This bin-robot has been tested in individual functions in typical commercial apple orchards, and will start performing integrated autonomous capability in the 2017 season.

Publications

ARIZONA Lati, R.N., Siemens, M.C. & Fennimore, S.A. 2015. Intelligent cultivators – New tool for improved integrated weed management in vegetable crops. In Proc. 2015 Weed Sci. Soc. of America Ann. Meeting., Abstract no. 194. Lawrence, Kansas: WSSA. Lati, R.N., Siemens, M.C. Rauchy, J.S. & Fennimore, S.A. 2016. Intra-row weed removal in broccoli and transplanted lettuce with an intelligent cultivators. Weed Tech. 30(3): 655-663. Fennimore, S.F., Slaughter, D.C., Siemens, M.C., Leon, R.G. & Saber, M.N. 2016. Technology for Automation of Weed Control in Specialty Crops. Weed Tech. (In-Press) CALIFORNIA Nguyen, T.T., D.C. Slaughter, J.N. Maloof, and N. Sinha. 2016.  Plant phenotyping using multi-view stereo vision with structured lights.  Proc. SPIE  9866, Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping, 986608 (May 17, 2016);   doi: 10.1117/12.2229513 Shiu, J.W., D.C. Slaughter, L.E. Boyden, D.M. Barrett. 2016. Correlation of Descriptive Analysis and Instrumental Puncture Testing of Watermelon Cultivars. J. food Sci. 18(6):S1506-S1514. Fennimore, S.A., D.C. Slaughter, M.C. Siemens, R.G. Leon, and M.N. Saber. 2016.  Technology for Automation of Weed Control in Specialty Crops.  Weed Technology (doi: 10.1614/WT-D-16-00070.1) Arikapudi, R., Vougioukas, S.G., Jiménez- Jiménez, F., Farangis Khosro Anjom, F. (2016). Estimation of Fruit Locations in Orchard Tree Canopies Using Radio Signal Ranging and Trilateration. Computers and Electronics in Agriculture (125):160-172. Vougioukas, S.G., He, L., Arikapudi, R. (2016). Orchard Worker Localisation Relative to a Vehicle Using Radio Ranging and Trilateration. Biosystems Engineering (147): 1-16. FLORIDA Li, H., W. S. Lee, and K. Wang. 2016. Immature green citrus fruit detection and counting based on fast normalized cross correlation (FNCC) using natural outdoor colour images. Precision Agriculture, DOI 10.1007/s11119-016-9443-z. Zhao, C., W. S. Lee, and D. He. 2016. Immature green citrus detection based on colour feature and sum of absolute transformed difference (SATD) using colour images in the citrus grove. Computers and Electronics in Agriculture, 124: 243-253. <a href="http://dx.doi.org/10.1016/j.compag.2016.04.009">http://dx.doi.org/10.1016/j.compag.2016.04.009</a>.  Pourreza, A., W. S. Lee, M. A. Ritenour, and P. Roberts. 2016. Spectral characteristics of citrus black disease. HortTechnology 26(3): 254-260.  Yun, H. S., S. H. Park, H.-J. Kim, W. S. Lee, K. D. Lee, S. Y. Hong, G. H. Jung. 2016. Use of unmanned aerial vehicle for multi-temporal monitoring of soybean vegetation fraction. Journal of Biosystems Engineering 41(2):126-137.  Choi, D., W. S. Lee, R. Ehsani, J. K. Schueller, and F. M. Roka. 2016. Detection of dropped citrus fruit on the ground and evaluation of decay stages in varying illumination conditions. Computers and Electronics in Agriculture 127: 109-119.  Cubero, S., W. S. Lee, N. Aleixos, F. Albert, and J. Blasco. 2016. Automated systems based on machine vision for inspecting citrus fruits from the field to postharvest - A review. Food and Bioprocess Technology 9: 1623-1639.  Ni, Z., T. F. Burks, W. S. Lee. 2016. 3D reconstruction of plant/tree canopy using monocular and binocular vision. J. Imaging. In press.  Posadas, B., W. S. Lee, S. Galindo, Y. Hong and S. Kim. 2016. State of knowledge of apple Marssonina blotch (AMB) disease among Gunwi farmers. Journal of Biosystems Engineering. In press.  Park, S. H., W. S. Lee, Y. Hong, M. Shuaibu, and S. Kim. Detection of apple Marssonina blotch with PLSR, PCA, and LDA using outdoor hyperspectral imaging. Spectroscopy and Spectral Analysis. In press.  Castro, A. I. p, R. Ehsani, R.C. Ploetz, J.H. Crane, and J. Abdulridha. 2015. Optimum spectral and geometric parameters for early detection of laurel wilt disease in avocado. Remote Sensing of Environment. 171:33-44.  Katti, A.R., W.S. Lee, R. Ehsani, C. Yang. 2015. Band selection using forward feature selection algorithm for citrus. Journal of Biosystems Engineering. 40(4):417-427. Sankaran S.p, R. Ehsani, and K. Morgan. 2015. Detection of anomalies in citrus leaves using laser induced breakdown spectroscopy (LIBS). Applied Spectroscopy. 69:913-919.  Castro, A. I. p, R. Ehsani, R.C. Ploetz, J.H. Crane, and S. Buchanon. 2015. Detection of laurel wilt disease in avocado using low altitude aerial imaging. PLoS ONE. DOI:10.1371/journal.pone.0124642. HAWAII Extension bulletins are in preparation. IOWA Bravo-Palacios, G. F., G. R. Luecke, and B. L. Steward. 2016. Distortion masking control algorithm for a pneumatic cylinder. ASABE Annual International Meeting, Orlando, FL. July 17-20.  Gai, J., L. Tang, and B. L. Steward. 2016. Plants Detection, Localization and Discrimination using 3D Machine Vision for Robotic Intra-row Weed Control. ASABE Annual International Meeting, Orlando, FL. July 17-20.  Schramm, M. W., M. Hanna, M. J. Darr, S. J. Hoff, and B. L. Steward. 2016. Measuring sub-second wind velocity changes at one meter above the ground. ASABE Paper No. 162461726. St. Joseph, Mich.: ASABE. DOI: 10.13031/aim.202461726  Schramm, M., M. Hanna, M. Darr, S. Hoff, and B. Steward. 2016. A not so-random walk with wind: evaluating wind velocity update methods in ground based spray deposition models. ASABE Paper No. 162459709. St. Joseph, Mich.: ASABE. DOI: 10.13031/aim.202459709  Hanna, H.M., D. N. Polk, B. L. Steward, and K. A. Rosentrater. 2016. Economic analysis of row cover insect exclusion for cucurbit crops. ASABE Paper No. 162461363. St. Joseph, Mich.: ASABE.  Felizardo, K. R., H. V. Mercaldi, P. E. Cruvinel, V. A. Oliveira, and B. L. Steward. 2016. Modeling and model validation of a chemical injection sprayer system. Applied Engineering in Agriculture 32(3): 285-297. doi: 10.13031/aea.32.10606 Jingyao, G. 2016. Plants detection, localization and discrimination using 3D machine vision for robotic intra-row weed control. MS thesis. Iowa State University. KENTUCKY Rounsaville, J., Dvorak, J., Stombaugh, T. (2016). Methods for Calculating Relative Cross-Track Error for ASABE/ISO 12188-2 from Discrete Measurements. Transactions of the ASABE. In Press.  Seyyedhasani, H., Dvorak, J., Sama, M., & Stombaugh, T. (2016). Technical Note: Mobile device-based location services accuracy. Applied Engineering in Agriculture. 32(5). In Press.  Dvorak, J., Stombaugh, T., & Wan, Y. (2016). Nozzle Sensor for In-System Chemical Concentration Monitoring. Transactions of the ASABE. 59 (5). In Press.  Jackson, J. & Dvorak, J. (2016). Hybrid Diesel-Electric Drivetrain for Small Agricultural Field Machines. Transactions of the ASABE. 59 (5). In Press  Rounsaville, J. & Dvorak, J. System Power requirements for a Fully Electric Drivetrain in Ag. 2016 ASABE Annual International Meeting, Orlando, Florida. July 17-20, 2016.  Dvorak, J.S. Electrical Energy for Agricultural Machinery. Oral Presentation. 2015 Electric & Hybrid Vehicle Technology Conference. Novi, Michigan. September 15-17, 2015  Dvorak, J. & Seyyedhasani, Hasan. Simple Field Logistics Simulation Comparing Field Efficiencies and Field Capacities between Larger and Smaller Equipment. Poster Presentation. 2016 ASABE Annual International Meeting, Orlando, Florida. July 17-20, 2016.  Seyyedhasani, H. & Dvorak, J. Comparison of traditional path assignment for multiple vehicles with computer generated one in agricultural field context. 2016 ASABE Annual International Meeting, Orlando, Florida. July 17-20, 2016. MICHIGAN Donis-Gonzalez, I.R., Guyer, D.E., Fulbright, D. 2016. Quantification and identification of microorganisms found on shell and kernel of fresh edible chestnuts in Michigan. Journal of the Science of Food and Agriculture. Vol 96(4514-4522) <a href="http://dx.doi.org/10.1002/jsfa.7667">http://dx.doi.org/10.1002/jsfa.7667</a>  Donis-Gonzalez, I.R., Jeong, S., Guyer, D.E., Fulbright, D. 2016. Microbial contamination in peeled chestnut and the efficiency of post-processing treatments for microbial spoilage management. J. Food Processing and Preservation. <a href="http://dx.doi.org/10.1111/jfpp.12874">http://dx.doi.org/10.1111/jfpp.12874</a>  Donis-Gonzalez, I.R., Guyer, D.E., Pease, A. 2016. Postharvest non-invasive assessment of undesirable fibrous tissue in fresh processing carrots using computer tomography images. Journal of Food Engineering. Vol 190(154-166) <a href="http://dx.doi.org/10.1016/j.jfoodeng.2016.06.024compag.2016.06.018">http://dx.doi.org/10.1016/j.jfoodeng.2016.06.024compag.2016.06.018</a>  Donis-Gonzalez, I.R., Guyer, D.E., Pease, A. 2016. Postharvest non-invasive classification of tough-fibrous asparagus using computed tomography images. Postharvest Biology and Technology. Vol 127 (27-35) <a href="http://dx.doi.org/10.1016/j.compag.2016.06.018">http://dx.doi.org/10.1016/j.compag.2016.06.018</a>  Donis-Gonzalez, I.R. and Guyer, D.E. 2016. Classification of processing asparagus sections using color images. Computers and Electronics in Agriculture. Vol 127 (236-241). <a href="http://dx.doi.org/10.1016/j.compag.2016.06.018">http://dx.doi.org/10.1016/j.compag.2016.06.018</a> MISSISSIPPI Thesis: Opeyemi Christiana Olojede, “Comparative evalutation of three different methodologies for determining embryo temperature in broiler hatching eggs during incubation”, Mississippi State University, August 2015 PENNSYLVANIA Lyons, D.J., P.H. Heinemann, J. Liu, J., J.R. Schupp, and T.A. Baugher. 2015. Development of a selective automated blossom thinning system for peaches. Transactions of ASABE. 58(6):1447-1457.  Zhang, Z., P.H. Heinemann, J. Liu, J.R. Schupp, and T.A. Baugher. 2016. Design and field test of a low-cost apple harvest-assist unit. Transactions of ASABE. 59(5): (in press)  Zhang, Z., P.H. Heinemann, J. Liu, J.R. Schupp, and T.A. Baugher. 2016. Development of mechanical apple harvesting technology – a review. Transactions of ASABE. 59(5): (in press)  WASHINGTON Amatya, S., and M. Karkee, 2016. Integration of visible branch sections and cherry clusters for detecting cherry tree branches in dense foliage canopies. 2016. Biosystems Engineering, 119:72-81.  Amatya, S., M. Karkee, A. Gongal, Q. Zhang, M.D. Whiting. 2016. Detection of Cherry Tree Branches in Planner Architecture for Automated Sweet-Cherry Harvesting. Biosystems Engineering. 146:3-15.  Davidson, J., Silwal, A., Karkee, M., Mo, C., Qin, Z. 2016. Hand Picking Dynamic Analysis for Undersensed Robotic Apple Harvesting. Transactions and the ASABE, Vol. 59(4): 745-758. De Kleine, M. E., and M. Karkee. 2016. A Semi-Automated Harvesting Prototype for Shaking Fruit Tree Limbs. Transactions of the ASABE, 58(6): 1461-1470.  Gongal, A., A. Silwal, S. Amatya, M. Karkee, Q. Zhang, and K. Lewis. 2016. Apple Crop-load Estimation with Over-the-Row Machine Vision System. Computers and Electronics in Agriculture, 20: 26–35.  Li, J., M. Karkee, Q. Zhang, K. Xiao, T. Feng, 2016. Characterizing apple fruit robotic picking patterns and detaching parameters. Computers and Electronics in Agriculture, 127:633-640. Santiago, W. E., N. J. Leite, B. J. Teruel, M. Karkee, C. A. M. Azania, and R. Vitorino. 2016. Development and testing of image processing algorithm to estimate weed infestation level in corn fields. Australian Journal of Crop Science.10(9): 12232-1237.  Ye, Y., 2016. A maneuverability study on a wheeled bin management robot in tree fruit orchard environments. Ph.D. Dissertation, April 2016, Washington State University.  Ye, Y. L. He, Q. Zhang. 2016. Steering control strategies for a four-wheel-independent-steering bin managing robot. Paper and presentation at the 5th IFAC Conference on Sensing, Control and Automation for Agriculture, August 14-17, Seattle, WA. WEST VIRGINIA Talks to stakeholders, peer groups, multistate clientele: Tabb, A. Computer vision in tree fruit production. Marquette University Electrical and Computer Engineering lecture series, Milwaukee, Wisconsin. October 13, 2015.  Tabb, A. Engineering Computer Vision Tools for Entomology Research. Brown Marmorated Stink Bug Integrated Pest management working group meeting. Virginia Tech’s Alson H. Smith, Jr. Agricultural Research and Extension Center (AREC), Winchester, VA. December 2, 2015.  Tabb, A. Autonomously Determining the Shape of Trees for Structural Phenotyping and Pruning. Institute of Electrical and Electronics Engineers technical committee on Agricultural Robotics, international virtual presentation. Feb 11, 2016.  Tabb, A. Robotic Imaging System for Orchard Automation. Young Growers Alliance (of Pennslyvania) Tour. USDA-ARS-Appalachian Fruit Research Station, Kearneysville, West Virginia. June 7, 2016.  Tabb, A. A robotic system for three-dimensional tree architecture phenotyping. Cornell Fruit Field Day, Geneva, New York. July 20, 2016

