Brief Summary of Minutes of Annual Meeting

Meeting Summary:

8:00 AM - Meeting called to order (Dana Choi)

8:00 AM – 8:15 AM - Attendee introduction

8:15 AM – 8:45 AM – Ganesh Bora – National Program Leader, NIFA-USDA

• History of legislation for USDA
• Review of different acts related to multistate
• USDA fiscal priorities
• Formation of multi-state projects
• Some pertinent competitive grant program
• New investigator and seed grants (USDA NIFA-AFRI)
• Priorities to be addressed (CAFF)
• Steven Thompson (USDA NIFA) introduced himself and his work in USDA.

8:45 AM – 10:00 AM – Business meeting

• Summary of 2021 meeting/reports approved with a minor edit by participants
• 2023 meeting location and time

Cornel, in June 2023, Yu Jiang (Cornell University) will host

• New secretary nomination/election

Hao Gun (University of Tennessee)

• Project renewal (proposal writing team organization)

Submit the proposal by Jan 15, 2023

Or termination by Sep

Suggestions for changing the title of the group or adding the number of objectives

Stavros Vougioukas (UC Davis) leads the proposal

Zahid Aslan (Texas A&M Univ.)

Joe Dvorak (Univ. of Kentucky)

Hao Gan (Univ. Tennessee)

Irwin Donis Gonzalez (UC Davis)

• Announcements

FIRA, Fresno, CA, Oct 18-20, 2022, 3 Day conference organizes by the international robotic association.

https://www.ifac-control.org/conferences/sensing-control-and-automation-technologies-for-agriculture-7th-agricontrol-2022sensing-control-and-automation-technologies-for-agriculture-7th-agricontrol-2022tm

Agricontrol Sensing, Control and Automation Technologies for Agriculture - 6th AGRICONTROL

CIGR congress http://cigr2022.org/

ASABE robotic competition, request for judges, start from Sunday (July 17, 2022) and continue to Tuesday (July 19, 2022)

Cornel institute of digital agriculture (annual event and symposium) invite researchers to present at this event

http://www.hackag.tech/

S1090 Multistate project (2021-2026) AI in agroecosystems: big data and smart technology-driven sustainable production. 2022, Annual meeting Gainesville, FL, Aug 4

• Opportunities for collaboration
• Annual Report

Each institute sends one report by July 24 deadline. The one-page report should include accomplishment and impact (the most important part)

10:00 AM – 10:10 AM - Break

10:10 AM – 1:10 PM - Institute report presentations (Alphabetical order)

Arizona

• The novel, energy efficient band-steam applicator for controlling soilborne pests developed in the project was further evaluated with iceberg and romaine lettuce in field with a known history of Fusarium wilt of lettuce. Trial results showed that band-steam reduced fusarium wilt disease incidence by ~50%, increased head weight by > 20% and improved yield by > 300% and > 90% in iceberg and romaine lettuce respectively as compared to the untreated control. Additionally, use of band steam improved weed control by ~80% and reduced hand weeding labor requirements by > 50%. Machine work rate (0.05 ac/hr) and energy costs ($891/ac) were considered acceptable if labor reductions and yield increases can be realized.

