Brief Summary of Minutes of Annual Meeting

The 2020 annual meeting was originally planned to be held at Washington State University in September 2020. Due to the Covid-19 pandemic, the meeting was cancelled. The officer team had a zoom meeting to discuss the final report, new officer nomination, and the location for the next annual meeting. The team nominated Yu Jiang (Cornell University) for the new secretary, Daeun Choi (Penn State) and Long He (Penn State) promoted to the vice chair and chair respectively, and Irwin Donis-Gonzalez (UC Davis) became the past chair. The team also agreed to have the 2021 annual meeting at Washington State University. 

Arizona
• A high speed and centimeter scale resolution sprayer that can spot apply herbicides to weeds while traveling at speeds that are viable for commercial farming operations was developed and tested. During this review period, an extensive outreach effort was made to educate stakeholders and garner commercial interest in the technology. Over 500 individuals were reached via presentations at field days (1), extension/ag industry meetings (4) and by organizing workshops/tours/field days (2) and hosting student groups (2). Many more were reached through publishing ag industry articles (3) and on-line postings of presentations (3) and device in action videos (2). This activity has led to in-person commercialization conversations with seven start-up companies that are developing automated in-row weeding robots.
• Additionally, the technology was further developed so that it is capable of sub-centimeter scale resolution spot spraying at commercially viable speeds. Performance testing and research efforts towards developing a computer imaging system that provides a real-time weed targeting map is planned.

California
• Low-cost wireless mesh network of soil moisture sensors for precision irrigation
We have designed a low cost solution of wireless moisture sensors suitable for precision agriculture and urban landscape using LoRa. LoRa communication has been adopted as it enables the mesh network to relay over distances longer than the traditional Wifi or Bluetooth, and with power consumption lower than Zigbee. LoRa module was enabled to work as a provisioned mesh node in which nodes are inter-connected dynamically and non-hierarchically to route to the base node. This way the entire system is decentralized and easy to self-heal in case of node failure. Also the lack of dependency on one node allows for every other node to participate in the relay of information. Low cost capacitance sensors were calibrated and programmed to collect moisture measurement at a frequency of 1 hour. Cloud-based server has been used for off-site data storage and visualization.
• Data driven model to estimate actual evapotranspiration from simple on-site weather stations
Two commercial all-in-one weather stations were installed next to an EC station over an alfalfa-field to evaluate the possibility of using simple and commercial all-in-one meteorological stations on-site as an alternative to EC measurements to estimate hourly Eta. Different sets of input data (weather parameters) and different machine learning models (Linear regression, Gaussian process regression, support vector machine, and artificial neural networks) will be employed to analyze the ability of data-driven modeling to estimate actual evapotranspiration. The ability of optimization-based machine learning methods like genetic programming and group method of data handling can be analyzed as well. To identify the most relevant set of inputs in ETa modeling, Average Mutual Information (AMI), and Minimum Redundancy Maximum Relevance (MRMR) algorithms will also be used.
• Operational and safety evaluation criteria for All-Terrain Vehicles
Several operational and safety evaluation criteria for All-Terrain Vehicle (ATV) equipped with Crush Protection Devices were developed in a study. Enhancing criteria in previous studies. Also, previous studies regarding the CPD performance in ATV rollover incidents were reviewed.
Offered a virtual extension course through the Postharvest technology center short course series in the field of agricultural safety and health.
Several ATV safety booths were held in different events such as the World Ag Expo and UC Davis field day for FFA and 4H students.
• Lift-assist mechanism to adjust the foldable rollover protective structures (FROPS)
A lift-assist mechanism to raise and lower the foldable rollover protective structures (FROPS) from the operator's seat was designed, manufactured, and tested. The design considered can be retrofitted and will not modify or compromise the FROPS structure. A universal lift-assist lever design has been constructed and successfully tested for three FROPS of different sizes meeting appropriate ergonomics engineering standards.
• Review of injury burden of ATV use in agriculture
A comprehensive review was conducted to evaluate the current injury burden of ATV use in agriculture, the need for future research, and possible solutions related to agricultural ATV safety. Potential injury prevention approaches are evaluated based on the hierarchy of control, including elimination or substitution, engineering control, administrative authority, training, and use of personal protective equipment.
• Integrated color computer vision system for fresh walnut kernels
Designed, evaluated and published findings for a fully integrated color computer vision system to determine external properties such as surface color and textural aspects of peeled fresh walnut kernels.
• Portable spectrometers to non-invasively predict table grape quality
Published findings related to the study were two commercially available portable spectrometers (F-750: Felix Instruments, WA, USA; and SCiO: Consumer Physics, Tel Aviv, Israel) were evaluated to non-invasively predict quality attributes, including the dry matter (DM), and total soluble solids (TSS) content of three fresh table grape cultivars (‘Autumn Royal’, ‘Timpson’, and ‘Sweet Scarlet’) and one peach cultivar (‘Cassie’).
• Internal microstructure of apples using micro computed tomography
Developed and published a technique to evaluate internal microstructure of apples using micro computed tomography (-CT) during digestion trials. -CT image slices showed differences in cell membrane structure after digestion. Digested samples contained larger cells, suggesting cellular breakdown induced by the presence of gastric fluid. This observation is not the result of water absorption; as larger cellular structures were not present in apples soaked in water.
Offered virtual extension courses through the Postharvest technology center short course series, in the field of none-invasive assessment of quality.
Built an online sensing system to predict water activity and moisture content of dried produce using a commercial Time-Domain reflectometry device. Evaluation and validation is ongoing.
• Efficient use of water resources in orchard crop production
During the 2020 growing season, a leaf monitor system was used in a walnut orchard in Winters, CA to monitor plant water status. The continuous data obtained from leaf monitors were analyzed on a weekly basis and 15-day changes in plant water status were estimated to determine the incidence of stress, if any. The system appeared to work well in keeping the walnut trees stress free throughout the whole season (- only incidence of stress detected was due to pump failure towards the end of the season). A dynamic heat and mass transfer model of the leaf monitoring system is being developed to address the acclimatization issues which appear to effect plant response as season progresses.
• Computer-controlled orchard harvest platform
A commercial harvest-aid orchard platform was modified so that pickers on the right side of the platform can work at variable heights from the ground. Actuation was performed via hydraulic cylinders under computer control. The platform’s speed was also computer controlled. A stereo camera system in the front of the platform detected apples, and two instrumented picking bags measured each picker’s harvesting rate. An online optimizing controller was developed, tested and tuned to adjust picker working height and platform speed, based on the sensed fruit load and workers’ picking speeds. The objective was to maximize the machine’s harvesting throughput. Experiments were performed in September 2020, in a Fuji apple orchard, in Lodi CA, and 3.3 tn of apples were harvested, in total. Results showed that the machine’s harvesting speed increased by 11.3% to 26% compared to the speed of the conventional, commercial platform.
A simulator was further developed and calibrated to model crew harvest activities and robot fruit-transporting activities during strawberry harvesting. Robot scheduling algorithms were tested using the simulator, and labor efficiency increases ranged between 15% and 24%.
• Novel crop recognition technique for robotic weed control
A novel technique using crop signaling to detect and classify weeds vs. crop plants for robotic weed control in leafy vegetables was successfully developed. Three different crop signaling-based machine vision systems were developed for plant labels, topical markers, and systemic markers. Several trials have been conducted for weed control in both tomato and lettuce fields. The experimental result shows that the system can detect and distinguish crop plants from weeds with 100% accuracy in a field having densely populated weed with no false-positive error.
• AI technologies for agricultural production
Developed a deep learning imaging and analysis system for direct biomass prediction of leafy greens grown in a controlled indoor environment. The system enables non-destructive monitoring of growth rates for individual plants and is capable of detecting stress induction with 1-2 days. We are in the process of preparing a manuscript for submission.
Developed and tested an AI-enabled a prototype sensing kit that mounts on existing farm vehicles and uses computer vision to estimate yield at about 2 – 3 m resolution within vineyards. The kit includes custom lighting, GPU processing, GPS, power distribution, and accompanying enclosures. We have recorded data for about 50k grapevine plants with corresponding harvester-based yield monitor data. This data will be used to train a deep learning model for predicting, and eventually forecasting yield.