Impact Statements

Field testing utilizing a redesigned distributor on a low-cost harvest-assist device for apple orchards reduced downgrading of apple quality to 5%

Date of Annual Report: 11/13/2017

Report Information

Annual Meeting Dates: 09/14/2017 - 09/15/2017
Period the Report Covers: 10/01/2016 - 09/30/2017

Participants

Daeun Dana Choi, Pennsylvania State University;
Irwin Donis-Gonzalez, University of California, Davis;
Joseph Dvorak, University of Kentucky;
Loren Gautz, University of Hawaii at Manoa;
Dan Guyer, Michigan State University;
Long He, Washington State University;
Paul Heineman, Pennsylvania State University;
Lewis, Karen, Washington Cooperative Extension;
Won Suk Lee, University of Florida;
Jude Liu, Pennsylvania State University;
Renfu Lu, Michigan State University;
James Schupp, Pennsylvania State University;
Abby Tam, West Virginia ARS/USDA;
S. D. Filip To, Mississippi State University;
Stavros Vougioukas, University of California, Davis;
Qin Zhang, Washington State University.

Brief Summary of Minutes

The annual meeting started (9/14/17) with a visit to Hollabaugh Orchards near Biglerville, PA and tour of high density apple and pear plantings. Next, the group visited Rice Fruit Company and witnessed the newest commercial technologies for fruit sorting, packing, and storage; discussion of engineering research needs was also undertaken. After lunch the group visited Mt. Ridge Farms and discussed with growers who successfully use GPS-guided planters, real-time weather/pest alert systems, and mechanical blossom thinning equipment. The last stop was the Penn State Fruit Research and Extension Center for an orchard tour and demonstration of rules-based approach to pruning tall spindle apple plantings. Discussion of implications for labor efficiency and automation systems concluded the working day.

The venue of the business meeting (9/15/17) was Penn State Fruit Research and Extension Center. The Members present are listed above, in the participants list, in alphabetical order. The meeting was called to order at 8:45 am by Stavros Vougioukas. Qin Zhang moved to start the business meeting before state reports; Paul Heineman seconded and the motion passed. Qin Zhang gave a brief introduction of the project and went over the main tasks that needed to be accomplished during the meeting. He also gave some guidelines on reporting. Renfu Lu made a brief announcement about an ASABE-IEEE symposium - planning conference regarding the area of Smart Agriculture. The event was planned to take place at Michigan State, Dec 3-5, 2017. Discussion followed and the consensus was that IEEE and other new entrants seem to be duplicating research and technologies developed over 20 years ago, and that agricultural and biosystems engineers need to inform IEEE leadership about the current frontiers of technology. Next, Annual Reporting requirements and specifications were discussed. Stavros Vougioukas will collect station reports and compile them into one report that will be sent to Qin Zhang; he will review and submit to NIFA. The next agenda item was the renewal of the proposal. Our committee is five years old and needs to submit a renewal proposal by the end of this year. A proposal writing committee was formed. Filip To volunteered to lead. Committee members are: Paul Heineman, Charlie (Changying) Li, Stavros Vougioukas, and Daeun Choi. Future project objectives were discussed and there was general agreement that the current objectives are acceptable. Some discussion was initiated on new objectives, and it will be continued during proposal drafting. New Committee Officers were elected. Next Chair will be Renfu Lu. He is not an active member, but Qin Zhang will make sure he is added so he can serve as chair. Joe Dvorak was voted as next Vice-Chair. Paul nominated Irwin Donis-Gonzalez for next Secretary; Jim seconded and the motion was passed unanimously. Next, the people who will head the station reports were determined and next venue was discussed. Filip To volunteered to host the next meeting in mid-September, 2018 at Mississippi State University, where sweet potato is the main specialty crop. A move to adjourn was made by Loren at 12:13 and seconded by Amy Tabb. The motion was passed and the meeting was adjourned.