California

• An industry assessment study was conducted to quantify the performance of the current quality and food safety assessment system used in the Californian dehydrator onion and garlic industries. The study results show that the current system cannot reliably produce a statistically random sample due to several factors, including systematic bias created by 1) the design of the current mechanical sampling system and 2) the use of subjective decision-making processes by non-third-party individuals who may be perceived to have a conflict of interest in the assessment results. A design proposal was developed that would create a semi-automated sampling system capable of collecting a statistically random sample by eliminating sources of bias in the process as well as by eliminating the use of subjective human-controlled decisions. Ongoing research is being conducted to determine the economic feasibility of the proposed system as well as a timeline for potential implementation.
• An automated high-throughput phenotyping (HTPP) system with a real-time, proximal plant architecture sensor with integrated GPS was created. The research was conducted that developed methods to measure architectural plant phenotypes (height, width, and volume) of different genotypes in the Solanaceae family utilizing 3D model data from a time-of-flight camera over the course of an entire growing season. The data collected and processed by the system using automated methods created a more comprehensive picture of the growth of a genotype over the course of a season with many more sample points, higher temporal resolution, and an entire 3D model as compared to traditional manual methods.
• An inline moisture estimation system was built to measure the moisture content (MCwb) of green coffee using a time-domain reflectometry (TDR) probe. Model validation yielded a high correlation (R2 = 0.93) with accuracy of up to 91%. The TDR inline green coffee moisture estimation system has the potential to be applied in real-time, industrial-scale operations.
• A hybrid (virtual and in-person) applied extension workshop was organized on the topic of emerging technologies addressing grand challenges in the produce industry. The workshop brought together academics and industry representatives to discuss challenges facing the produce distribution industry. Topics included: Automation in agriculture, mechanical and robotic harvesting, postharvest sensing, and controlling of quality.
• While there have been discussions about how new technologies can increase output, optimize inputs, and save the environment, there hasn't been much attention to how safe these technologies are for farmers. A comprehensive study in collaboration with the National Institute of Safety and Health assesses the current situation of new technology safety in Agriculture. In addition, a workshop titled "Safety For Emerging Robotics and Autonomous aGriculture (SAFER AG) will be held November 9-10, 2022, in Urbana, Illinois.
• A fruit-harvesting robot is being developed that comprises an array of custom-made linear robot arms. A ROS-based simulator was developed and tested for the robot, and a Mixed Integer Programming model was formulated to minimize the overall picking time, also known as the makespan. This new formulation computes the optimal harvester travel speed and the optimal overall arms-to-fruits schedule that maximizes the fruit picking throughput for a given minimum picking efficiency.
• An automated Internet of Things (IoT) double ring infiltrometer (DRI) was developed and validated with the aim to facilitate soil infiltration mapping for precision agriculture and to build a soil infiltration inventory that could be used to continuously improve existing soil database.

Florida

• A method for biomarker reflectance signature specification for disease detection and classification was developed
• A technique was developed for sugarcane yield prediction and genotype selection using UAV-based hyperspectral imaging and machine learning
• A method was developed for determining leaf nutrient concentrations in citrus trees using UAV imagery and machine learning
• A yield prediction model was developed for citrus trees utilizing aerial and ground sensing and machine learning
• A method was developed for the diagnosis of grape leaf diseases using automatic K-means clustering and machine learning
• A smart tree crop sprayer was developed utilizing sensor fusion and artificial intelligence

Michigan

• Three formal student senior design course projects focused on small- to medium-scale chestnut harvest automation were the primary efforts for Michigan under this multi-state project. The first project followed taking the common and functional hand-harvest tool of a “Nut Wizard” and designing an approach of coupling multiple of such together into a fully mechanical system that could be pushed or pulled by a small tractor or ATV to collect and deposit into an on-board containment bin. A prototype was built and tested.  The second and third approaches were addressing the development of a pick-up concept and component for chestnuts on the ground (as is necessary due to maturation) if given a higher-technology small electric unmanned ground vehicle (UGV) platform system to move about the orchard having a vision system to locate the centroid of the chestnut within +/- 10 mm and move to the appropriate location.  Thus, the task was focused on only the pick-up and on-boarding of the chestnut given vision and robotic vehicle technology already quite well developed.  One of the concepts pursued the more traditional multi-jointed robotic type arm and a unique gripper development with the latter aspect being the most advancing and applicable. The other concept worked toward an automated, and less complex, approach of coming down onto the nut in a single dimension linear fashion/stroke and forcing the chestnut up into a tube and collecting the chestnuts until automatically dumping a set of multiple nuts after the tube fills.  This last concept required engineering a static flexible end effector with similarity to a “shag bag” for collecting golf balls (however, chestnuts greatly vary in size and shape!). All concepts demonstrated approximately 80% harvest pick up efficiency depending on ground cover type/status.
• Tangential indirect effort continues to advance, with technology and produce handling collaborators, to commercial-level prototyping, and hopefully beyond, of highly successful previous work under this project of non-destructive sorting of internal defects/quality using Computed Tomography (CT) and image processing. Examples include commodities with hard coatings such as chestnuts, and undesirable tissue characteristics such as fiber in whole carrots or asparagus.
• Additionally, work was finished on one book chapter related to concepts behind mechanical harvesting of fruit trees and another book chapter is in final review on image-based automated insect identification toward the goal of automated scouting.
• The current Michigan representative to this Multi-State Project is retiring and a new representative with likely a somewhat different specific focus will come on board in the coming year.

