MECHANICAL DESIGN AND INITIAL PERFORMANCE TESTING OF AN APPLE-PICKING END-EFFECTOR

The fresh market apple industry currently relies on manual labor for all harvesting activities. The lack of mechanical harvesting technologies is a serious concern because of rising labor costs and increasingly uncertain labor availability. Researchers have been working for several decades to develop mechanical harvesters for tree fruit. The two fruit removal methods considered include mass mechanical harvesters and selective harvesting with robotics technology. Whereas mass mechanical harvesters have demonstrated unacceptable damage rates, robotic systems have been limited by insufficient speed and robustness. This paper describes the design and analysis of a novel underactuated end-effector fabricated for the robotic harvesting of tree fruit. The device has been optimized around a set of target tasks, the most critical being speed, low complexity, suitability for a highly variable field environment, and the replication of hand picking so as to minimize fruit damage. Development of the end-effector has been facilitated by a thorough study of the dynamic forces involved during the manual harvesting of apples. The end-effector produces a spherical power grasp with a normal force distribution and picking sequence replicating selected human patterns. An underactuated, tendon-driven device with compliant flexure joints has been adopted to improve system performance in the presence of position errors as well as enhance robustness to variable fruit size, shape, and orientation. The prototype end effector also uses minimal sensors and incorporates open-loop control to reduce complexity and improve picking speed. This paper presents the theoretical analysis of the end-effector kinematics and discusses the selection of key geometric parameters. Experiments have been conducted to determine the normal forces developed during grasping of the apple. Results indicate that open-loop, feedforward control can be used to produce optimal normal force patterns.