Accomplishments

Short-term Outcomes:  (AZ) Use of automated in-row weeding technologies was found to reduce hand weeding labor requirements by roughly 30%. Results from testing of novel weeding spray assembly showed that targeting accuracy for all treatments was better than ± 2.0 mm and ± 1.6 mm in the longitudinal and lateral directions respectively. Average percent coverage of the target areas was 59.3% and off-target drift was 4.9%. Results exceeded the established success criteria of delivering spray at the centimeter level scale of accuracy with < 5% off target spray.  (CA) By adopting a fully automated tomato juice inspection system developed at UC Davis, workers were no longer required to manually lift and invert 10-pound stainless steel containers of tomato juice for each truckload of tomatoes inspected. This represents a potential reduction of 1,000 repetitive motion hazards per day for those individuals.  (FL) A deep-learning machine vision system for evaluation of harvested citrus fruit quality yielded detection accuracies of 100%, 89.7%, 94.7%, and 88.9% for healthy, Huanglongbing, rust mite and wind scar, respectively.  (HI) The data showed that a small handheld NIR spectrometer could be used in the field to measure water stress in coffee. Also, a system that was developed to conduct small (100-1000 g) lot fermentation of cacao gave repeatable results in chocolate quality by tree without the need of large mass of cacao seed.  (IA) Investigations into the deployment of row covers for cucurbit pest exclusion and bacterial wilt spread reduction showed that burying the cover material was better at excluding insects than anchoring the cover material. Structurally, conduit hoops kept the material from sagging and resulted in the least amount of damage.  (MI) Major improvements were made in the bin filler design and automatic handling system for a new self-propelled apple harvest and infield sorting prototype machine.  (PA) The development of heuristic rules to accommodate robotic pruning showed that limb to trunk ratio worked well for setting severity determined using maximum limb diameter, and that removing next largest branch to threshold makes up for ¾ of the required pruning. A two-person N.M. Bartlett Chariot orchard platform equipped with a small harvest-assist device was evaluated to be better suited for hilly US orchards than the original platform without the unit.  (WA) Preliminary results from the evaluation of a robotic apple harvesting system showed that: 5DOF (instead of 8 DOF) don’t compromising the workspace of the robot; fruit picking and catching could be completed in about 5 s using a 5 degree-of-freedom (DOF) robotic system. Results from field tests of a targeted shake-and-catch apple harvesting system showed that fruit detachment and collection efficiency were higher with shorter branch length when the branch size is similar. Fruit detachment and collection rates of 90% or more could be achieved in modern, formally trained orchard. It was also shown that shake-and-catch harvesting showed promise for faster and potentially low cost harvesting of apples for fresh market consumption. However, the method tends to show varietal dependence with Fuji and Jazz showing higher removal efficiency and better quality fruit while varieties like gala and honey crisp suffering from either low removal efficiency, low fruit quality or both. Preliminary trajectory tracking tests for a robotic weed control machine showed that linear, sinusoidal and circular paths could be followed with a maximum position error of 2.2 cm at a driving speed of 0.10 m·s-1 which met the required performance for precise herbicide application on WA organic vegetable fields. Results from preliminary field evaluation tests of a red raspberry cane bundling and tying machine showed the developed bundling mechanism was successful for over 90% of times whereas the success percentage for combined bundling and tying mechanisms was about 84%. It was also found that the performance was variety dependent (Meeker showing a greater promise than Wakefield). Early results from multiple field trials of a preliminary bird identification and deterrence drone-based system showed that drones flown by hand could successfully deter birds at a very high rate.  Outputs: A total of fifty five (55) journal publications were produced by all stations in the past year. Hardware, software, data and report outputs are presented next for each participating station.  (AZ) The results of precision weeding research were disseminated (presentations, articles) by making presentations at meetings (3), hosting field days (1), giving demos (4) and working with journalist to publish popular press articles (3). An outreach effort was made to educate stakeholders about the feasibility of using commercially available robotic cultivators in U.S. vegetable production. The outreach effort comprised making presentations at meetings on the findings from trials conducted as part of this project (3), hosting field days (2), conducting on-farm demonstrations (5) and publishing popular press articles (2).  (CA) Three peer-reviewed journal papers were published and eight conference papers were presented. Data from forty digitized trees and fruits (pears and cling-peaches) were generated. An instrumented fruit picking bag was developed and calibrated (hardwar and sofware). A fully automated tomato juice inspection system developed (hardware and software).  (FL) A machine vision system (hardware and software) was developed to evaluate the quality of harvested citrus fruit. An image fusion method (software) was developed for color and thermal images to detect immature green citrus fruit on the tree.  (HI) Two publications were made. A thesis on leaf stress measurement and a journal article on small lot fermentation system for variety evaluation. A system (hardware) for small (100-1000 g) lot fermentation of cacao seed was developed.  (IA) A 3D machine vision system (hardware and software) was developed to recognize and determine the location of specialty crop plants, specifically, broccoli and lettuce. An intra-row weeding actuator (hardware) was built and a controller (software) was designed for it to follow a trajectory around vegetable crop plants. Test results (report) comparing spray coverage against changes in boom height and carrier application rate were generated for dynamic pulse width modulated nozzle systems. (KY) Computer software for routing tractors and UASs was developed. Simulations were verified with tractors in agricultural fields and UAS flying over fields (articles).  (MI) A multichannel hyperspectral imaging probe for measuring optical properties and quality attributes of tomatoes and peaches (hardware and software). A structured-illumination reflectance imaging (SIRI) technique (software) for detection of defects in fruit. Quantitative comparison between conventional versus over-the-row harvest systems for tart cherries (data).  (PA) Heuristic rules for robotic pruning were developed and evaluated (articles). Harvest-assist device for small operations was developed (hardware).  (WA) A robotic apple harvesting system was developed that included a dual robot collaboration mechanism for fruit detachment and catching and an end-effector with novel smart soft material (hardware, software, articles). A targeted shake-and-catch apple harvesting system was designed and fabricated (hardware). A prototype robotic weed control machine for vegetable crops was designed and fabricated (hardware and software). A prototype robotic red raspberry cane bundling and tying machine was designed and fabricated (hardware and software).  Activities: (AZ) Work continued to develop a precision weeding machine for controlling intra-row weeds at the centimeter level scale of accuracy. In FY17, a second spray assembly for precision weeding was developed. The unit comprises a high-speed solenoid valve and a custom-built nozzle body with a straight, thru-hole orifice. The assembly was evaluated at travel speeds ranging from 1-2 mph and nozzle tip to target distances of 3-7 inches.  A significant effort was made to identify a solenoid valve/nozzle combination that would deliver fluorescent marking paint to lettuce seedlings. Application of marking paint facilitates crop/weed differentiation. Over 25 combinations were evaluated in the lab. The best performing assemblies were tested in the field. Although the assemblies provided spray patterns that measured roughly 2x2” with minimal off target spray, results showed, that improvements in targeting accuracy and spray coverage are needed in order for the imaging system to reliably detect marked crop plants.  A project was initiated to develop a multispectral imaging system for detecting fecal matter on leafy greens. Study results showed that imaging using relatively inexpensive components could provide the basis for detection of fecal contamination in produce fields if surveys were conducted during dawn or dusk, or at night.  (CA) Engineering research design, development, deployment, and scientific assessment activities for the creation of new, novel smart machines for a reduction in menial labor requirements, and an increase in method objectivity and automation for quality characterization and food safety assessment of fruits and vegetables were conducted by the research team in the Slaughter lab.  In the Vougioukas lab, cling peach and pear trees were digitized and 3D models were created. Simulation experiments were conducted using these 3D models to investigate the picking efficiency and throughput of multi-arm robotic harvesters. A Linear Mixed Model was developed and trained to predict the picking time in manual strawberry harvesting. The dataset consisted of 161 picking times from 18 workers and was collected in strawberry fields in Salinas, CA. A standard fruit-picking bag was retrofitted to measure the weight of manually harvested fruits in real time. Two load cells, electronics, and software running on a microcontroller were integrated in a custom-made enclosure.  Research was conducted by the research team in the Donis-Gonzalez lab at the University of California, Davis to assess commercially available portable, non-invasive produce quality spectrometers. (FL) An image fusion method was developed for color and thermal images to detect immature green citrus fruit on the tree. The method utilized photogrammetry and bundle adjustment to calibrate relative orientations of the cameras. A machine vision system was developed to evaluate the quality of harvested citrus fruit. A graphical processing unit (GPU) and a deep learning technique were used to process videos of the fruit on a conveyer system. Another study was initiated to detect strawberry flowers in outdoor images under natural illumination conditions.  (HI) A scientific study was conducted to develop a calibration using near infrared spectroscopy and capacitance to determine coffee leaf water stress as measured by pressure bomb method. A system was developed to conduct small (100-1000 g) lot fermentation of cacao seed.  (IA) Robotic solutions were developed to automate the process of plant phenotyping traits extraction. 3D machine vision technology was developed to recognize and determine the location of specialty crop plants, specifically, broccoli and lettuce. This technology is being incorporated into an automated mechanical weeding system which will assist growers, particularly of organic crops, to efficiently tackle the problem of weed plant growing in crops.  Research was initiated into automatic control of an intra-row weeding actuator. The controller is designed to guide the actuator to follow a trajectory around vegetable crop plants. Model predictive control (MPC) was investigated in as an alternative to classical control approaches. Field research was conducted that investigated the drift of larger spray droplets in-situ at varying wind speeds. Several investigations into the deployment of row covers were completed in summer of 2017 for cucurbit pest exclusion and bacterial wilt spread reduction. Various methods can be used to sealing row cover perimeters and prevent cucumber beetles from entering rows. Investigations into the effectiveness of four different methods of perimeter sealing were tested at three different locations. In addition, different methods of anchoring the row cover material as well as support structures were all investigated as well. Research was conducted that quantified the consistency of herbicide placement in dynamic pulse width modulated nozzle systems. This technology was investigated through replicated machine trials and on-farm research. Herbicide placement distribution was quantified using large ground targets and an automated digital image analysis tool which measured the uniformity of spray coverage. Testing compared spray coverage against changes in boom height as well as carrier application rate.  (KY) Computer simulations of machinery routing in hundreds of scenarios (field shape, vehicle to field size ratios) have been carried out. Simulations were verified with tractors in agricultural fields and UAS flying over fields.  (MI) USDA/ARS A new multichannel hyperspectral imaging probe was measured and evaluated for measuring optical properties and quality attributes of tomatoes and peaches. The new probe allows acquiring 30 spectra of 550-1,650 nm from samples of flat or curved surface. Calibration procedures were developed, which enable the probe to measure optical absorption and scattering properties. Further progress was also made in the development of structured-illumination reflectance imaging (SIRI) technique for defect detection of fruit. Algorithms were developed for extracting direct, alternate and phase component images from the acquired SIRI images. Good progress was made on further development of apple harvest and infield sorting technology. The concept of canopy shaking harvest this year continued to be focused on fruit quality comparison between conventional versus over-the-row (OTR) harvest systems but with a more quantitative approach this year rather than a qualitative approach. For 2017, a small instrumented sphere, developed at the U. of Georgia BAE Dept., (W2009 Collaborator) capable of measuring impact forces was hung within tree systems and “harvested” along with fruit. Impacts in severity and number were measured under multiple harvester and production systems. Fruit and the instrumented sphere were also dropped at controlled heights and the fruit was assessed for damage to calibrate the impacts to damage occurring in the orchard harvests. Data is currently being analyzed from the 2017 season. Additionally, trial dwarfing plant growth plots being developed for the purpose of OTR production were evaluated for yield and canopy harvest compatibility. Harvest was conducted with a first generation commercial OTR canopy spindle shaker. This OTR system was compared against two conventional double-incline trunk shaking system in two locations. The OTR harvester was tested in multiple dwarfing training systems. A commercial equipment manufacturer continued collaboration with the harvest evaluation studies. Finally, Computed tomography (CT), often coupled with parallel studies of hyperspectral imaging and spectroscopy, were implemented to study internal characteristics/defects of carrots, asparagus, and chestnuts which are not detectable by current commercial technology.  (PA) Rules developed for robotic pruning based on heuristics. Limb to trunk ratio worked well for setting severity determined using maximum limb diameter. Removing next largest branch to threshold is ¾ of the required pruning.  Harvest-assist device for small operations was redesigned by undergraduate student design team, to fit on N.M. Bartlett Chariot two-person platform. This platform was better suited for hilly US orchards than the original platform. The unit was field tested in apple orchards in Fall 2017.  (WA) A robotic apple harvesting system has been designed and fabricated. It included the development of a dual robot collaboration mechanism for fruit detachment and catching. The fruit picking end-effector has also been improved using a novel smart soft material. Laboratory and field test data have been acquired to evaluate the performance of the developed system in terms of fruit detachment efficiency and fruit harvesting speed. The parallel operation of various degrees of freedom for picking-and-catching was investigated to increase harvesting speed.  A targeted shake-and-catch apple harvesting system has been designed and fabricated. A series of field tests was completed to evaluate fruit detachment efficiency, fruit collection efficiency and fruit damage percentage different pruning treatments.  One field prototype robotic weed control machine for vegetable crops has been designed and fabricated. Also, one prototype robotic red raspberry cane bundling and tying machine has been designed and fabricated. A preliminary bird identification system was fielded which could be used to help autonomously control drones for bird deterrence from high-value fruit.  Milestones: (AZ) Spray assembly for targeted weeding exceeded the established success criteria of delivering spray at the centimeter level scale of accuracy with < 5% off target spray.  (CA) Deployment of smart machines developed in the Slaughter lab for fully automated inspection of tomato juice for economic value, food quality, and food safety, reached 25% of the long-term target of full adoption by the processing tomato industry in 2017. Fourty trees were digitized during the summer of 2017.  (FL) Vision-based yield detection accuracies achieved rates of 100%, 89.7%, 94.7%, and 88.9% for healthy, Huanglongbing, rust mite and wind scar, respectively.  (HI) System for small (100-1000 g) lot fermentation of cacao was completed and produced repeatable results.  (IA) 3D machine vision prototype for plant recognition and localization was developed and tested, resulting in a milestone toward automated mechanical weeding systems. Different methods of anchoring row cover material and support structures were investigated as milestone result for cucurbit pest exclusion. Herbicide placement distribution testing was performed as a major step in the study of consistency of herbicide placement in dynamic pulse width modulated nozzle systems.  (KY) Field verification of optimal routing for field coverage by agricultural machinery was completed.  (MI) A hyperspectral imaging probe was calibrated as a milestone in measuring optical properties and quality attributes of tomatoes and peaches. Algorithms for extracting direct, alternate and phase component images from structured-illumination reflectance images were developed as a milestone in detection of fruit defects. Tart cherry shake-and-catch experiments were performed using an instrumented sphere and new dwarfing plants as a milestone in developing advanced over-the-row harvesters.  (PA) Development of harvest-assist device for small orchard platforms was completed thus enabling the testing of such platforms’ efficiency. Rules were developed for robotic pruning based on heuristics, as an important milestone to the further development of such robotic systems.  (WA) One robotic bin-handling machine has driven fully autonomously in actually managing fruit bins for over 40 km in WA commercial orchards.