Mississippi

• Improved fruit detectors: Various fruit detection models were improved architecturally for better detection accuracy and faster speed, including canopy-attention-YOLOv4 and Res-Dense-focal-DeepLabv3+ on apples or wine grapes in field conditions. Accurate machine vision system will be able to serve as a solid foundation for efficient and reliable robotic harvesting and canopy management.
• Tested robotic end-effector: A machine vision enabled robotic end-effector was designed and tested indoor for automatic cotton harvesting. The end-effector was able to locate and reach to the cotton tissue automatically. It also can detach the cotton from the cotton ball completely without cutting off the cotton tissue for better cotton quality.

Oklahoma

• A line-scan X-ray camera system was designed and developed to automate the inspection of peanut pods. In X-ray images, healthy peanut pods filled with seed are denser than infected pods filled with teliospores of Thecaphora frezzii. We developed a control system and a computer-based user interface to allow easy operations of the X-ray imaging system. A previously developed image processing and analysis algorithm was modified to fit for the developed line-scan camera.
• The system will improve the efficiency of disease rating process during peanut breeding and new variety development for peanut smut resistance. Current hand-opening peanut pods method during the disease rating will be replaced with the automated, multipods detection system. This new technology is hoping to greatly improve the speed and accuracy of the disease rating process and allow automatic data storage and backup.

Oregon

• The Economic Model to Compare Crop Rotations is an interactive tool written in Excel^© that allows agricultural producers to compare the financial impacts of changing to an alternative crop rotation. The model will enable growers to develop two alternative rotations compared to their current cropping system based on whole-farm net returns, quantities of production inputs, and crops grown. Producers can select from 21 crops and two fallow options provided in a drop-down menu. These crops are typically grown in the dryland production systems in the inland Pacific Northwest. Also provided is one livestock budget for rotations that may include livestock grazing. This model is unique in that when a crop is added, replaced, or acres increased or decreased, the costs of producing other crops in that rotation also change. Not only are budgets dynamic, but each of the three rotations is independent of the other. As acres of crops are modified, the budget information only within that specified rotation changes. The foundation of this model is enterprise budgets, which include gross income, out-of-pocket cash costs, and fixed costs, broken into cash fixed and fixed non-cash costs. Producers can modify inputs, such as crop yields and prices, seeding rates, chemicals applied, fertilizer requirements, custom hire operations, the number of times a field operation occurs during a production season, machinery costs, the width of implements, speed of operations, and field efficiencies. The results show the total farm net returns for each rotation, the number of inputs used, and the value difference and percentage change from the grower's current rotation. The output also includes the total amounts of crop seeds, fertilizers, pesticides, machinery labor, fuel use, repairs and maintenance, and production units. This model allows producers to assess the financial and environmental tradeoffs in dryland farming. Producers can use this model to make cropping decisions based on 1) total net returns, 2) reducing fertilizer and chemical inputs, or 3) a balanced approach based on their financial and environmental goals. The Economic Model to Compare Crop Rotations was designed as an easy-to-use tool. However, instructional videos are included to assist producers with limited understanding of Excel or knowledge of financial data.

Pennsylvania

• Two green fruit thinning end-effectors were developed and tested in the orchard environment. The test results showed that the end-effectors were able to singulate the targeted fruits with high success.
• A deep learning based algorithm was developed to segment green fruits and fruit stems, then the orientation of the fruits were identified to provide guidance for the robotic green fruit system to remove fruits. A path planning algorithm was also developed with a six-degree-freedom robotic arm to engage targeted green fruits.
• A series of early apple buds images were acquired with two image acquisition systems, and a YOLOv4 model was developed to detect the buds in the tree canopies.
• A Cartesian robotic thinning system was developed to apply targeted blossom thinning, including a Cartesian robot, a ZED camera, and a solenoid valve controlled nozzle. Field tests indicated that the robotic thinning system saved more than 50% chemical and achieve relatively better thinning performance in the narrow tree canopy trees.
• A computational fluid dynamic model (CFD) for heat transfer in porous canopies was developed and validated. The influences of heater output, heating duration, and heating angles were simulated, and validated in the field condition with two propane heaters. Developed a ground vehicle platform that can be operated autonomously using a RF-based transceiver and UDP protocol, built and tested a UAV that can capture and send spatiotemporal maps in real-time using a heuristic approach.
• Continued the field tests with the developed precision irrigation and precision spraying system in the apple and peach orchards for various purposes.