Connecticut
A multi-disciplinary team at the University of Connecticut began work to develop a monitoring system for insect pest damage using small unmanned aerial systems (UAS) outfitted with spectral sensors. The project objective is to detect the presence and early plant damage caused by the potato leafhopper Empoasca fabae on beans. Experiments are underway to test the impact of the potato leafhopper feeding on 3 different bean cultivars and associated leaf spectra. Unfortunately, due to the COVID-19 pandemic, field tests were not possible as originally planned.

Georgia
• Fruit traits such as cluster compactness, fruit maturity, and berry number per clusters are important to blueberry breeders and producers for making informed decisions about genotype selection related to yield traits and harvestability as well as for plant management. We developed a data processing pipeline to count berries, to measure maturity, and to evaluate compactness (cluster tightness) automatically using a deep learning image segmentation method for four southern highbush blueberry cultivars (‘Emerald’, ‘Farthing’, ‘Meadowlark’, and ‘Star’).
• Early detection of internal bruises in blueberries is a significant challenge for the blueberry industry. We developed a method to detect blueberries’ internal bruising accurately, after mechanical damage from hyperspectral transmittance images (HSTIs), using the deep learning-based method of fully convolutional networks (FCNs) for segmentation tasks. To improve detection accuracy, a total of three classes (bruised tissue, unbruised tissue, and calyx end of blueberries), were treated as segmentation targets. A near-infrared hyperspectral imaging system was used to acquire transmittance images of 1200 blueberries, and the images were divided randomly to form training, validation, and testing sets. Three categories of input HSTIs were used to evaluate the FCN models using pre-trained weights (transfer learning) and random initialization. Random forests and linear discriminant analysis were applied to generate 9-channel and 3-channel input images along with full-wavelength multi-channel images. The results indicate that when using the deep learning approach, blueberry bruises and calyx ends can be segmented from the blueberry fruit as early as 30 min after mechanical damage has been inflicted on the blueberries. The new full-wavelength model with random initialization had the highest accuracy (81.2% over the entire test set), and can be used to research the resistance of blueberry fruit to mechanical damage. The new 3-channel and 9-channel models show potential for application to packing-line detection and online inspection.
• We also developed robotic platforms to be used for in-field plant high throughput phenotyping.

Iowa
• Modelled and measured the soil reaction forces on a rotating time mechanism to be use for robotic mechanical weeding.
• Launched the ISU Soil-Machine Dynamics Laboratory for investigating ground-engaging tool performance and wear and traction system mobility.
• Developed navigation controller for the field-based plant phenotyping platform – PhenoBot 3.0. Both under- and above-canopy vision based row detection algorithms and navigation control algorithms based on Pure Pursuit and Linear Quadratic Gaussian were developed for PhenoBot 3.0 and field tested this summer. Machine learning algorithms for stalk (StalkNet) and leaf angle (AngleNet) detection for maize and sorghum plants were developed; and in conjunction with our customized PhenoStereo 3D sensor, highly accurate stalk size and leaf angle measurements were obtained.