Publications

ARIZONA Lefcourt, A.M. & Siemens, M.C. Interactions of insolation and shading on ability to use fluorescence imaging to detect fecal contaminated spinach. Applied Sci. 7 1041; doi:10.3390.  CALIFORNIA Shiu, J.W., D.C. Slaughter, L.E. Boyden, D.M. Barrett. 2016. Correlation of Descriptive Analysis and Instrumental Puncture Testing of Watermelon Cultivars. J. food Sci. 18(6):S1506-S1514.  Doan, H.K., K. Perez, R.M. Davis, and D.C. Slaughter. 2016. Survey of Molds in California Processing Tomatoes. J. of Food Science. 81(11): 2785-2792.  Xiaotuo, W., G.G. Atungulu, R. Khir, G. Zhenjiang, P. Zhongli, S.A. Wilson, G. Olatunde, and D. Slaughter. 2017. Sorting in-shell walnuts using near infrared spectroscopy for improved drying efficiency and product quality. International Agricultural Engineering Journal. 26(1): 165-172.  Vougioukas, S.G., Arikapudi R., Munic, J. (2016). A Study of Fruit Reachability in Orchard Trees by Linear-Only Motion. Journal: IFAC-PapersOnLine, 49(16), pp.277-280. <a href="https://doi.org/10.1016/j.ifacol.2016.10.051">https://doi.org/10.1016/j.ifacol.2016.10.051</a>.  Arikapudi, R., Vougioukas, S.G., Jiménez- Jiménez, F., Farangis Khosro Anjom, F. (2016). Estimation of Fruit Locations in Orchard Tree Canopies Using Radio Signal Ranging and Trilateration. Computers and Electronics in Agriculture (125): 160-172. <a href="http://dx.doi.org/10.1016/j.compag.2016.05.004">http://dx.doi.org/10.1016/j.compag.2016.05.004</a>.  Vougioukas, S.G., He, L., Arikapudi, R. (2016). Orchard Worker Localisation Relative to a Vehicle Using Radio Ranging and Trilateration. Biosystems Engineering (147): 1-16. <a href="http://dx.doi.org/10.1016/j.biosystemseng.2016.03.006">http://dx.doi.org/10.1016/j.biosystemseng.2016.03.006</a>  FLORIDA Pourreza, A., W. S. Lee, E. Czarnecka, L. Verner, and W. Gurley. 2017. Feasibility of using the optical sensing techniques for early detection of Huanglongbing in citrus seedlings. Robotics 6(11). Doi:10.3390/robotics6020011.  Shuaibu, M., W. S. Lee, Y. K. Hong, and S. Kim. 2017. Detection of apple Marssonina blotch disease using particle swarm optimization. Trans. ASABE 60(2): 303-312.  Khedher Agha, M. K., W. S. Lee, C. Wang, R. W. Mankin, A. R. Blount, R. A. Bucklin, and N. Bliznyuk. 2017. Detection and prediction of Sitophilus oryzae infestations in triticale via visible and near infrared spectral signatures. Journal of Stored Products Research 72: 1-10.  Khedher Agha, M. K., R. A. Bucklin, W. S. Lee, R. W. Mankin, and A. R. Blount. 2017. Effect of drying conditions on triticale seed germination and weevil infestation. Trans. ASABE 60(2): 571-575.  Barocco, R., W. S. Lee, and G. Hortman. 2017. Yield mapping hardware components for grains and cotton using on-the-go monitoring systems. UF/IFAS EDIS AE518. <a href="http://edis.ifas.ufl.edu/ae518">http://edis.ifas.ufl.edu/ae518</a>.  HAWAII Provera, M. 2016. Determination of the Water Content of Coffee Leaves using Infrared Spectroscopy. University of Hawaii at Manoa, Biological Engineering, Honolulu, HI.  Bittenbender, H. C., L. D. Gautz, E. Seguine, and J. L. Myers. 2017. Microfermentation of Cacao: The CTAHR Bag System. Horttechnology 27(5):5.  IOWA Fernandez, M. G. S., Bao, Y., Tang, L., & Schnable, P. S. (2017). A high-throughput, field-based phenotyping technology for tall biomass crops. Plant Physiology, pp-00707.  Felizardo, K. R., H. V. Mercaldi, P. E. Cruvinel, V. A. Oliveira, and B. L. Steward. 2016. Modeling and model validation of a chemical injection sprayer system. Applied Engineering in Agriculture 32(3): 285-297. doi: 10.13031/aea.32.10606.  Lu, H., L. Tang, S. A. Whitham, Y. Mei. 2017. A Robotic Platform for Corn Seedling Morphological Traits Characterization. Sensors 17(9), 2082. doi:10.3390/s17092082  Li, J., L. Tang. 2017. Developing a low-cost 3D plant morphological traits characterization system. 2017. Computers and Electronics in Agriculture, 143:1-13. <a href="https://doi.org/10.1016/j.compag.2017.09.025">https://doi.org/10.1016/j.compag.2017.09.025</a>.  Li, J., L. Tang. 2017. Crop Recognition under weedy conditions based on 3D imaging for robotic weed control. Journal of Field Robotics. DOI: 10.1002/rob.21763.  Bao, Y.*, L. Tang, D. Shah. 2017. Robotic 3D Plant Perception and Leaf Probing with Collision-Free Motion Planning for Automated Indoor Plant Phenotyping. ASABE Paper No. 1700369. St. Joseph, Mich.: ASABE. doi: 10.13031/aim.201700369  Herzberg, R. L., H. M. Hanna, B.L. Steward, and K. A. Rosentrator. 2017. Assessment of the mechanization of row covers for cucurbit crops. ASABE Paper No. 162460814. St. Joseph, Mich.: ASABE. DOI: 10.13031/aim.201700686  Villibor, G. P., B. L. Steward, G. R. Luecke, D. M. Queiroz, L. Tang, S. Kshetri. 2017. Vibrations levels assessment of a robotic intra-row weeder using low-cost data acquisition system. ASABE Paper No. 1700652. St. Joseph, Mich.: ASABE. DOI: 10.13031/aim.201700652  Kshetri, S., J. Gai, L. Tang, and B. L. Steward. 2017. Trajectory controller design for precisely positioning a mechanical weeding mechanism. ASABE Annual International Meeting, Spokane, WA. July 16-19.  Gai, J., S. Kshetri, L. Tang, and B. L. Steward. 2017. Robotic intra-row weed control using 3D computer vision. ASABE Annual International Meeting, Spokane, WA. July 16-19.  Breitzman, M. W., Bao, Y., Tang, L., Schnable, P. S. & Fernandez, M. G. S. 2017. High-throughput architectural traits phenotyping for association mapping. Session of Physiological Traits for High Throughput Phenotyping of Abiotic Stress Tolerance at the ASA, CSSA and SSSA International Annual Meetings, Tampa, Florida.  Jafni Johari Jiken. 2016. Experimental approach to determine the efficacy of a tine mechanism for auto weeding machine. M. S. Thesis. Iowa State University Parks Library.  KENTUCKY Seyyedhasani, H., Dvorak, J. (2017). Using the Vehicle Routing Problem to Reduce Field Completion Times with Multiple Machines. Computers and Electronics in Agriculture. 134. March 2017. 142-150. <a href="http://dx.doi.org/10.1016/j.compag.2016.11.010">http://dx.doi.org/10.1016/j.compag.2016.11.010</a>.  Seyyedhasani, H., Dvorak, J. S., Sama, M., Aerial Validation of a Logistics Model for Area Coverage in Agriculture. Conference Presentation. 2017 ASABE Annual International Meeting, Spokane, WA, United States. July 16-19, 2017.  MICHIGAN Donis-González, I.R., Guyer, D.E., Lu, R. 2016. Postharvest assessment of undesirable fibrous tissue (choking hazard) in fresh processing carrots using Vis/NIR hyperspectral images. Proceedings for 3rd International Conference on Fresh-Cut Produce: Maintaining Quality and Safety Sept. 13-18, 2015. Acta Horticulturae 1141 ISHS 2016. DOI 10.17660/ActaHortic.2016.1141.21.  Donis-Gonzalez, I.R., Jeong, S., Guyer, D.E., Fulbright, D. 2017. Microbial contamination in peeled chestnut and the efficiency of post-processing treatments for microbial spoilage management. J. Food Processing and Preservation. Vol. 41: <a href="http://dx.doi.org/10.1111/jfpp.12874">http://dx.doi.org/10.1111/jfpp.12874</a>.  Lu, Y. and Lu, R. Histogram-based automatic thresholding for bruise detection of apples by structured-illumination reflectance imaging. Biosystems Engineering 160:30-41. 2017.  Huang, Y., Lu, R., and K. Chen. Development of a multichannel hyperspectral imaging probe for food property and quality assessment. Postharvest Biology and Technology 133:88-97. 2017.  Zhang, Z., Pothula, A. K. and Lu, R. Economic analysis of a self-propelled apple harvest and in-field sorting machine for the apple industry. ASABE Paper No. 2456644 (DOI: 10.13031/aim.202456644), 12 pp. 2016 (Proceedings)  Lu, R., Zhang, Z., and Pothula, A. K. Innovative technology for apple harvest and in-field sorting. Fruit Quarterly 25(2):11-14. 2017. (Industry Publications)  Huang, Y., Lu, R., and K. Chen. Development of a multichannel hyperspectral imaging probe for food property and quality assessment. In SPIE Proceedings Vol. 9864 - Sensing for Agriculture and Food Quality and Safety VII (edited by Kim, M. S. et al.), Paper No. 98640Q, 12 pp. SPIE (The International Society for Optical Engineering), Bellingham, WA. 2016. (Proceedings)  Lu, Y. and Lu, R. Phase analysis of three-dimensional surface reconstruction of apples using structured-illumination reflectance imaging. SPIE Proceedings Vol. 9864 - Sensing for Agriculture and Food Quality and Safety VII (edited by Kim, M. S. et al.), Paper No. 98640Q, 12 pp. SPIE (The International Society for Optical Engineering), Bellingham, WA. 2017. (Proceedings)  Zhang, Z., Pothula, A. K., and Lu, R. Development of a new bin filler for apple harvesting and infield sorting with a review of existing technologies. ASABE Paper #201700662, 16pp. DOI: 10.13031/aim.201700662. 2017. (Proceedings)  Huang, Y., Lu, R. and Chen, K. Nondestructive measurement of tomato postharvest quality using a multichannel hyperspectral imaging probe. ASABE Paper #201700195, 11pp. DOI: 10.13031/aim.201700195. 2017. (Proceedings)  Lu, Y. and Lu, R. Structured-illumination reflectance imaging coupled with spiral phase transform for bruise detection and three-dimensional geometry reconstruction of apples. ASABE Paper #201700584, 15pp. DOI: 10.13031/aim.20170584. 2017. (Proceedings)  PENNSYLVANIA Zhang, Z., P.H. Heinemann, J. Liu, J.R. Schupp, and T.A. Baugher. 2016. Design and field test of a low-cost apple harvest-assist unit. Transactions of ASABE. 59(5):1149-1156.  Zhang, Z., P.H. Heinemann, J. Liu, T.A. Baugher and J. R. Schupp. 2016. Development of mechanical apple harvesting technology – a review. Transactions of ASABE. 59(5):1165-1180.  Zhang, Z., P. H. Heinemann, J. Liu, J. R. Schupp, T. A. Baugher. 2017. Brush mechanism for distributing apples in a low-cost apple harvest unit. Applied Engineering in Agriculture 33(2): 195-201.  Zhang, Z., and P.H. Heinemann. 2017. Economic analysis of a low-cost apple harvest-assist unit. HortTechnology. 27(2):240-247.  Schupp, J. R., H. E. Winzeler, T. M. Kon, R. P. Marini, T. A. Baugher, L. F. Kime and M. A. Schupp. 2017. A method for quantifying whole-tree pruning severity in mature tall spindle apple plantings. HortScience 52 (accepted for publication 13 July 2017).  Baugher, T., E. Dugan, M. Basedow, T. Jarvinen, J. Schupp, E. Winzeler and M. Schupp. 2017 Competitive orchard systems and technologies. Pennsylvania Fruit News 97(2):27.  Schupp, J., E. Winzeler and M. Schupp. 2017. Evaluation of artificial spur extinction as a potential crop load management technique. Pennsylvania Fruit News 97(1):74-76.  WASHINGTON Fu, H., L. He, S. Ma, M. Karkee, D. Chen, Q. Zhang, and S. Wang. 2017. “Jazz” Apple Impact Bruise Responses to Different Cushioning Materials. Transactions of the ASABE. 60(2): 327-336.  He, L., H. Fu, D. Sun, M. Karkee, and Q. Zhang. 2017. Shake and Catch Harvesting for Fresh Market Apples in Trellis Trained Trees. Transactions of the ASABE. 60(2): 353-360.  He, L., H. Fu, M. Karkee, and Q. Zhang. 2017. An Effect of fruit location on apple detachment with mechanical shaking. Biosystems Engineering, 157: 63-171.  Silwal, A., J. R. Davidson, M. Karkee, C. Mo, Q. Zhang, and K. Lewis. 2017. Design, integration, and field evaluation of a robotic apple harvester. Journal of Field Robotics. 34(6): 1140-1159.  Silwal, A., M. Karkee, and Q. Zhang. 2016. A Hierarchical approach of apple identification for robotic harvesting. Transaction of the ASABE. 59(5): 1079-1086.  Ye, Y., Z. Wang, D. Jones, L. He, M.E. Taylor, G.A. Hollinger, and Q. Zhang. Bin-Dog: A Robotic Platform for Bin Management in Orchards. Robotics, 6(2), 2017.  Zhou, J., L. He, M. Whiting, S. Amatya, P. Larbi, M. Karkee, and Q. Zhang. 2016. Field evaluation of a mechanical-assist cherry harvesting system. Engineering in Agriculture, Environment and Food, 9(4): 324-331.  WEST VIRGINIA Tabb, A. and H. Medeiros. 2017. A robotic vision system to measure tree traits. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).  Tabb, A. and K. M. Ahmad Yousef. 2017. Solving the Robot-world, Hand-eye calibration problem with iterative methods. Machine Vision and Applications. 28(5-6): 569-590.