Tennessee

• A mobile robotic farm (Farmbot) was built in preparation of simulating drone-based autonomous pollination operation. A mobile raised bed was constructed as the supporting infrastructure for both a robotic gantry system, bedding materials and crops. Tomato plants have been grown in the bed since March 2021. The robotic farm has been controlled through custom-developed Python code. Images has been taken which will be used to develop computer vision algorithms for flower identification and localization.
• A mini-IoT system including five independent units were developed for real-time environmental sensing. The system consists of a raspberry pi-based central data transmission unit, and four Arduino-based end devices. The end devices collect soil moisture, CO2, temperature and relative humidity data for display on a cloud-based dashboard. The system was developed with the goal of being ultra-low power. The end devices are powered by four AA batteries and can work continuously for roughly 4 - 6 months.

Texas

• A deep learning model was developed to detect the bacterial wilt disease in greenhouse tomato crops. Over-amplification of the contrast due to uneven illumination is a major concern for color image-based disease identification systems. We used image enhancement algorithms to adjust the light and contrast in the images to improve the model performance. The developed model successfully detected the disease symptoms and severity levels on leaves and stems with superior accuracy, precision, and recall.

Washington

• A vision-based flower cluster detection system has been developed and tested in apple and cherry orchards. This system reached an 86% accuracy on cluster location detection and an 84% accuracy on flower density estimation.  This system could be used on both fruit tree blossom thinning robot and pollination robot underdevelopment at WSU.
• Continue improve a machine-vision (using a tracking camera) and robotic system for pruning apple trees, which has been tested in the laboratory environment and has started the tuning and testing in commercial apple orchards.
• Continue working with a commercial partner to convert and integrate the outcomes from our robotic apple harvesting research to a product prototype to make it usable to apple growers in Washington, PNW of US, and beyond.
• Improved the design of the automated green shoot thinning machine and tested a research prototype in commercial vineyards. The project has moved into the third phase of collaborating with a local manufacturer in developing a product prototype. The first commercial prototype is expected to be fabricated for field test in 2023 growing season.
• Designed an information management platform for a DEMO farm of smart agriculture. The infostructure of this demo farm will consist of a field network of sensors, a (or more) mobile equipment connected to the field network, an in-house control center, and a data communication link between field and farm office. The construction of this platform is under way.
• Working on transmitting a developed technology of synthesized Cellulose NanoCrystals (CNC)-based dispersion for insulating tree fruit buds thus protecting them from cold damage. A licensing agreement has been reached between WSU and an interested commercial partner.
• Improved and conducted field testing of an Internet-of-Things (IoT) enabled Crop Physiology Sensing System (CPSS 3.0) for apple fruit surface temperature monitoring and real-time actuation of modified evaporative cooling system for heat stress management in fresh market apple cultivars (cv Honeycrisp and Cosmic Crisp). CPSS 3.0 has been refined to extract other canopy/fruit quality attributes to aid grower decision support.
• Developed aerial imagery (multispectral and thermal) based spectral sensing integrated energy balance modeling approach to estimate evapotranspiration (ET) at high spatial resolution (10 cm/pixel). Validate the approach for ET and leaf level transpiration (aka crop water use) estimation in grapevine, apple, and field crops (mint, alfalfa, potato).
• Developed and validated tree-row-volume and unit-canopy-ration driven base spray rate estimation approaches for an intelligent orchard sprayer to perform efficient spray applications in tall spindle apple crop canopies.