Michigan
• The potential for Computed Tomography (CT) was demonstrated in some cases coupled with parallel studies of hyperspectral imaging and spectroscopy, to have good potential for non-destructive sensing of internal defects and attributes in various specialty crops which are important to consumers and not measurable manually or with presently available sorting technology. While no direct studies or research was conducted related to this programming during this reporting period, opportunity for moving the concept of CT technology for sorting specialty crops to commercial application was continued through collaboration with a specialty crop importer/exporter having special interest in chestnut. Through this entity, a company with electronic sorting and measurement experience including the development of new high-speed CT imaging has been brought to the table and is participating in testing and data analysis algorithm development focused on chestnut defect/quality assessment. Results are promising to date with further testing planned this season.
• Potential chestnut harvest solutions ranging from manual harvest assist tooling (“basic automation”), low-power mechanical systems, to possible opportunities for feasible small but multipliable robotic or co-robotic technology has been worked on or investigated with a faculty-student extracurricular engineering group and Mechanical Engineering colleagues interested in sustainable agriculture solutions. Possible external proposal opportunities have also been identified and will likely be pursued. Harvest assist prototype systems were built and evaluated, however the programming was put on hold with the COVID-19 closure of the university. Many chestnut producers are ‘caught’ between being of size large enough to afford European mechanical harvesters but yet are too large to conduct harvest manually as their orchards come into full production, and thus a void exists in feasible harvest solutions.
• Pawpaws are limited in the opportunity to advance into a more substantial or significant commodity due to their need to nearly fully tree ripen and because they are relatively easy to damage during handling once ripe. Thus, opportunity for incorporation into the fresh market is very limited and the skin/peel must be removed prior to any attempt to process, such as into a puree. A student-faculty-stakeholder team investigated concepts to improve effectiveness and efficiency of peel removal and potentially, either partially or fully, automate the process. Success was obtained in both efficiency and effectiveness in getting a pawpaw to a “state” such that the peel could easily be removed with very minimal loss of desirable flesh. Concepts for automating the process were proposed should the level of pawpaw production warrant such.
• Development of a text on Tree Fruit Automation was led by two colleagues of this multi-state project and involved multiple W3009 members as well as other national and international colleagues. The contribution from this specific project has been a chapter on Tree Fruit Harvest Technology.

Oklahoma
• We focused on three tasks: 1) Re-design and re-configure a drone platform; 2) Re-design the ground-based, remote-controlled peanut phenotyping platforms; and 3) Develop image processing and analysis algorithms for counting peanut flowers within canopy and identify diseased plants.
• The drone used for experiment in previous years carried only an RGB camera, which limited its applications. We designed a new drone system which could carry multiple cameras/sensors capture images simultaneously. In the summer 2020, the drone was used to collect RGB, thermal, and NDVI images for peanut field. All the data collected were time and location stamped.
• The previously designed ground-based peanut phenotyping system was very bulky and the mechanical driving modules were not running smoothly in the field. For the image acquisition, the shadows from the platform affected the quality of the collected images. Another problem was that the platform was driven by two deep-cycle batteries, which could only last for 1.5 hours. We upgraded the old platforms with the new design of the mechanical driving modules to optimize the maneuverability of the platforms, adding new shading materials to avoid the shadow, and using solar panels with the batteries to extend the running time of the platform.
• Due to the Covid-19 pandemic and unstable weather conditions, we were not able to complete the all planned field experiment. Hence, the data for validation process on the system design and algorithm development was not sufficient.

Pennsylvania
• Orchard temperature profiles were measured utilizing a propane heater in April 2020. This effort was part of the project on automated frost protection. Air temperatures were measured in horizontal grid and vertical grid patterns to determine the distribution of heat. This will help determine the movement patterns of autonomous ground vehicles carrying the heaters.
• The RootRobot unit, part of the DOE ARPA-E DEEPER project, was further tested in the laboratory, then brought to the field in September 2020 to begin tests on actual corn plantings. The RootRobot excavates and prepares corn stalks for phenotyping through imaging
• A three-rotational (3R) degrees of freedom (DoF) end-effector was designed and integrated with a cartesian manipulator by considering maneuvering, spatial, mechanical, and horticultural requirements. Simulations and a series of field work were conducted to test the performance of the system. The field tests validated the simulation results, and the end-effector successfully cut branches up to ~25 mm diameter at wide range of orientations. Meanwhile, a simulation study focused on investigating the branch accessibility of a six-rotational (6R) degrees of freedom (DoF) robotic manipulator with a shear blade type end-effector. With the developed algorithms, a collision-free path was created to the targeted branch in the virtual environment.
• An unmanned ground-based canopy density measurement system was developed to support precision spraying in apple orchards. A data processing and analysis algorithm was also developed to measure point cloud indices from 3D LiDAR sensor to describe the distribution of tree canopy density. Finally, a canopy density map was generated to provide a graphical view of the tree canopy density in different sections.
• An IoT-based precision irrigation system with LoRaWAN technology was developed and evaluated in both vegetable field and tree fruit orchards. Soil moisture sensors were installed in the field, and the data was sent to a cloud-based platform in real-time (10 minutes interval). The irrigation system was automatically operated with controlling the solenoid valves to apply water to the field based on the soil moisture thresholds.
• Heating requirement maps were created utilizing UAV-based thermal and RGB cameras, computer vision techniques, and artificial flower bud critical temperatures to simulate orchard heating demands during frost events. The results demonstrated the feasibility of the proposed orchard heating requirement determination methodology, which has the potential to be a critical component of an autonomous, precise frost management system.
• A 3D machine vision system was developed to detect individual mushrooms among highly clustered crops. A practical 3D mobile imaging platform for mushroom production beds acquired RGB-D images from various angles, created high-resolution composite point cloud images using an iterative closest algorithm. Mushroom detection accuracies using various point cloud image resolutions were compared to investigate an optimal level of image details for both processing time and accuracy of the system.
• An external lighting system using LEDs by over-current was developed to produce a powerful flash was developed as a viable active lighting source for daytime imaging. The system was deployed to an apple orchard to take images in both sunny and cloudy days on different canopy structures. The results indicate a substantial improvement over using a camera’s auto-exposure setting for outdoor imaging regarding both color consistency and motion blur effects on images.

