The lack of mechanical harvesting technologies is a significant problem that threatens the long-term economic sustainability of the U.S. tree fruit industry. This webinar presents preliminary results from a project designed to address this problem by employing mechanization and human-machine collaboration in the production of high-quality apples for the fresh market. Dynamic analysis of hand picking has been conducted in order to determine optimal patterns for fruit removal and to facilitate the design of an underactuated, prototype end-effector. An apple identification algorithm that uses a hierarchical approach to improve the accuracy of apple detection for robotic harvesting is also discussed. Field testing of the integrated system was recently completed in a commercial apple orchard in Washington State. Some preliminary test results related to manipulation performance, vision performance, and overall system cycle time are also presented.
Joe Davidson received the B.S. degree from the United States Military Academy, West Point, N.Y., in 2004. After completing military service, he was a project manager with CH2M Hill from 2009 to 2012. He received the M.S. degree in Mechanical Engineering from Washington State University (WSU) in 2013 and is currently a Ph.D. student in the School of Mechanical and Materials Engineering at WSU. His research interests include dynamics, field robotics, numerical analysis, and additive manufacturing.
Abhisesh Silwal received the B.Eng. degree in Electronics and Communication from Tribhuvan University, Nepal, in 2009 and the M.Eng. degree in Mechatronics from the Asian Institute of Technology, Bangkok, Thailand, in 2012. He is currently working as a research assistant at Washington State University while pursuing his Ph.D. in Agricultural Automation Engineering. His current research interests include machine vision systems, field robotics, human-machine collaboration, and algorithm development.