Arizona

Book Chapter

Fennimore, S.A. & Siemens, M.C. 2022. Mechanized weed management in vegetable crops. In Encyclopedia of Smart Agricultural Technologies, ed. Qin Zhang. (accepted)

Outreach Publications

Siemens, M.C. 2022. New Weeding Technologies for the 2022 Growing Season – Article II. 1 July 13. Vol. 14, Issue 14. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. New Weeding Technologies for the 2022 Growing Season. 1 June 29. Vol. 13, Issue 13. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. 2022 International Robotic Ag Technologies. 1 June. Vol. 13, Issue 11. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. 2022 Automated Technology Field Day – Salinas, CA : UC Cooperative Extension. 18 May. Vol. 13, Issue 10. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. Control of Palmer Amaranth with Finger Weeders Shows Good Promise in Texas A&M Cotton Studies. 4 May. Vol. 13, Issue 9. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. Specialty Crop Agricultural Robotics and Technology Forum. 20 April. Vol. 13, Issue 8. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. Finger Weeder Removing Large Palmer Amaranth Plant in Cotton Video. 6 April. Vol. 13, Issue 7. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. 2nd Generation Prototype Band-Steam Machine – Initial Testing. 22 March. Vol. 13, Issue 6. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. Pre-Plant Injection of Steam for Controlling Soilborne Pathogens and In-Row Weeds: Summary of Trial Results. 9 March. Vol. 13, Issue 5. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. “Innovations in Weed Control Technologies” Session and Field Demo at 2022 Southwest Ag Summit. 23 February. Vol. 13, Issue 4. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. Band-Steam Applicator Field Demo and Trial Results – 2022 Southwest Ag Summit. 9 February. Vol. 13, Issue 3. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. Use of Steam for Post Emergent Weed Control. 26 January. Vol. 13, Issue 2. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2022. Control of Fusarium Wilt with Band-Steam – Trials Show Mixed Results. 12 January. Vol. 13, Issue 1. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2021. Automated Thinning Machine Performance  – Vigilance Important. 15 December. Vol. 12, Issue 25. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2021. Camera Guided Shift Hitch and Finger Weeders. 1 December. Vol. 12, Issue 24. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2021. Commercial Autonomous Ag Field Robots - Update. 17 November. Vol. 12, Issue 23. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2021. Automated In-Row Weeders Impress in Weedy Fields. 3 November. Vol. 12, Issue 22. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Siemens, M.C. 2021. 2nd Automated Weeding Technologies Field Demo – Update. 06 October. Vol. 12, Issue 20. Tucson, Ariz.: University of Arizona, Yuma Agricultural Center.

Invited Presentations

Siemens, M.C. 2022. “New” Technologies and Innovations for Improved Weed Control. New Mexico Chile Conference, February 1.

California

Perez-Ruiz, M., Slaughter, DC. 2021. Development of a precision 3-row synchronized transplanter. Biosystems Engineering. Vol 206: 67-78.

Anokye-Bempah, L, Phetpan, K, Slaughter, D.C. & Donis-González, I.R. 2022. Design, calibration, and validation of a green coffee inline moisture content estimation system using time-domain reflectometry (TDR). Submitted for publication; Journal of Food Engineering.

Peng, C., Vougioukas, S., Slaughter, D., Fei, Z., Arikapudi, R. (2022) A strawberry harvest-aiding system with crop-transport corobots: Design, development, and field evaluation. Journal of Field Robotics.

Chou, H-Y., Khorsandi, F., Vougioukas, S.G., Fathallah, F. (2022). Developing and Evaluating an Autonomous Agricultural All-Terrain Vehicle for Field Experimental Rollover Simulations. Computers and Electronics in Agriculture (194) 106735.

Avigal, Y., Wong, W., Presten, M., Theis, M., Aeron, S., Deza, A., Sharma, S., Parikh, R., Oehme, S., Carpin, S., Viers, J., Vougioukas, S., Goldberg, K. (2022). Simulating Polyculture Farming to Learn Automation Policies for Plant Diversity and Precision Irrigation. IEEE Transactions on Automation Science and Engineering. 19(3):1352-1364.

Fei, Z., Vougioukas, S.G. (2022). Row-sensing Templates: A Generic 3D Sensor-based Approach to Robot Localization with Respect to Orchard Row Centerlines. Journal of Field Robotics, 1-27.