Washington
• Optimized a vision-based fruit orientation estimation and obstacle avoidance system for a 12-armed robotic apple harvester.
• Developed a machine-vision system for detecting flower clusters (with 86% accuracy) and estimating flower density (with 84% accuracy) in apple and cherry orchards, which will be used in developing an automated thinning and pollination systems.
• Developed a machine-vision and robotic system for pruning apple trees, which was tested in the laboratory environment with more than 90% accuracy in reaching and cutting target branches.
• Developed and tested an automated green shoot thinning mechanism for grapevines (with 1.4 cm cordon following accuracy) that used a deep-learning-based machine vision system for detecting vine cordon and shoots and for estimating trajectory fitting model which reached a 80% cordon trajectory estimation accuracy.
• Further optimized a fixed spray system (i.e. solid set chemical delivery system configurations and pertinent field validation for tree fruit orchards.
• Improved and conducted field testing of an Internet-of-Things (IoT) enabled Crop Physiology Sensing System (CPSS) for apple fruit surface temperature monitoring and real-time actuation of modified evaporative cooling system for heat stress management in fresh market apple cultivars.
• Developed hyperspectral imaging based spectral sensing for grapevine leafroll disease detection at asymptomatic stages and pertinent data mining for identification of salient spectral bands.

West Virginia
The USDA-ARS-AFRS location in Kearneysville, WV concentrated on developing tools for plant phenotyping using computer vision, specifically for shape. Publications included the extension of one such tool for trees, applied to medical domain (Zhu et al. 2020), a collaboration in strawberry (Feldmann et al. 2020), and studies for automated mark-and-release for invasive insects (Kirkpatrick et al. 2020). Code and data was released for two tools as well.

Arizona
Raja, R., Slaughter, D.C., Fennimore, S.A., Nguyen, T.T., Vuong, V.L., Sinha, N., Tourte, L., Smith, R.F. & Siemens, M.C. 2019. Crop signaling: A novel crop recognition technique for robotic weed control. Biosystems Eng. 187: 278-291.

California
Rojo, Francisco, Rajveer Dhillon, Shrinivasa Upadhyaya, and Bryan Jenkins. 2020. Development of a dynamic model to estimate canopy par interception. Biosystems Eng. 198:120-136
Rojo, Francisco, Rajveer Dhillon, and Shrinivasa Upadhyaya. 2020. Comparing ground-based par interception data with UAV images and sun position. Submitted for publication is Applied Engineering in Agriculture.
Khorsandi, F., P.D. Ayers, E.J. Fong. 2019. Evaluation of Crush Protection Devices for agricultural All-Terrain Vehicles. Biosystems Engineering. Volume 185, September 2019, Pages 161-173
Peng, C., Vougioukas, S.G. (2020). Deterministic predictive dynamic scheduling for crop-transport co-robots acting as harvesting aids. Computers and Electronics in Agriculture, 178, 105702. https://doi.org/10.1016/j.compag.2020.105702
Fei, Z., Shepard, J., Vougioukas, S.G. (2020). Instrumented Picking Bag for Measuring Fruit Weight During Manual Harvesting. Transactions of the American Society of Agricultural and Biological Engineering. IN PRESS.
Thayer, T., Vougioukas, S.G., Goldberg, K., Carpin, S. (2020). Multi-Robot Routing Algorithms for Robots Operating in Vineyards. IEEE Transactions on Automation Science and Engineering, 17(3): 1184-1194. https://doi.org/10.1109/TASE.2020.2980854
Seyyedhasani, H., Peng, C., Jang, W., Vougioukas, S.G. (2020). Collaboration of Human Pickers and Crop-transporting Robots during Harvesting - Part I: Model and Simulator Development. Computers and Electronics in Agriculture. (172): p.105324. https://doi.org/10.1016/j.compag.2020.105324
Seyyedhasani, H., Peng, C., Jang, W., Vougioukas, S.G. (2020). Collaboration of Human Pickers and Crop-transporting Robots during Harvesting - Part II: Simulator Evaluation and Robot-Scheduling Case-study. Computers and Electronics in Agriculture. (172): p.105323. https://doi.org/10.1016/j.compag.2020.105323
Agricultural All-Terrain Vehicle Safety. Committee on Agricultural Safety and Health Research and Extension. 2020. Agricultural All-Terrain Vehicle Safety. USDA-NIFA. Washington, DC.
Ayers, P.D., F.K. Khorsandi, M.J. Poland, C.T. Hilliard. 2019. Foldable rollover protective structures: Universal lift-assist design. Biosystems Engineering. Volume 185, September 2019, Pages 116-125
Khorsandi, et al. In Press. A manuscript titled “Agricultural All-Terrain Vehicle Safety: Hazard Control Methods Using the Haddon Matrix” will be published in Journal of Aeromedicine.
Donis-Gonzalez, I.R., Valero, C., Momin, M.A., Kaur, A., Slaughter, D.C., 2020. Performance Evaluation of Two Commercially Available Portable Spectrometers to Non-Invasively Determine Table Grape and Peach Quality Attributes. AGRONOMY-BASEL Vol. 10: DOI: 10.3390/agronomy10010148.
Donis-Gonzalez, I.R., Sidelli, G., Bergman, S.M., Slaughter, D.C., Crisosto, C.H. 2020. Color Vision System to Assess English Walnut (Juglans Regia) Kernel Pellicle Color. Postharvest Biology and Technology. Volume 167, September 2020, 111199.doi.org/10.1016/j.postharvbio.2020.111199
Olenskyj, A.G., I.R. Donis-González, G.M. Bornhorst. 2020. Nondestructive characterization of structural changes during in vitro gastric digestion of apples using 3D time-series micro-computed tomography. Journal of Food Engineering. Volume 267, February 2020, 109692
Raja, R., Slaughter, D.C., Fennimore, S.A., Nguyen, T.T., Vuong, V.L., Sinha, N., Tourte, L., Smith, R.F., Siemens, M.C., 2019. Crop signalling: A novel crop recognition technique for robotic weed control. Biosystems Engineering. Vol 187: 278-291. DOI: 10.1016/j.biosystemseng.2019.09.011.
Raja, R., Nguyen, T.T., Slaughter, D.C., Fennimore, S.A., 2020. Real-time robotic weed knife control system for tomato and lettuce based on geometric appearance of plant labels. Biosystems Engineering. Vol. 194: 152-164.
Kennedy, H. Fennimore, S.A., Slaughter, D.C., Nguyen, T.T., Vuong, V.L., Raja, R., Smith R.F., Crop Signal Markers Facilitate Crop Detection and Weed Removal from Lettuce and Tomato by an Intelligent Cultivator. Weed Technology. DOI: https://doi.org/10.1017/wet.2019.120