Impact Statements

(WA) We will continue to further innovate and develop all mechanization, robotic and precision agricultural technologies presented in this report.

Date of Annual Report: 11/17/2018

Report Information

Annual Meeting Dates: 09/20/2018 - 09/21/2018
Period the Report Covers: 10/01/2017 - 09/30/2018

Participants

Zhongyang Cheng, Auburn University;
Daeun Dana Choi, Pennsylvania State University;
Irwin Donis-Gonzalez, University of California, Davis;
Joseph Dvorak, University of Kentucky;
Loren Gautz, University of Hawaii at Manoa;
Dan Guyer, Michigan State University;
Long He, Washington State University;
Paul Heineman, Pennsylvania State University;
Manoj Karkee, Washington State University;
Renfu Lu, USDA/ARS, Michigan;
Filip To, Mississippi State University;
Stavros Vougioukas, University of California, Davis;
Qin Zhang, Washington State University.

Brief Summary of Minutes

The annual meeting was hosted by Mississippi State University (MSU) (local host: Dr. Fillip To) on September 20-21, 2018. The first day of the group’s activities mainly included field tours. The group first visited the USDA/ARS and MSU research facilities in Poplarville, where the station’s directors introduced their research programs in small fruits, and a grower gave a talk about his blue berry and tea production and processing operations. The group then toured the laboratories at the station, followed by a tour to the greenhouse facilities and the station’s blue berry breeding field. Thereafter, the group visited Lazy Magnolia brewery in Kiln, MS, touring the brewing facilities and had lunch there. In the afternoon, the group visited MSU research facilities in McNeill, MS, where the station administrator introduced the station’s research and extension programs and a horticulturist also introduced her research and extension work in urban horticulture.

In the morning of September 21, the group had an annual meeting in IP Casino Resort in Biloxi, MS, chaired by Renfu Lu. Each station (AL, CA, KY, HI, MI, MI-ARS, MS, PA, WA) first gave a brief report on their research activities and accomplishments for the past year. After the station reports, the group began discussing collaboration ideas. One concern was raised about low attendance in recent annual meetings by participating stations. It was agreed that we should encourage all project members to participate in the annual meeting and each station should send at least one member to the annual meeting. Qin Zhang agreed to provide a complete list of all station members for the new project W3009, so that the chair can reach out to all stations for next year’s annual meeting in advance. In addition, it was also mentioned that in the past several annual meetings, no NIFA program leader was present. Qin Zhang agreed to reach out to NIFA and invite a program leader to participate in the group meeting next year. The group also discussed on how to make concerted effects to acquire funding for large projects, which has not been quite successful for the group in recent years. The group then discussed the issue of data repository. There have been huge amounts of data generated in sensors and automation for specialty crops over the years by the group, but they are not shared and publicly available. It was proposed that this group needs to take leadership for creating such data repository. Dvorack (Chair for 2018-2019) agreed to work with NIFA program leader to get their support. A committee was formed, consisting of To, Karkee, Cheng, Choi and Zhang, to work on the data repository project. The group then discussed about providing independent evaluation of different commercial sensors (e.g., NIR sensors). However, concerns were raised on whether these commercial equipment manufacturers would be willing to work with us and in doing so, it may have legal implications and other concerns for such project. However, the group agreed that it would be a good idea to evaluate and test some sensors and algorithms developed by different stations. But no final recommendation was reached on this topic. In addition, it was also suggested that to develop better collaboration among the participating stations, the group may want to consider having additional activities or meetings during the year, such as holding quarterly webinars to share research progress, new topic, and discuss collaboration opportunities.

New officers for 2018-2019: Joseph Dvorak – Chair, Irwin Donis-Gonzalez – Vice Chair, Long He – Secretary. The 2019 annual meeting will be hosted by University of Kentucky (local host: Joseph Dvorak) and specific dates are yet to be decided. The meeting adjourned at noon.