1. Abdelmoneim, A. Daccache, R. Khadra, M. Bhanot, G. Dragonetti (2021). Internet of Things (IoT) for double ring infiltrometer automation. Computers and Electronics in Agriculture, Volume 188, September 2021, 106324

Florida

Patel, A., W. S. Lee, N. A. Peres, and C. W. Fraisse. 2021. Strawberry plant wetness detection using computer vision and deep learning. Smart Agricultural Technology 1, 2021, 100013, ISSN 2772-3755, https://doi.org/10.1016/j.atech.2021.100013

Yun, C., H.-J. Kim, C.-W. Jeon, M. Gang, W. S. Lee, and J. G. Han. 2021. Stereovision-based ridge-furrow detection and tracking for auto-guided cultivator. Computers and Electronics in Agriculture 191, 2021, 106490, ISSN 0168-1699, https://doi.org/10.1016/j.compag.2021.106490.

Puranik, P., W. S. Lee, N. Peres, F. Wu, A. Abd-Elrahman, and S. Agehara. 2021. Strawberry flower and fruit detection using deep learning for developing yield prediction models. In the Proceedings of the 13th European Conference on Precision Agriculture (ECPA), July 19-22, 2021, Budapest, Hungary.

Zhou, X., W. S. Lee, Y. Ampatzidis, Y. Chen, N. Peres, and C. Fraisse. 2021. Strawberry maturity classification from UAV and near-ground imaging using deep learning. Smart Agricultural Technology 1, 2021, 100001, ISSN 2772-3755, https://doi.org/10.1016/j.atech.2021.100001.

Michigan

Guyer, D.E. Mechanical Harvesting.  In: Advanced Automation for Tree Fruit Orchards and Vineyards.  Eds: Vougioukas and Zhang.  Springer Media. (at publisher)

Guyer, D.E. Advances in Image-based Identification and Analysis of Crop Insect Pests.  In:  Advances in Monitoring of Native and Invasive Insect Crop Pests. Eds: Fountain and Pope.  Burleigh Dodds Publishing. (in final review)

Mississippi

Publications

He, L., Zhang, X., & Zahid, A. (2022). Chapter 3 – Mechanical management of modern planar fruit tree canopies. In Advanced Automation for Tree Fruit Orchards and Vineyards (Vougioukas, S. G., & Zhang, Q. ed.), Springer Book Series: Agriculture Automation and Control. (In Press)

Lu, S., Chen, W., Zhang, X., & Karkee, M. (2022). Canopy-attention-YOLOv4-based immature/mature apple fruit detection on dense-foliage tree architectures for early crop load estimation. Computers and Electronics in Agriculture, 193, 106696.

Upadhyaya, P., Karkee, M., Kashetri, S., & Zhang, X. (2022). Automated lag phase detection in wine grapes. In Proceedings of the 15^th International Conference on Precision Agriculture (unpaginated, online). Monticello, IL: International Society of Precision Agriculture.

Peng, H., Zhong, J., Liu, H., Li, J., Yao, M., & Zhang, X. (2022). ResDense-focal-DeepLabv3+ enabled litchi branch semantic segmentation for robotic harvesting. Available at SSRN.

Barnes E. M., G. Morgan, K. Hake, J. Devine, R. Kurtz, G. Ibendahl, A. Sharda, G. Rains, J. Snider, J. M. Maja, J. A. Thomasson, Y. Lu, H. Gharakhani, J. Griffin, E. Kimura, R. Hardin, T. Raper, S. Young, K. Fue, M. Pelletier, J. Wanjura, and G. Holt.  2021.  Opportunities for robotic systems and automation in cotton production.  AgriEngineering 3(2):339-362; doi.org/10.3390/agriengineering3020023.

Gharakhani, H., J. A. Thomasson, and Y. Lu.  2022.  An end-effector for robotic cotton harvesting.  Smart Agricultural Technology 2(1):1-11.