Georgia
Iqbal, J., Xu, R., Halloran, H., and Li, C. 2020. Development of a Multi-Purpose Autonomous Differential Drive Mobile Robot for Plant Phenotyping and Soil Sensing. Electronics, 9 (9), 1550.
Ni, X, Li, C, Jiang, H, and Takeda, F. 2020. Deep learning image segmentation and extraction of blueberry fruit traits associated with harvestability and yield. Horticulture Research, 7 (1), 1-14.
Iqbal J., Xu, R., Sun, S., and Li, C. 2020. Simulation of an autonomous mobile robot for LiDAR-based in-field phenotyping and navigation. Robotics, 9 (2), 46.
Jiang, Y. and Li, C. 2020. Convolutional neural networks for image-based high throughput plant phenotyping: A review. Plant Phenomics, 2020 (4152816).
Jiang, Y., Snider, J. L., Li, C., Rains, G. C., and Paterson, A. H. 2020. Ground based hyperspectral imaging to characterize canopy-level photosynthetic activities. Remote Sensing, 12 (2), 315.
Zhang, M., Jiang, Y., Li, C., and Yang, F. 2020. Fully convolutional networks for blueberry bruising and calyx segmentation using hyperspectral transmittance imaging. Biosystems Engineering, 192, 159-175.

IOWA
Kshetri, S., B. L. Steward, J.J. Jiken, L. Tang, and M. Tekeste. 2019. Investigating effects of interaction of single tine and rotating tine mechanism with soil on weeding performance using simulated weeds. Transactions of the ASABE 62(5): 1283-1291.
Gai, J., L. Tang, and B.L. Steward. 2020. Automated crop plant detection based on the fusion of color and depth images for robotic weed control. Journal of Field Robotics. 37(1): 35-52.
Schramm, M. W., H. M. Hanna, M. J. Darr, and S. J. Hoff, and B. L. Steward. 2019. Sub-second wind velocity changes one meter above the ground. Applied Engineering in Agriculture 35(5): 697-704.
Mantilla-Perez, M. B., Y. Bao, L.Tang, P. S. Schnable, M. G. Salas-Fernandez. 2020. Towards "smart canopy" sorghum: discovery of the genetic control of leaf angle across layers. Plant Physiology, DOI: https://doi.org/10.1104/pp.20.00632

Steward, B. L., H. M. Hanna, P. M. Dixon, R. K. Mompremier. 2019. Measuring and modeling the movement of spray droplets into off-target areas. ASABE Paper No. 1901496. St. Joseph, Mich.: ASABE. DOI: doi.org/10.13031/aim.201901496
Gai, J., T. Tuel, L. Xiang, L. Tang. 2020. PhenoBot 3.0 - an Autonomous Robot for Field-based Maize/Sorghum Plant Phenotyping, Phenome 2020, Tucson, AZ, February 24-27.
Gai, J., T. Tuel, L. Xiang, L. Tang. 2020. Developing the Control System of an Autonomous Robot for Field-based Maize/Sorghum Plant Phenotyping, 2020 ASABE Annual International Meeting, Omaha, Nebraska, July 12–15, 2020.
Xiang, L., J. Gai, L. Tang. 2020. Developing a high-throughput stereo vision system for plant phenotyping. 2020 Phenome, Tucson, AZ, Feb. 24-27, 2020.
Xiang, L., L. Tang, J. Gai, & L. Wang. 2020. PhenoStereo: a high-throughput stereo vision system for field-based plant phenotyping-with an application in sorghum stem diameter estimation. 2020 ASABE Annual International Virtual Meeting. July 13-15, 2020. Paper No. 2001190

Michigan
Rady, A.M., Guyer, D.E., Donis-Gonzalez, I.R., Kirk, W., Watson, N.J. 2020. A comparison of different optical instruments and machine learning techniques to identify sprouting activity in potatoes during storage. Journal of Food Measurement and Characterization. doi.org/10.1007/s11694-020-00590-2.

Pennsylvania
Refereed Journals
Caliskan-Aydogan, O., H. Yi, J.R. Schupp, D. Choi, P. H. Heinemann, V. M. Puri. 2020. Changes in thermal properties of 'Gala' apple during the growing season. Transactions of the ASABE, 63(2), 305-315.
Fu, H., Karkee, M., He, L., Duan, J., Li, J., & Zhang, Q. (2020). Bruise Patterns of Fresh Market Apples Caused by Fruit-to-Fruit Impact. Agronomy, 10(1), 13.
Kon, T. M., J. R. Schupp, M. A. Schupp, and H.E. Winzeler. 2020. Screening thermal shock as an apple blossom thinning strategy. II. Pollen tube growth and spur leaf injury in response to thermal shock temperature and duration. HortScience, 55(5), 632-636.
Kon, T. M., M. A. Schupp, H.E. Winzeler and J. R. Schupp. 2020. Screening thermal shock as an apple blossom thinning strategy. I. Stigmatic receptivity, pollen tube growth, and leaf injury in response to thermal shock temperature and timing. HortScience, 55(5), 625-631.
Zahid, A., He, L., Zeng, L., Choi, D., Schupp, J., & Heinemann, P. (2020). Development of a Robotic End-Effector for Apple Tree Pruning. Transactions of the ASABE, 63, 847-856.
Zahid, A., Mahmud, M., He, L., Choi, D., Schupp, J., & Heinemann, P. Development of an Integrated 3R End-effector with a Cartesian Manipulator for Pruning Apple Trees. Computers and Electronics in Agriculture, 179.
Zeng, L., Feng, J., & He, L. (2020). Semantic segmentation of sparse 3D point cloud based on geometrical features for trellis-structured apple orchard. Biosystems Engineering, 196, 46-55.
Zhang, X., He, L., Karkee, M., Whitting, M., & Zhang, Q. (2020). Field Evaluation of Targeted Shake-and-Catch Harvesting Technologies for Fresh Market Apple. Transactions of the ASABE. [In press].
Zhang, X., He, L., Zhang, J., Whiting, M. D., Karkee, M., & Zhang, Q. (2020). Determination of key canopy parameters for mass mechanical apple harvesting using supervised machine learning and principal component analysis (PCA). Biosystems Engineering, 193, 247-263.