Accomplishments

Short-term Outcomes/Outputs: (AZ) Work continued on a multi-state SCRI project to develop a precision weeding machine for controlling intra-row weeds at the centimeter level scale of accuracy. The machine utilizes a machine vision system for plant detection and herbicidal spray to kill weeds. In FY18, a third spray assembly for precision weeding was developed. The unit comprises a high-speed solenoid valve and a custom-built nozzle body with two straight, thru-hole orifices. The design improves precision to 0.5 cm.  Formal performance trials and integration with the machine vision system are planned for the coming year. The results of this research were disseminated by making presentations at meetings (1), giving demos to various professional and student groups (3) and working with journalist to publish popular press articles (4). A project was initiated to identify parameters for optical detection of bird excrements in leafy green produce fields.  Results showed that reflectance imaging at around 500-525 nm or 600-620 nm could be used to reliably detect excrements from the three bird species tested.  Fluorescence responses to UV illumination at 525 nm were also found to be an effective method for detecting bird droppings.  The significance of these findings it that based on the parameters identified, inexpensive imaging systems could be developed and mounted on drones or ground based vehicles and used to help prevent the fecal contaminant from entering the food supply. (CA) An instrumented strawberry picking cart was developed and used for yield mapping. A prototype fruit-catching system was developed and tested. A simulator for strawberry harvesting was developed and calibrated. Scientific knowledge, on the feasibility and performance of new, novel instrumental methods of objective characterization of product quality, phenotypes for plant breeding, and sensing technologies for food safety and process control optimization were reported in industry meetings and scientific conferences. Scientific knowledge, applied instrumental methods to objectively characterize product quality and digestibility. Five peer-reviewed journal papers were published and four conference papers were presented. One Ph.D. and one M.Sc. thesis were completed. (GA) 1) The processing pipeline of 3D point cloud data developed in this study is an effective tool for blueberry breeding programs (e.g., for mechanical harvesting) and farm management. 2) The fundamental optical properties of blueberry flesh and skin help researchers better understand light interaction with fruit tissues. The results revealed that the near infrared spectral region is an effective spectral range for inspecting bruised blueberries using either reflectance or transmittance method. These findings would provide guidance to develop non-destructive sensing methods for blueberry internal bruising detection. (HI) Designed downdraft, recirculating dehumidified air, 3-layer dryer for two coffee growers and a cacao grower. (IA) Robotic plant phenotyping: How to generate high-quality plant phenotypic data in a high-throughput fashion represents a bottleneck problem in plant breeding and genetic research. We have been developing automated robotic solutions to automate the process of plant phenotyping traits extraction. Sensing of crop plants: Deep neural network based machine vision technology has been developed to recognize and determine the location of specialty crop plants, specifically, broccoli and lettuce.  This technology is being incorporated into an automated mechanical weeding system which will assist growers, particularly of organic crops, to efficiently tackle the problem of weed plant growing in crops.  Assessing mechanical weeding actuators in disturbing soil and plants: Research was initiated into automatic control of an intra-row weeding actuator.  The controller is designed to guide the actuator to follow a trajectory around vegetable crop plants.  Promising controller performance was achieved by guiding the actuator as close to the crop plants as possible while not damaging them to mechanically control intra-row weed plants.  Cucurbit pest exclusion technology: Several investigations into the deployment of row covers were completed in summer of 2018.  The goal of the row covers is to exclude insect pests from cucurbit crops and reduce the spread of bacterial wilt.  Various methods can be used to sealing row cover perimeters and prevent cucumber beetles from entering rows.  Four row cover securing and sealing methods were investigated using polyethylene netting (ProtekNet) as the row cover fabric: burying, PVC clip attachment, sand-bags placed at 5 foot and 14 ft intervals on the fabric. The method of burying the edges showed no discernable advantages over the three methods where the edges were not buried. (MI) Over-the-Row canopy shaking tart cherry production has demonstrated good promise to the extent several progressive growers have implemented the system on a trial basis.  Some challenges remain in fruit handling.  Computed Tomography concepts and parameters for internal fruit, vegetable, and nut quality and defect detection have been developed and further advancement lies in the demand for such systems and the economics so as to draw interest from hardware technology development entities.  Paw paw fruit were found to require near-final on-tree fruit ripening to obtain optimal flavor and texture characteristics, but they can be harvested while slightly immature if a selective harvest technique could be developed. (MI-ARS) A multichannel hyperspectral imaging system in semi-transmittance mode was constructed for detecting internally defective apples. Results showed that combination of six spectra, each covering different sections of fruit, overall resulted in better results for classification of defective and normal apples, with the overall accuracies of as high as 96%. Good progress has been made on the development of structured-illumination reflectance imaging (SIRI) technique as a new modality for enhanced defect detection of fruit. A fast image preprocessing algorithm, called bi-dimensional empirical mode (BEMD), was developed for removing noise and artifacts in the demodulated SIRI images. The proposed BEMD method was further implemented in conjunction with machine learning algorithms to detect both surface and subsurface defects of apples, with superior classification results (up to 98% accuracy). SIRI also showed superior performance in early detection of disease infection in peaches. An improved version bin filler was constructed, tested and evaluated in both laboratory and field conditions. (PA) Conducted strategic planning with representatives from regional horticultural associations. The RootRobot unit was designed and under construction through DOE ARPA-E funding.  The RootRobot will automate the excavation, cleaning, and imaging of corn roots from research plots. Initiated and conducted a new study to evaluate crop sensing in apple trees that were pruned to three levels of severity, with and without prohexadione calcium, a plant growth regulator that reduces current shoot extension growth. Initiated and planted an intensive peach orchard, with four levels of planting density. Once established, this orchard block will be used to evaluate tree density and novel trellis design and components. A sensor-based irrigation system was installed and tested in an apple block. Four irrigation strategies were investigated for scheduling irrigation events: evapotranspiration, crop water stress index, soil water content, and soil water potential. The impact of various canopy depths on machine sensing performances was studied in a tall spindle orchard system. Developed sensing systems measured the size and count of apples at various times from early in the. Various technologies for automated mushroom harvesting have been investigated. A proof of concept for harvesting robot mechanisms that are specifically designed for PA wooden bed system is being developed. (WA) WA team worked on fruit harvesting and handling technologies using a dual-robot system, which is expected to achieve 50% improvement in the cycle time (time for harvesting each fruit) compared to a single robot system used in the past to pick and place fruit. Another fruit harvesting approach evaluated for apple harvesting was to use a targeted shake-and-catch system. This approach showed promise for faster and potentially low cost harvesting of apples for fresh market consumption. However, the method tended to show varietal dependence with Fuji and Jazz showing higher removal efficiency and better quality fruit while varieties like gala and honey crisp suffering from either low removal efficiency, low fruit quality or both. Field assessment tests showed that fruit detachment and collection efficiency increased with shorter branch length on similar size branches, and could reach 90% or more in modern, formally trained orchards. For handing the harvested fruit, our team has developed and evaluated a self-propelled bin managing robot in laboratory and orchard environments. A multi-robot simulation with bin- managing robots and human pickers reduced the time to collect bins in a real-world orchard simulation by up to 30%. Our team also worked on a weeding robot, which was able to control the end-effector base at a desired level of accuracy while traveling on uneven ground causing up to 10° roll and/or pitch of the machine. The machine can follow either linear, sinusoidal or circular paths with a maximum position error of 2.2 cm at an operation speed of 0.10 m/s. In another project, the team evaluated cane bundling mechanism for red raspberries, which showed a success rate of 90% whereas the success percentage for combined bundling and tying mechanisms was ~84%.  The team also works on soil sensing for precision management. The work advanced with the design and testing of a new trailer for electromagnetic induction (EMI) surveys in orchards, remote and proximal sensor-based, and work on sensor fusion for soil profile characterization. WSU team also participated economic analysis of Neutral Harvest Aid System and Sensor Technologies for Fresh Market Highbush Blueberries. Cost-benefit was analyzed for 4 alternative mechanization devices for fresh market blueberries. It was found that price differential between fresh market and processing market blueberries is the main determinant to trigger adoption of mechanized technologies. (WV-ARS) Research centered on creating tools for autonomous shape phenotyping of plants using computer vision and robotics; outreach consisted of giving four invited talks at Phenome 2018, the Donald Danforth Plant Science Center, Michigan State University, and the University of Minnesota, as well as giving public tours. Activities: (CA) Simulation experiments were conducted using 3D models of cling peach and pear trees to investigate the picking efficiency and throughput of robotic harvesters with many cartesian arms, given gripper size and arm extension constraints. A prototype novel fruit-catch harvesting system was developed and tested to assess catching efficiency and fruit bruising. Results were promising and the design is being developed further. A Linear Mixed Model was developed to predict the picking time in manual strawberry harvesting. Prediction errors lower than 10% were achieved. A simulator was developed and calibrated that models crew harvest activities and robot fruit-transporting activities during strawberry harvesting. Robot scheduling algorithms were tested using the simulator. A perception system was developed to detect trees and tree rows for autonomous orchard navigation. A set of 15 fully automated smart machines were designed and deployed in the processing tomato industry in California that prepare and inspect tomato samples and perform disposal and sanitation tasks. Application of commercially available produce quality spectroscopic systems, and nondestructive characterization of structural changes during in vitro gastric digestion of applies using micro Computed Tomography (CT). (GA) 1) We developed a laser ranging sensor based 3D imaging approach to measure blueberry bush size and shape traits that are relevant to mechanical harvesting. One-dimensional traits (height, width, and crown size) had strong correlations between sensor and manual measurements, whereas bush volume showed a decreased correlation. Statistical results demonstrated that the five genotype groups were statistically different in crown size and bush shape. The differences matched with human evaluation regarding optimal bush architecture for mechanical harvesting. 2) Fundamental optical properties (absorption, reduced scattering coefficient, and scattering anisotropy) were measured for healthy and bruised blueberry tissues at the spectral range of 400–1400 nm.  We also investigated the light propagation model of blueberries using Monte Carlo multi-layered simulation. The simulation results showed that the spectral region of 400-700 nm is not effective in detecting bruises due to strong absorption and backward scattering of the blueberry skin. In contrast, the absorption effect of the skin in the near infrared range (930-1400 nm) was small, allowing light to penetrate and interact with the flesh. A scientific study was conducted to develop a calibration using near infrared spectroscopy and capacitance to determine coffee leaf water stress as measured by pressure bomb method. A system was developed to conduct small (100-1000 g) lot fermentation of cacao seed.  (MI) Programming continued on comparison of tart cherry quality resulting from electronic impact data collected from conventional trunk shaking and a developmental over-the-row (OTR) canopy shaking production concept.  Canopy shaking showed more impacts but the severity of impacts, and a possible total integrative analysis of energy of input to the cherry in each system resulting from harvesting could not be concluded as many impacts in both systems exceeded the maximum measurement capacity of the wireless impact sensor. Computed Tomography-based image analysis efforts for sensing quality characteristics of commodities continues only in the capacity of sharing results with various industries looking for opportunity to detect internal characteristics not detectable by current commercial systems.  This technology is in need of advancement by dedicated hardware development beyond the capability of project. New programming was initiated toward determining maturity indicators for harvest of paw paw fruit such that they can reach optimal quality characteristics yet be harvested at a status when low occurrence of damage will occur to the fruit.  (MI-ARS) Experiments were conducted on detecting internal defect of ‘Honeycrisp’ apples using the multichannel hyperspectral system. Experiments were also carried out on using the structured-illumination reflectance imaging (SIRI) for early detection of disease infection for two varieties of peach. Preliminary tests were also conducted on real-time acquisition of SIRI images from moving apples, with promising results. Laboratory tests were conducted using 3-D imaging technique to evaluate the performance of an improved bin filler for distributing apples in the bin. (PA) Rules developed for robotic pruning based on heuristics. Limb to trunk ratio worked well for setting severity determined using maximum limb diameter. Removing next largest branch to threshold is ¾ of the required pruning. Harvest-assist device for small operations was redesigned by undergraduate student design team, to fit on N.M. Bartlett Chariot two-person platform.  This platform was better suited for hilly US orchards than the original platform. The unit was field tested in apple orchards in Fall 2017. (WA) A dual-robot system was developed for fruit picking and catching, which was evaluated in field conditions. The picking hand has been improved using a novel smart soft material. A multi-layer self-propelled shake and catch harvesting platform was developed and further evaluated in 2018 harvest season. A robotic prototype was evaluated for automated bin movement in orchards. The prototype with four wheel steering system used RTK GPS and laser sensing systems to navigate in orchards. In another project, WSU team designed and fabricated a research prototype of self-propelled robotic weeding machine for vegetable production. Another activity was the investigation of mechanized red raspberry cane bundling and tying. A cane tying mechanism has been designed, fabricated, and then evaluated in field operation. WSU team also works on sensing and automation technologies with UASs. One specific project we worked on was to use UASs to deter birds from fruit crops such as wine grapes, blueberries and apples. We are also working on integrating ground and aerial imaging systems to rapidly quantify/evaluate biotic and abiotic stressors in specialty crops using hyperspectral imaging and associated data analytics methods. We have also been evaluating applicability of small-UAS-based multi-spectral sensing modules to monitor retrofitted/modified irrigation techniques. In one of the other projects, sub-surface pulse and continuous drip irrigation treatments effect on vine physiology and fruit quality are being monitored. In another project, the team is developing and automating solid set canopy delivery system for tree fruit and berry crops. This year, we also started working on Localized Sensing of Canopy and Fruit Microclimate for Real-time Management of Sunburn in Apple.