Presentations

Zhang, X. & Regmi, A. MLCAS2021 Crop yield prediction challenge. 3^rd International Workshop on Machine Learning for Cyber-Agricultural Systems, online (11/2/2021–11/3/2021) (invited talk)

Zhang, X. Study of canopy-machine interaction in mass mechanical harvest of fresh market apples. 30^th Members’ Meeting of the Club of Bologna (Agriculture mechanization vision for the future: The Club of Bologna thirty years of contribution for improve its diffusion and sustainability), Bologna, Italy (10/22/2021–10/23/2021) (invited talk)

Zhang, X., Liu, X., Lu, S., & Karkee, M. Deepsort-YOLOv3: Robust on-the-go grape bunch video tracking for yield estimation throughout the growth season. ASABE AIM, Houston, TX (7/17/2022–7/20/2022)

Chakraborty, M., Pourreza, A., Zhang, X., Jafarbiglu, H., & Shackel, K. A. Almond bloom mapping at the tree level for early yield forecasting. ASABE AIM, Houston, TX (7/17/2022–7/20/2022)

Upadhyaya, P., Zhang, X., Lu, S., & Karkee, M. Smartphone-app for crop load estimation and lag phase detection in wine grapes. 15^th International Conference on Precision Agriculture (ICPA), Minneapolis, MN (6/26/2022–6/29/2022)

Pennsylvania

Journal Publications:

Zhang, H., He, L., Di Gioia, F., Choi, D., Elia, A. and Heinemann, P., 2022. LoRaWAN based internet of things (IoT) system for precision irrigation in plasticulture fresh-market tomato. Smart Agricultural Technology, 2, p.100053.

Yuan, W., Choi, D., Bolkas, D., Heinemann, P.H. and He, L., 2022. Sensitivity examination of YOLOv4 regarding test image distortion and training dataset attribute for apple flower bud classification. International Journal of Remote Sensing, 43(8), pp.3106-3130.

Zahid, A., Mahmud, M.S., He, L., Schupp, J., Choi, D. and Heinemann, P., 2022. An Apple Tree Branch Pruning Analysis. HortTechnology, 32(2), pp.90-98.

Hussain, M., He, L., Schupp, J. and Heinemann, P., 2022. Green Fruit Removal Dynamics for Robotic Green Fruit Thinning End-Effector Development. Journal of the ASABE (in press).

Xiao, D., Pan, Y., Feng, J., Yin, J., Liu, Y. and He, L., 2022. Remote sensing detection algorithm for apple fire blight based on UAV multispectral image. Computers and Electronics in Agriculture, 199, p.107137.

Mahmud, M.S., Zahid, A., He, L., Choi, D., Krawczyk, G. and Zhu, H., 2021. LiDAR-sensed tree canopy correction in uneven terrain conditions using a sensor fusion approach for precision sprayers. Computers and Electronics in Agriculture, 191, p.106565.

Book Chapter:

He, L., Zahid, A. and Mahmud, M.S., Robotic Tree Fruit Harvesting: Status, Challenges, and Prosperities. Sensing, Data Managing, and Control Technologies for Agricultural Systems, p.299-332.

Extension Publication:

He, L., Choi, D., & Pecchia, J. (2021). "Investigation of computer vision system and robotic picking mechanism for button mushroom harvesting." Mushroom News.

He, L. (2021). Introduction of automatic irrigation systems for tree fruit orchards. Penn State Extension.

He, L., Shannon, T., & Mahmud, M. S. (2021). Unmanned aerial vehicle-based crop scouting in fruit trees. Penn State Extension.

Thesis/Dissertations:

Md Sultan Mahmud (2022). Study of core technologies in tree canopy parameter measurements for development an advanced precision sprayer. PhD Dissertation. June 2022. Pennsylvania State University.

Wenan Yuan (2022). Development of a UAV-based multi-dimensional mapping framework for precise and convenient frost management in apple orchard. PhD Dissertation. May 2022. Pennsylvania State University.

Tennessee

Oleksak, K., Wu, Y., Abella, M., Wang, Z., & Gan, H. (2021). Trajectory Optimization of Unmanned Aerial Vehicles for Wireless Communication with Ground Terminals. In AIAA Scitech 2021 Forum (p. 0709).

Daniel, A., Wu, Y., Wang, Z., & Gan, H. (2021). Trajectory Optimization of Unmanned Aerial Vehicles for Wireless Coverage under Time Constraint. In AIAA Scitech 2021 Forum (p. 1581).