Non-refereed publications
Choi, D., J. Schupp, T. Baugher, and L. He. Evaluation of effective canopy depths of apple trees for optimal machine sensing performance – Year2/2. PA Fruit News 100(1):39-41.
He, L. (2020). Drip Irrigation and Sensor-Based Precision Irrigation. In the Penn State Tree Fruit Production Guide. (2020-2021), (pp. 426-430).
He, L., & Weber, D. (2020). Updates on Soil Moisture-Based Irrigation for Orchards. Pennsylvania Fruit News.
He, L., D. Choi, J. Schupp and T. Baugher. 2020. A sensor-based irrigation test system for apple orchards (Final report). PA Fruit News 100(1):24-26.
He, L., J. Schupp, D. Choi and D. Weber. 2020. Branch and fruit accessibility for mechanical operations with various tree canopies (Year 1 report). PA Fruit News 100(1):22-24.
Huang, M., He, L., Jiang, X., Choi, D., & Pecchia, J. (2020). Hand-picking Dynamic Analysis for Robotic Agaricus Mushroom Harvesting. Paper No. 2000415. 2020 ASABE Annual International Meeting.
Jarvinen, T., Choi, D., Heinemann, P., & Baugher, T. A. (2019). Tree trunk position estimation for accurate fruit counts in apple yield mapping. 2019 ASABE Annual International Meeting, Paper No. 1900918, July 7 – July 10, 2019. (pp. 1-7).
Jiang, X., He, L., & Tong, J. (2020). Investigation of Soil Wetting Pattern in Drip Irrigation using LoraWAN Technology. Paper No. 2000419. 2020 ASABE Annual International Meeting.
Lee, C.-H., Choi, D., Pecchia, J., He, L., & Heinemann, P. (2019). Development of A Mushroom Harvesting Assistance System using Computer Vision. 2019 ASABE Annual International Meeting, Paper No. 190050, July 7 – July 10, 2019. (pp. 1-5).
Mahmud, M. S., & He, L. (2020). Measuring Tree Canopy Density Using A Lidar-Guided System for Precision Spraying. Paper No. 2000554. 2020 ASABE Annual International Meeting.
Mirbod, O., Choi, D., Heinemann, P., & Marini, R. (2020). Towards image-based measurement of accurate apple size and yield using stereo vision cameras. 2020 ASABE Annual International Meeting, Paper No. 2001115, July 12- 15, 2020. (pp. 1-6).
Schupp, J., H. E. Winzeler and M. Schupp. 2020. Blossom Thinning Pennsylvania Apples Using the Pollen Tube Growth Model. PA Fruit News 100 (1):46-47.
Schupp, J., H. E. Winzeler and M. Schupp. 2020. Development of a High Density, Highly Mechanized, Pedestrian Peach System. PA Fruit News 100 (1): 43-44.
Schupp, J., L. He, H. E. Winzeler, M. Schupp and M. Clowney. 2020. Improving orchard performance with terrain analysis using drone technology and Geographical Information Systems. PA Fruit News 100 (1):45-46.
Shi, X., Choi, D., Heinemann, P., Lynch, J. P., & Hanlon, M. (2019). RootRobot: A Field-based Platform for Maize Root System Architecture Phenotyping. 2019 ASABE Annual International Meeting, Paper No.1900806, July 7 – July 10, 2019. (pp. 1-7).
Zahid, A., He, L., Choi, D., Schupp, J., & Heinemann, P. (2020). Collision free Path Planning of a Robotic Manipulator for Pruning Apple Trees. Paper No. 2000439. 2020 ASABE Annual International Meeting.
Zhang, H., He, L., Di Gioia, F., Choi, D., & Heinemann, P. (2020). Internet of Things (IoT)-based Precision Irrigation with LoRaWAN Technology Applied to High Tunnel Vegetable Production. Paper No. 2000762. 2020 ASABE Annual International Meeting.

Patent
Lyons, D.J. & Heinemann, P.H. 2019. US patent No. 10,448,578 B2: Selective Automated Blossom Thinning. October 22, 2019.

Extension Presentation
Schupp, J. 2020. Blossom thinning Golden Delicious using lime sulfur and the pollen tube growth model. Mid-Atlantic Fruit and Vegetable Conference, Hershey, PA. January 28, 2020.
Schupp, J., 2020. Research on fruit thinning. Ohio Produce Network, Columbus, OH. 23 Jan 2020.
Schupp, J., 2020. Research on orchard systems/ pruning. Ohio Produce Network, Columbus, OH. 23 Jan 2020
Schupp, J., and D. Weber. 2020. Demonstrations of the REDpulse pneumatic defoliator for increasing red coloration of apples. Biglerville, PA. 19 and 20 August 2020.
Schupp, J., He, L., H. E. Winzeler, M. Schupp and M. Clowney. 2020. Improving orchard performance with terrain analysis using drone technology and Geographical Information Systems (GIS). Mid-Atlantic Fruit and Vegetable Conference, Hershey, PA. January 28-30, 2020 (poster).
Schupp, J., M. Schupp and H. E. Winzeler. 2020. High density mechanized pedestrian peach system. Mid-Atlantic Fruit and Vegetable Conference, Hershey, PA. January 28-30, 2020 (poster).

