No abstract

No abstract

No abstract

HighlightsA critical torque of 0.257 N-m is required to detach 95% of apples, when the preferred twist picking mode is used.New silicone-based end effectors performed much better than the original, non-conformable end effector.The straight end effector had the best overall picking performance with 87% picking success rate.The new vacuum-based harvesting robot looks promising for automated harvesting of apples.Abstract. The end effector plays a critical role in fruit picking by a robotic fruit harvesting system. A newly developed vacuum-based robotic apple harvesting system, using the twist-and-pull fruit picking method, has shown promise in picking fruit from clusters and navigating through the tree canopies. The robot’s original thin foam end effector failed to achieve acceptable picking performance because it was unable to conform to fruit of different sizes and thus could not generate sufficient suction forces needed to detach fruit. This research was therefore aimed at developing new end effectors to greatly enhance the robot’s fruit picking performance. Field manual pulling and twisting experiments for three varieties of apples were conducted, and the critical pulling or suction force and twisting torque needed to detach 95% of apples were determined to be 28.3 N and 0.257 N-m (equivalent to a pulling force of 21.0 N for the current robot’s configuration), respectively. Three new silicone-based end effectors of different geometries (denoted as “Straight”, “Bellow” and “Curved”) were designed and fabricated, and they were evaluated in lab and field experiments. Results showed that the three new end effectors performed significantly better than the original, unconformable end effector based on multiple performance metrics, including vacuum pressure, overall picking success rate, picking rate by the rotation mechanism, and fruit attachment orientation. The “Straight” end effector performed consistently better than the other two new end effectors; it had 87% overall picking success rate, 65% success rate by the rotation mechanism alone, and 89% success rate when the middle section or cheek of fruit attached to the end effector. With further improvements, the “Straight” end effector should meet the apple picking performance requirement for the new vacuum-based robotic harvesting system. Keywords: Apple, End Effector, Fruit, Harvest, Robotics, Vacuum.

Due to labor shortage and rising labor cost for the apple industry, there is an urgent need for the development of robotic systems to efficiently and autonomously harvest apples. In this paper, we present a system overview and algorithm design of our recently developed robotic apple harvester prototype. Our robotic system is enabled by the close integration of several core modules, including calibration, visual perception, planning, and control. This paper covers the main methods and advancements in robust extrinsic parameter calibration, deep learning-based multi-view fruit detection and localization, unified picking and dropping planning, and dexterous manipulation control. Indoor and field experiments were conducted to evaluate the performance of the developed system, which achieved an average picking rate of 3.6 seconds per apple. This is a significant improvement over other reported apple harvesting robots with a picking rate in the range of 7-10 seconds per apple. The current prototype shows promising performance towards further development of efficient and automated apple harvesting technology. Finally, limitations of the current system and future work are discussed.This work is partly supported by the USDA-ARS inhouse project 5050-43640-003-00D.