Sponsor Agency: NSF-USDA-NRI
Karkee, M.*; Lewis, K.; Mo, Changki; Zhang, Q.
Apple harvesting is not only labor intensive but also a time critical task requiring right amount of semi‐skilled workforce at right time. The lack of mechanized harvesting system threatens the future of fresh market apple production because of the decreasing availability of farm labor force. Despite the research and development efforts over the last several decades, no commercially viable robotic harvesting systems have been available yet, primarily
because of the challenges posed by unstructured farming environment. This project investigated novel approaches to overcome the challenges in robotic apple harvesting. First, a machine vision system capable of identifying apples in a naturally clustered and occluded conditions was developed. Artificial lighting was used to provide capability for night time operation. Then, hand picking dynamics were studied to understand optimal picking patterns and forces required to detach apples. Based on this study, an under‐sensed power grasp end‐effector was designed. Both mechanical and soft‐material based hands were investigated. Vision system, robotic arm, and end‐effector were then integrated and evaluated in a commercial orchard in Prosser, WA. Results showed a huge potential for in‐field automated robotic harvesting system capable of accurately identifying, localizing, and picking fruit at relative high speed.