Publications

ARIZONA Lefcourt, A.M., Siemens, M.C. & Rivadeneira, P. 2018. Optical parameters for using VIS reflectance or fluorescence imaging to detect bird excrements in produce fields. Applied Sciences (submitted) CALIFORNIA Arikapudi R., Vougioukas, S.G., (2018a). Estimating the Fruit Picking Throughput of a Telescopic Arm in High Density Trellised Pear Orchards. ASABE Annual International Meeting. Paper Number # 1801684 , Detroit, Michigan. Arikapudi, R., Vougioukas, S. (2018b). A Study on Pick-Cycle-Times of Robotic Multi-Arm Tree Fruit Harvesters. Intl. Conference on Agricultural Engineering (AgEng 2018). Durand-Petiteville, A., Le Flecher, E., Cadenat, V., Sentenac, T.,  Vougioukas, S.G. (2018). Tree detection with low-cost 3D sensors for autonomous navigation in orchards. IEEE Robotics and Automation Letters. 3(4): 3876-3883. Jang, W.J., (2018). Investigation on the Harvest-aid Robot Scheduling Problem and the Implementation of Its Simulation Platform. M.Sc. Thesis. University of California, Davis. Khosro Anjom, F., Vougioukas, S. G., Slaughter, D.C. (2018a). Development of a Linear Mixed Model to Predict the Picking Time in Strawberry Harvesting Processes. Biosystems Engineering. (166): 76-89. Khosro Anjom, F. (2018b). Predictive Modeling of the Temporal Distribution of Tray-Transport Requests for Robot-Aided Strawberry Harvesting. Ph.D. Dissertation. University of California, Davis. Peng, C.,  Seyyedhasani, H., Vougioukas, S.G., (2018). Optimized predictive dispatching of robotic harvest- aids using Multiple Scenario Approach. ASABE Annual International Meeting. Paper Number # 1801694, Detroit, Michigan. Seyyedhasani, H., Peng, C., Vougioukas, S.G., (2018). Efficient Dispatching of a Team of Harvest-aid Ro- bots to Reduce Waiting Time for Human Pickers. ASABE Annual International Meeting. Paper Number # 1801715, Detroit, Michigan. Jantra, C., D.C. Slaughter, P.S. Liang, S. Pathaveerat.  2017.  Nondestructive determination of dry matter and soluble solids content in dehydrator onions and garlic using a handheld visible and near infrared instrument.  Postharvest Biology and Technology.  133: 98-103. Westwood, J.H., R. Charudattan , S.O. Duke, S.A. Fennimore, P. Marrone, D.C. Slaughter, C. Swanton and R. Zollinger.  2018.  Weed Management in 2050: Perspectives on the Future of Weed Science.  Weed Science. Volume: 66   Issue: 3   Pages: 275-285. Perez-Ruiz, M., Brenes, R., Urbano, JM., Slaughter, DC., Forcella, F., Rodriguez-Lizana, A. 2018. Agricultural residues are efficient abrasive tools for weed control. AGRONOMY FOR SUSTAINABLE DEVELOPMENT. Volume: 38: 2 Article Number: 18. FLORIDA Pourreza, A., W. S. Lee, E. Czarnecka, L. Verner, and W. Gurley. 2017. Feasibility of using the optical sensing techniques for early detection of Huanglongbing in citrus seedlings. Robotics 6(11). Doi:10.3390/robotics6020011. Shuaibu, M., W. S. Lee, Y. K. Hong, and S. Kim. 2017. Detection of apple Marssonina blotch disease using particle swarm optimization. Trans. ASABE 60(2): 303-312. Khedher Agha, M. K., W. S. Lee, C. Wang, R. W. Mankin, A. R. Blount, R. A. Bucklin, and N. Bliznyuk. 2017. Detection and prediction of Sitophilus oryzae infestations in triticale via visible and near infrared spectral signatures. Journal of Stored Products Research 72: 1-10. Khedher Agha, M. K., R. A. Bucklin, W. S. Lee, R. W. Mankin, and A. R. Blount. 2017. Effect of drying conditions on triticale seed germination and weevil infestation. Trans. ASABE 60(2): 571-575. Barocco, R., W. S. Lee, and G. Hortman. 2017. Yield mapping hardware components for grains and cotton using on-the-go monitoring systems. UF/IFAS EDIS AE518.  http://edis.ifas.ufl.edu/ae518. GEORGIA Patrick, A., and C. Li. 2017. High throughput phenotyping of blueberry bush morphological traits using unmanned aerial systems. Remote Sensing. 9 (12): 1250. Kuzy, J., Y. Jiang, and C. Li, 2017. Blueberry bruise detection by pulsed thermographic imaging. Postharvest Biology and Technology, 136 (2018): 166-177. Gallardo, R. K., E.T. Stafne, L.W DeVetter, Q. Zhang, C. Li, F. Takeda, J. Williamson, W. Yang, R. Beaudry, W. Cline, R. Allen. 2018. Blueberry producers' attitudes toward harvest mechanization for fresh market. Hort Technology. 28.1: 10-16. Zhang, M., C. Li, F. Takeda, and F. Yang. 2017. Detection of internally bruised blueberries using hyperspectral transmittance imaging. Transactions of ASABE, 60(5): 1-14. Fan, S.X., C. Li, W.Q. Huang, and L.P. Chen. 2017. Detection of blueberry internal bruising over time using NIR hyperspectral reflectance imaging with optimum wavelengths. Postharvest Biology and Technology, 134:55-66. Takeda, F., W. Yang , C. Li, A. Freivalds, K. Sung , R. Xu, B. Hu, J. Williamson and S. Sargent. 2017.  Applying new technologies to transform blueberry harvesting. Agronomy, 7: 33. HAWAII Bittenbender, H. C., L. D. Gautz, E. Seguine, and J. L. Myers. 2017. Microfermentation of Cacao: The CTAHR Bag System. Horttechnology 27(5):690-694. IOWA Conference Papers: Gai, J., L. Tang, I. Tegeler, X.Yu. 2018. Machine vision for plant detection and localization for robotic weeding based on deep convolutional neural network. ASABE Annual International Meeting, Detroit, MI. July 29 - August 1, 2018 Bao, Y. and L. Tang. 2018. A robotized multi-sensor perception-driven indoor plant phenotyping system. ASABE Annual International Meeting, Detroit, MI. July 29 - August 1. Bao, Y. and L. Tang. 2018. Plant architectural traits characterization for maize using time-of-flight 3D imaging. ASABE Annual International Meeting, Detroit, MI. July 29 - August 1. Xiang, L., Y. Bao, L. Tang, and M. G. Salas-Fernandez. 2018. Automated morphological trait extraction for sorghum plants via 3D point cloud data analysis. ASABE Annual International Meeting, Detroit, MI. July 29-August 1. Widmer, J. M., H. Mark Hanna, Brian L. Steward, and Kurt A. Rosentrater. "Improving and Testing Methods of Securing Row Cover for Organic Cucurbit Production." 2018 ASABE Annual International Meeting, Detroit, MI, July 29-August 1, 2018. Paper No. 1801263. DOI:10.13031/aim.201801263 Journal Articles: Hanna, H. M., B. L. Steward, and K. A. Rosentrater. 2018. Evaluating row cover establishment systems for cantaloupe and summer squash. Applied Engineering in Agriculture. 34(2):355-364. https://doi.org/10.13031/aea.12217 Bao, Y., L. Tang, M. W. Breitzman, M. G. Salas Fernandez, P. S. Schnable. 2018. Field-based robotic phenotyping of sorghum plant architecture using stereo vision. Journal of Field Robotics 2018: 1-19. DOI: 10.1002/rob.21830. Bao, Y., D. Shah, L. Tang. 2018. 3D Perception-based Collision-Free Robotic Leaf Probing for Automated Indoor Plant Phenotyping. Transaction of the ASABE 61(3). MICHIGAN Huang, Y., Lu, R., Xu, Y., Chen, K. 2018. Prediction of tomato firmness using a spatially-resolved multichannel hyperspectral imaging probe. Postharvest Biology and Technology. 140:18-26.  Huang, Y., Hu, D., Lu, R., Chen, K. 2018. Quality assessment of tomato quality by optical absorption and scattering properties. Postharvest Biology and Technology. 143:78-85. Huang, Y., Lu, R., Chen, K. 2018. Assessment of tomato soluble solids content and pH by spatially-resolved and conventional Vis/NIR spectroscopy. Journal of Food Engineering. 236:19-28.  Li, R., Lu, Y., Lu, R. 2018. Structured illumination reflectance imaging for enhanced detection of subsurface tissue bruising in apples. Transactions of the ASABE. 61(3):809-819.  Lu, Y., Lu, R. 2017. Non-destructive defect detection of apples by spectroscopic and imaging technologies: A review. Transactions of the ASABE. 60(5):1765-1790.  Lu, Y., Lu, R. 2017. Development of a multispectral structured-illumination reflectance imaging (SIRI) system and its application to bruise detection of apples. Transactions of the ASABE. 60(4):1379-1389.  Lu, Y., Lu, R. 2018. Structured-illumination reflectance imaging coupled with phase analysis techniques for surface profiling of apples. Journal of Food Engineering. 232:11-20. Lu, Y., Lu, R. 2018. Fast bi-dimensional empirical mode decomposition as an image enhancement technique for fruit defect detection. Computers and Electronics in Agriculture. 152:314-323.  Lu, R., Pothula, A. K., Mizushima, A., Vandyke, M. and Zhang, Z. 2018. System for sorting fruit. U.S. Patent #9,919,345. Pothula, A., Zhang, Z., Lu, R. 2018. Design features and bruise damage evaluation of an apple harvest and infield sorting machine. Transactions of the ASABE. 61(3):1135-1144.  Zhang, Z., Pothula, A., Lu, R. 2017. Development and preliminary evaluation of a new bin filler for apple harvesting and infield sorting. Transactions of the ASABE. 60(6):1839-1849.  Zhang, Z., Pothula, A.K., Lu, R. 2017. Economic evaluation of apple harvest and in-field sorting technology. Transactions of the ASABE. 60(5):1537-1550. PENNSYLVANIA Chen, L., Karkee, M., He, L., Wei, Y., & Zhang, Q. (2018). Evaluation of a Leveling System for a Weeding Robot under Field Condition. IFAC-PapersOnLine, 51(17), 368-373. Choi, D., & Jarvinen, T. (2018). A video processing strategy using camera movement estimation for apple yield forecasting. Proceedings of the 9th International Symposium on Machinery and Mechatronics for Agriculture and Biosystems Engineering, page 1-5, Jeju, South Korea, May 28-30, 2018. Feng, J., & He, L. (2018). Tree canopy estimation for mechanical pruning based on 3D Lidar. NABEC Paper No. 18-054. St. Joseph, MI: ASABE. Fu, H., Duan, J., Karkee, M., He, L., Chen, D., Sun, D., & Zhang, Q. (2018). Quantifying fruit quality affected by mechanical impact for selected apple varieties. IFAC-PapersOnLine, 51(17), 250-255. He, L., and J. Schupp. 2018. Sensing and automation in pruning of apple trees: a review. Agron. 2018, 8, 211. <a href="http://www.mdpi.com/2073-4395/8/10/211/pdf">http://www.mdpi.com/2073-4395/8/10/211/pdf</a>. 18 pp. He, L., Zhang, X., Karkee, M., & Zhang, Q. (2018). Fruit Accessibility for Mechanical Harvesting of Fresh Market Apples. ASABE Paper No. 1801007. St. Joseph, MI: ASABE. Jarvinen, T., Choi, D., Heinemann, P., & Baugher, T. A. (2018). Multiple object tracking-by-detection for apple fruit counting on a tree canopy. 