Rice, C., McDonald, S., Gan, H., Lee, W.S., Chen, Y., Shi, Y., Wang, Z. (2022) Perception, path planning, and flight control for drone-enabled autonomous pollination system. Computers and Electronics in Agriculture (under review)

Texas

Publications:

Ahamed M. S., Sultan, M., Monfet, D., Rahman, M.S., Zhang, Y., Zahid, A., Aleem, M., Achour, Y., and Ahsan, T. M. A. 2022. Thermal environment controls and sustainability challenges in indoor vertical farming, Journal of Cleaner Production [Under review]

Ojo, M., and Zahid, A. 2022. Deep learning and its potential in controlled environment agriculture, Applied Intelligence [Under review]

Presentations:

Ojo, M., Zahid, A. 2022. Automatic crop disease scouting system based on deep neural networks model. In 2022 ASABE Annual International Virtual Meeting Houston TX (Presentation)

Zahid, A. 2021. Robotics and intelligent systems for controlled environment agriculture, In 3^rd Annual Controlled Environment Agriculture Conference, Dallas TX (Presentation)

Washington

Journal Articles

Bhattarai, U., & Karkee M. (2022). A Weakly Supervised Approach for Flower/Fruit Counting in Apple Orchards. Computers in Industry, 138, 103635. https://doi.org/10.1016/j.compind.2022.103635

Bhusal, S., U. Bhattarai, M. Karkee, Y. Majeed, & Q. Zhang. (2022). Automated execution of pest bird deterrence system using a programmable unmanned aerial vehicle (UAV). Computers and Electronics in Agriculture. https://doi.org/10.1016/j.compag.2022.106972.

Gao, Z., Y. Zhao, G.-A. Hoheisel, L.R. Khot, and Q. Zhang, 2021. Blueberry bud freeze damage detection using optical sensors: Identification of spectral features through hyperspectral imagery. Journal of Berry Research, https://doi.org/10.3233/JBR-211506.

Guo, J., Karkee, M., Yang, Z., Fu, H., Li, J., Jiang, Y., ... & Duan, J. (2021). Discrete element modeling and physical experiment research on the biomechanical properties of banana bunch stalk for postharvest machine development. Computers and Electronics in Agriculture, 188, 106308.

Guo, J., Karkee, M., Yang, Z., Fu, H., Li, J., Jiang, Y., ... & Duan, J. (2021). Research of simulation analysis and experimental optimization of banana de-handing device with self-adaptive profiling function. Computers and Electronics in Agriculture, 185, 106148.

Lohan, S. K., Narang, M. K., Singh, M., Singh, D., Sidhu, H. S., Singh, S., Dixit, A.K, & Karkee, M. (2021). Design and development of remote-control system for two-wheel paddy transplanter. Journal of Field Robotics. https://doi.org/10.1002/rob.22045

Lohan, S. K., Narang, M. K., Singh, M., Khadatkar, A., & Karkee, M. (2021). Actuating force required for operating various controls of walk-behind type paddy transplanter leading to development of remotely operated system. Journal of Agricultural Safety and Health, 27(2):87-103. DOI:10.13031/jash.14186

Lu, S., Chen, W., Zhang, X., & Karkee, M. (2022). Canopy-attention-YOLOv4-based immature/mature apple fruit detection on dense-foliage tree architectures for early crop load estimation. Computers and Electronics in Agriculture, 193, 106696

Rathnayake, A.P., A. Chandel, M. Schrader, G.-A. Hoheisel and L.R. Khot. 2022. Air-assisted velocity profiles and perceptive canopy interactions of commercial airblast sprayers used in Pacific Northwest perennial specialty crop production. CIGR e-journal, 24(1): 73-89.

Worasit, S., A. Marzougui, S. Sankaran, L. R. Khot, A. A. Bates, and B. Schroeder. 2021. Identification of volatile biomarkers for high-throughput sensing of soft rot and Pythium leak diseases in stored potatoes. Food Chemistry, https://doi.org/10.1016/j.foodchem.2021.130910.

Zhou, Z., G. Diverres, C. Kang, S. Thapa, M. Karkee, Q. Zhang, & M. Keller. 2022. Ground-Based Thermal Imaging for Assessing Crop Water Status in Grapevines over a Growing Season. Agronomy, 12(2), 322.

US Patents

Zhang, X., C. Mo, M.D. Whiting, and Q. Zhang, 2021. Plant-based compositions for the protection of plants from cold damage.  Publication No. US 2021/0029896 A1 (Feb 4, 2021).