Award
Crassweller, R., K. Peter, G. Krawczyk, J. Schupp, T. Ford, M. Brittingham, J. Johnson, L. LaBorde, J. Harper, K., Kephart, R. Pifer, K. Kelley, L. He, P. Heinemann, D. Biddinger, M. Lopez-Uribe, R. Marini, T. Baugher, D. Weber, L. Kime, E. Crow, E. Weaver, B. Lehman. 2020. 2020-21 Penn State Tree Fruit Production Guide. The Outstanding Book Publication from the American Society for Horticultural Science.

Washington
Journal Articles
Bahlol, H., A. Chandel, G.-A. Hoheisel and L. R. Khot. 2020. Developing understanding on orchard sprayer air-assists and volume output patterns using smart spray analytical system. Crop Protection, 127: 104977. https://doi.org/10.1016/j.cropro.2019.104977
Bahlol, H. Y., A. Chandel, G.-A. Hoheisel, and L. R. Khot. 2020. Smart spray analytical system for orchard sprayer calibration: a-proof-of-concept and preliminary results. Transactions of the ASABE, 62(6): 29-35. https://doi.org/10.13031/trans.13196 .
Davidson, J., S. Bhusal, C. Mo, M. Karkee, and Q. Zhang. 2020. Robotic Manipulation for Specialty Crop Harvesting: A Review of Manipulator and End-Effector Technologies. Global Journal of Agriculture and Allied Sciences, 2(1), 25-41. https://doi.org/10.35251/gjaas.2020.004.
Fu, H., M. Karkee, L. He, J. Duan, J. Li, and Q. Zhang, 2020. Bruise patterns of fresh market apples caused by fruit-to-fruit impact. Agronomy, 10(1), Article 59. (http://doi.org/10.3390/agronomy 10010059).
Fu, L., Y. Majeed, X. Zhang, M. Karkee and Q. Zhang, 2020. Faster R-CNN-based apple detection in dense-foliage fruiting-wall trees using RGB and depth features for robotic harvesting. Biosystems Engineering, 197: 245-256. http://doi.org/10.1016/j.biosystemseng.2020.07.007.
Gao, F., L. Fu, X. Zhang, Y. Majeed, R. Li, M. Karkee and Q. Zhang. 2020. Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN. Computers and Electronics in Agriculture, 176, 105634. http://doi.org/10.1016/j.compag.2020.105634.
Gao, Z., R. A. Naidu, Q. Zhang, and L. R. Khot. 2020. Early detection of grapevine leafroll disease in a red-berried wine grape cultivar using hyperspectral imaging. Computers and Electronics in Agriculture, 179, 105807 https://doi.org/10.1016/j.compag.2020.105807
Khot, L. R.*. 2020. Transitioning from precision to decision horticulture: technology landscape. ISHS Acta Horticulturae 1279, XXX International Horticultural Congress IHC2018: VII Conference on Landscape and Urban Horticulture, IV Conference on Turfgrass Management and Science for Sports Fields and II Symposium on Mechanization, Precision Horticulture, and Robotics, 43:1, https://doi.org/10.17660/ActaHortic.2020.1279.29
Long, Y., M. Li, D. Gao, Z. Zhang, H. Sun, and Q. Zhang, 2020. Chlorophyll content detection based on image segmentation by plant spectroscopy. Spectroscopy and Spectral Analysis, 40(7): 2253-2258. https://doi.org/10.3964/j.issn. 1000-0593(2020)07-2253-06.
Majeed, Y., J. Zhang, X. Zhang, L. Fu, M. Karkee, Q. Zhang, and M.D. Whiting, 2020. Deep learning based segmentation for automated training of apple trees on trellis wires. Computers and Electronics in Agriculture, 170. Article 105277. (https://doi.org/10.1016/J.COMPAG.2020.105277).
Majeed, Y., M. Karkee, Q. Zhang, L. Fu, and M.D. Whiting, 2020. Determining grapevine cordon shape for automated green shoot thinning using semantic segmentation-based deep learning networks. Computers and Electronics in Agriculture, 171. Article 105308. (https://doi.org/10.1016/J.COMPAG.2020.105308).
Majeed, Y., M. Karkee, and Q. Zhang, 2020. Estimating the trajectories of vine cordons in full foliage canopies for automated green shoot thinning in vineyards. Computers and Electronics in Agriculture, 176. Article 105671. (https://doi.org/10.1016/j.compag.2020.105671).
Zhang, J., M. Karkee, Q. Zhang, X. Zhang, Y. Majeed, L. FU, and S. Wang, 2020. Multi-class object detection using faster R-CNN and estimation of shaking locations for automated shake-and-catch apple harvesting. Computers and Electronics in Agriculture, 173. Article 105384. (doi: 10.1016/J.COMPAG.2020.105384).
Zhang, X., L. He, J. Zhang, M.D. Whiting, M. Karkee and Q. Zhang, 2020. Determination of key canopy parameters for mass mechanical apple harvesting using supervised machine learning and principal component analysis (PCA). Biosystems Engineering, 193: 247-263. (doi: 10.1016/j.biosystemseng.2020.03.006).
Zhang, X., He, L., Karkee, M., Whiting, M. D., and Zhang, Q. 2020. Field Evaluation of Targeted Shake-and-Catch Harvesting Technologies for Fresh Market Apple. Transactions of the ASABE, 2020. doi: 10.13031/trans.13779.
Ranjan, R., L. R. Khot, R. Troy Peters, M. R. Salazar-Gutierrez and G. Shi. 2020. In-field crop physiology sensing aided real-time apple fruit surface temperature monitoring for sunburn prediction. Computers and Electronics in Agriculture, 157: 105558. https://doi.org/10.1016/j.compag.2020.105558.
Santiago, W. E., N. J. Leite, B. J. Teruel, M. Karkee, and C. A.M. Azania. 2019. Evaluation of bag-of-features (BoF) technique for weed management in sugarcane production. Australian Journal Crop of Science, 13(11):1819-1825.
Sinha, R., R. Ranjan, H. Y. Bahlol, L. R. Khot, G.–A. Hoheisel and M. Grieshop. 2020. Development and performance evaluation of a pneumatic spray delivery based solid set canopy delivery system for high-density apple orchard. Transactions of the ASABE, 62(6): 37-48. https://doi.org/10.13031/trans.13411
Sinha, R., R. Ranjan, G. Shi, G.-A. Hoheisel, M. Grieshop and L. R. Khot. 2020. Solid set canopy delivery system for efficient agrochemical delivery in modern architecture apple and grapevine canopies. Acta Horticulturae 1269: II International Symposium on Innovative Plant Protection in Horticulture, 277-286. https://doi.org/10.17660/ActaHortic.2020.1269.38
Wang, B., R. Ranjan, L. R. Khot and R. Troy Peters. 2020. Smartphone application‐enabled apple fruit surface temperature monitoring tool for in‐field and real‐time sunburn susceptibility prediction. Sensors, 20, 608. https://doi:10.3390/s20030608