2018 ASABE Annual International Meeting, Paper No. 1801193, page 1-8. Kon, T. M., J. R. Schupp, K. S. Yoder, L. D. Combs, and M. A. Schupp. 2018. Comparison of chemical blossom thinners using ‘Golden Delicious’ and ‘Gala’ pollen tube growth models as timing aids. HortScience 53:1143-1151. Schupp, J.R., H.E. Winzeler, T.M. Kon, R.P. Marini, T.A. Baugher, L.F. Kime, M.A. Schupp. 2017. A method for quantifying whole-tree pruning severity in mature tall spindle apple plantings. HortScience 52:1233-1240. Schupp, J., R. Marini and T. Baugher. 2018. Competitive Orchard Systems and Technologies. Pennsylvania Fruit News 98(1):21-23. Schupp, J., T. Baugher and P. Heinemann. 2018. Peach Crop Load Management: Blossom Thinning and Fruit Size. Penn State Fruit Times, <a href="https://extension.psu.edu/peach-crop-load-management-blossom-thinning-and-fruit-size?j=215664&sfmc_sub=22239605&l=159_HTML&u=4146493&mid=7234940&jb=1">https://extension.psu.edu/peach-crop-load-management-blossom-thinning-and-fruit-size?j=215664&sfmc_sub=22239605&l=159_HTML&u=4146493&mid=7234940&jb=1</a> Schupp, J., B. Wiepz, E. Winzeler and M. Schupp. 2018. Evaluation of Artificial Spur Extinction or 6BA at bloom as Potential Crop Load Management Techniques. Pennsylvania Fruit News 98(1):24-25. Wang, C., Lee, W. S., Zou, X., Choi, D., Gan, H., & Diamond, J. (2018). Detection and counting of immature green citrus fruit based on the Local Binary Patterns (LBP) feature using illumination-normalized images. Precision Agriculture. DOI: <a href="https://doi.org/10.1007/s11119-018-9574-5">https://doi.org/10.1007/s11119-018-9574-5</a> Zhang, X., Fu, L., Majeed, Y., He, L., Karkee, M., Whiting, M. D., & Zhang, Q. (2018). Field Evaluation of Data-based Pruning Severity Levels (PSL) on Mechanical Harvesting of Apples. IFAC-PapersOnLine, 51(17), 477-482. WASHINGTON Chandel, A., L. R. Khot, Y. Osroosh and R. T. Peters. 2018. Thermal-RGB imager derived in-field apple surface temperature estimates for sunburn management. Agricultural and Forest Meteorology, 253-254: 132-140. <a href="https://doi.org/10.1016/j.agrformet.2018.02.013">https://doi.org/10.1016/j.agrformet.2018.02.013</a> (5-Year IF: 4.753). Osroosh, Y., L. R. Khot, and R. T. Peters. 2018. Economical thermal-RGB imaging system for monitoring agricultural crops. Computers and Electronics in Agriculture, 147: 34-43. <a href="https://doi.org/10.1016/j.compag.2018.02.018">https://doi.org/10.1016/j.compag.2018.02.018</a> (5-Year IF: 2.502). Sinha, R., L. R. Khot, B. Schroeder and S. Sankaran. 2018. FAIMS based volatile fingerprinting for real-time postharvest storage infections detection in stored potatoes and onions. Postharvest Biology and Technology, 135: 83-92. <a href="https://doi.org/10.1016/j.postharvbio.2017.09.003">https://doi.org/10.1016/j.postharvbio.2017.09.003</a> (5-Year IF: 3.603). Zúñiga C. E., A. P. Rathnayake, M. Chakraborty, S. Sankaran, P. Jacoby and L. R. Khot. 2018. Applicability of time-of-flight based ground and multispectral aerial imaging for grapevine canopy vigour monitoring under direct root-zone deficit irrigation. International Journal of Remote Sensing, In Press (5-Year IF: 1.724). Bahlol, H. Y., R. Sinha, G.–A. Hoheisel, R. Ehsani and L. R. Khot. 2018. Efficacy evaluation of horticultural oil based thermotherapy for pear psylla management. Crop Protection, 113: 97-103. <a href="https://doi.org/10.1016/j.cropro.2018.07.015">https://doi.org/10.1016/j.cropro.2018.07.015</a> (5-Year IF: 1.936). Boydston, R., L. D. Porter, B. Chaves-Cordoba, L. R. Khot and P. N. Miklas. 2018. The impact of tillage on pinto bean cultivar response to drought induced by deficit irrigation. Soil & Tillage Research, 180: 63-72. <a href="https://doi.org/10.1016/j.still.2018.02.011">https://doi.org/10.1016/j.still.2018.02.011</a> (5-Year IF: 3.856). Jarolmasjed, S., S. Sankaran, L. Kalcsits and L. R. Khot. 2018. Proximal hyperspectral sensing of stomatal conductance to monitor the efficacy of exogenous abscisic acid applications in apple trees. Crop Protection, 109: 42-50. <a href="https://doi.org/10.1016/j.cropro.2018.02.022">https://doi.org/10.1016/j.cropro.2018.02.022</a> (5-Year IF: 1.936). Jarolmasjed, S., L. R. Khot and S. Sankaran. 2018. Hyperspectral imaging and spectrometry-derived spectral features for bitter pit detection in storage apples. Sensors, In Press. (5-Year IF: 2.677). Sankaran, S., J. Zhou, L.R. Khot, J.J. Trapp, E. Mndolwa and P.N. Miklas. 2018. High-throughput field phenotyping in dry bean using small unmanned aerial vehicle based multispectral imagery. Computers and Electronics in Agriculture, 151: 84-92. <a href="https://doi.org/10.1016/j.compag.2018.05.034">https://doi.org/10.1016/j.compag.2018.05.034</a> (5-Year IF: 2.502). Gallardo, R.K., E. Stafne, L. Wasko DeVetter, Q. Zhang, C. Li, F. Takeda, J. Williamson, W. Yang, R. Beaudry, W. Cline, and R. Allen. 2018. “Blueberry Producers’ Attitudes toward Harvest Mechanization for Fresh Market.” HortTechnology, 28(1):10-16. Gallardo, R.K. and H. Garming. “The Economics of Apple Production.” In Achieving Sustainable Cultivation of Apples. Ed. Kate Evans. Burleigh Dodds Science Publishing. Cambridge, UK. Published June 16, 2017. Ye, Y., L. He, Z. Wang, D. Jones, G. Hollinger, M. Taylor, and Q. Zhang, (2018). Orchard maneuvering strategy for a robotic bin-handling machine bin-dog a self-propelled platform for bin management in orchards. Biosystems Engineering, 169: 85-103. Ye, Y., Z. Wang, D. Jones, L. He, M. Taylor, G. Hollinger, and Q. Zhang, (2017). Bin-dog: a robotic platform for bin management in orchards.  Robotics, 6(2): Article 12 (17pp). Jones, D., and G. Hollinger, (2017). Planning energy-efficient trajectories in strong disturbances. Robotics and Automation Letters, 2(4): 2080-2087. Alhamid, J.O., C. Mo, <a href="https://www.sciencedirect.com/science/article/pii/S1537511017307742#!">X. Zhang, </a>P. Wang, <a href="https://www.sciencedirect.com/science/article/pii/S1537511017307742#!">M.D.Whiting, </a>Q. Zhang, (2018).  Cellulose nanocrystals reduce cold damage to reproductive buds in fruit crops. Biosystems Engineering, 172: 124-133. Zhang, J., L. He, M. Karkee, Q. Zhang, X. Zhang and Z. Gao. 2018. Branch Detection for Apple Trees Trained in Fruiting Wall Architecture using Depth Features and Regions-Convolutional Neural Network (R-CNN). Computers and Electronics in Agriculture. 155: 386-393. Zhang, X., He, L., Majeed, Y., Karkee, M., Whiting, M. D., & Zhang, Q. 2018. A precision pruning strategy for improving efficiency of vibratory mechanical harvesting of apples. Transactions of the ASABE. 61(5): 1565-1576. Ma, S., Karkee, M., Han, F., Sun, Q., & Zhang, Q.  (2018). Evaluation of shake-and-catch mechanism in mechanical harvesting of apples. Transactions of the ASABE, 61(4): 1257-1263. Khanal, K., S. Bhusal, M. Karkee, Q. Zhang. 2018. Raspberry Primocane Bundling and Taping Mechanisms. Transactions of the ASABE. 61(4): 1265-1274. Ma, S., M. Karkee#, P. Scharf, and Q. Zhang. Adaptability of Chopper Harvester in Harvesting Sugarcane, Energy Cane, and Banagrass. Transactions of the ASABE, 61(1): 27-35. He, L., M. Karkee#, Q. Zhang. 2018. Evaluation of a localized shake-and-catch harvesting system for fresh market apples. Agricultural Engineering International: CIGR Journal, 19(4), pp.36-44. Ma, S., P. Scharf, M. Karkee, Q. Zhang, J. Tong, and L. Yu. 2017. A Study on the Effects of Harvester Off-track Errors on Stubble Losses. Applied Engineering in Agriculture. 33(6): 771-779. Amatya, S., Karkee, M., Zhang, Q. and Whiting, M.D., 2017. Automated Detection of Branch Shaking Locations for Robotic Cherry Harvesting Using Machine Vision. Robotics, 6(4), p.31 Gasch, C.K., D.J. Brown, C.S. Campbell, D.R. Cobos, E.S. Brooks, M. Chahal, M. Poggio, and D.R. Huggins, 2017. A field-scale sensor network data set for monitoring and modeling the spatial and temporal variation of soil water content in a dryland agricultural field. Water Resources Research. 53: 10878-10887. DOI: 10.1002/2017WR021307 WEST VIRGINIA <ol start="2018"> <li>A. Dias, A. Tabb and H. Medeiros, “Multispecies Fruit Flower Detection Using a Re_ned Semantic Segmentation Network," in IEEE Robotics and Automation Letters, vol. 3, no. 4, pp. 3003-3010, Oct. 2018. </li> </ol> <ol start="2018"> <li>A. Hollender, P. Thierry, A. Tabb, T. Hadiarto, C. Srinivasan, W. Wang, Z. Liu, R. Scorza, and C. Dardick, \Loss of a highly conserved sterile alpha motif domain gene (WEEP) results in pendulous branch growth in peach trees," Proceedings of the National Academy of Sciences, vol. 115, no. 20, pp. E4690- E4699, 2018. </li> </ol> <ol start="2018"> <li>A. Hollender, J. M. Waite, A. Tabb, D. Raines, S. Chinnithambi, and C. Dardick, “Alteration of TAC1 expression in Prunus species leads to pleiotropic shoot phenotypes," Horticulture Research, vol. 5, no. 1, p. 26, May 2018. </li> </ol> <ol start="2018"> <li>A. Dias, A. Tabb, and H. Medeiros, Apple flower detection using deep convolutional networks," Computers in Industry, vol. 99, pp. 17-28, Aug. 2018. </li> </ol> <ol start="2018"> <li>Tabb and H. Medeiros, “Automatic segmentation of trees in dynamic outdoor environments," Computers in Industry, vol. 98, pp. 90-99, Jun. 2018. </li> </ol> Peer-reviewed conferences: <ol start="1943"> <li>Tabb and H. Medeiros, “Fast and Robust Curve Skeletonization for Real-World Elongated Objects," in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018, pp. 1935-1943. </li> </ol> <ol start="595"> <li>Tabb, K. E. Duncan and C. N. Topp, “Segmenting Root Systems in X-Ray Computed Tomography Images Using Level Sets," in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018, pp. 586-595. </li> </ol> Software releases: <ol start="2017"> <li>Tabb. 2017. Code from: Fast and robust curve skeletonization for real-world elongated objects. Ag Data Commons. 10.15482/USDA.ADC/1399689 </li> </ol> Data releases: P. A. Dias, A. Tabb, H. Medeiros. Multi-species fruit ower detection using a refined semantic segmentation network. Ag Data Commons.10.15482/USDA.ADC/1423466

Impact Statements

(WV-ARS) Allowed the quantification of plant phenotype, which is needed to verify hypotheses about gene function, as well as discover new phenotypes and gene functions.