Thesis/Dissertations
Gao, Zongmei (2020). Spectral imaging based non-contact detection of biotic and abiotic stress in berry crops. Ph.D. Dissertation. April 2020, Washington State University.
Majeed, Yaqoob (2020). Machine Vision System for the Automated Green Shoot Thinning in Vineyards. Ph.D. Dissertation. April 2020, Washington State University.
Zhang, Xin (2020). Study of Canopy-Machine Interaction in Mass Mechanical Harvest of Fresh Market Apples. Ph.D. Dissertation. March 2020, Washington State University.

Conference Paper and Presentations
Anura P. Rathnayake, G. A. Hoheisel and L. R. Khot. 2020. A PWM based retrofit controller for optimized spray applications in perennial specialty crops. Paper No. 2001023, ASABE 2020 Virtual Annual International Meeting, July 12-15, 2020 (Oral Presentation).
Bhattarai, U. Automated Blossom Detection in Apple Trees using Deep Learning. Twenty First IFAC World Congress, Berlin, Germany, July 12-17, 2020 (Virtual).
Bhusal, S., Bhattarai, U., and Karkee, M. 2019. Improving Pest Bird Detection in a Vineyard Environment Using Super-Resolution and Deep Learning. IFAC-PapersOnLine, 52(30), 18-23.
Fu, H., J. Duan, M. Karkee, L. He, H. Xia, J. Li and Q. Zhang. 2019. Effect of shaking amplitude and capturing height on mechanical harvesting of fresh market apples. IFAC-PapersOnLine, 52(30), 306-311.
Majeed, Y., Karkee, M., Zhang, Q. Fu, L. and Whiting, M.D. 2019. A study on the detection of visible parts of cordons using deep learning networks for the automated green shoot thinning in vineyards. IFAC-PapersOnLine, 52(30), pp.82-86.
Ranjan, R., R. Sinha, L. R. Khot, G. A. Hoheisel, M. Grieshop and M. Ledebhur. 2020. Effect of emitter modifications on spraying attributes of a pneumatic spray delivery based solid set canopy delivery system configured for high-density apple orchard. Paper No. 2000164, ASABE 2020 Virtual Annual International Meeting, July 12-15, 2020 (Oral Presentation).
Ranjan, R., L. R. Khot, R. T. Peters, and M. R. Salazar-Gutierrez. 2020. Field evaluation of visible-infrared and microclimate sensing aided crop physiology sensing system for apple sunburn management. Paper No. 2000165, ASABE 2020 Virtual Annual International Meeting, July 12-15, 2020 (Oral Presentation).
You, A., F. Sukkar, R. Fitch, M. Karkee, and J.R. Davidson. 2020. An efficient planning and control framework for pruning fruit trees. IEEE International Conference on Robotics and Automation. May 31 – Aug 31, 2020 (Virtual).
Zhang, Q. 2019. Digital Agriculture: Opportunities and Challenges, A View of Automation. WSU Digital Agriculture Summit, December 4-6, 2020 (Invited Keynote Speech).
Zhang, X., Fu, L., Karkee, M., Whiting, M. D., & Zhang, Q. 2019. Canopy segmentation using ResNet for mechanical harvesting of apples. IFAC-PapersOnLine, 52 (30), 306-311.

Other Products
Khot, L., R. Sinha, G.-A. Hoheisel, and Matthew Grieshop. 2019. Solid set canopy delivery system for WA vineyards. Washington State University - Viticulture and Enology Extension News, Spring 2019. http://wine.wsu.edu/extension/viticulture-enology-news-veen/.

West Virginia
Kirkpatrick, D., Rice, K., Ibrahim, A. Fleischer, S., Tooker, J., Tabb, A., Medeiros, H., Morrison, W., Leskey, T. 2020. The Influence of Marking Methods on Mobility, Survivorship, and Field Recovery of Halyomorpha halys (Hemiptera: Pentatomidae) Adults and Nymphs. Environmental Entomology, nvaa095, https://doi.org/10.1093/ee/nvaa095 .
Zhu, J., Teolis, S., Biassou, N., Tabb, A., Jabin, P., and Lavi, O. 2020. Tracking the adaptation and compensation processes of patients brain arterial network to an evolving glioblastoma.IEEE Transactions on Pattern Analysis & Machine Intelligence (accepted, currently preprint).
Feldmann, M. J., Hardigan, M. A., Famula, R. A., López, C. M., Tabb, A., Cole, G. S., Knapp, S. J. 2020. Multi-Dimensional Machine Learning Approaches for Fruit Shape Phenotyping in Strawberry. GigaScience. https://doi.org/10.1093/gigascience/giaa030

Code releases
Tabb, A. “Data and Code from: Using cameras for precise measurement of two-dimensional plant features: CASS.” Zenodo, 2020. http://doi.org/10.5281/zenodo.3677473
Tabb, A. and Feldmann, M. J. "Data and Code from: Calibration of Asynchronous Camera Networks: CALICO," (Version v.1) [Data set]. Zenodo, 2019. http://doi.org/10.5281/zenodo.3520866