Development and evaluation of a dual-arm robotic apple harvesting system

Abstract

Harvesting labor is the single largest cost in apple production in the U.S. Increased cost and growing shortage of labor has forced the apple industry to seek automated harvesting solutions. Despite considerable progress in recent years, the existing robotic harvesting systems still fall short of performance expectations, lacking robustness and proving inefficient or overly complex for practical commercial deployment. In this paper, we present the development and evaluation of a new dual-arm robotic apple harvesting system. The system hardware mainly consists of a perception component, two four-degree-of-freedom manipulators, a centralized vacuum system, and a fruit handling and bin filling component designed for the collection and transportation of picked fruits. Synergistic functionalities for automated apple harvesting were achieved through the development of software algorithms. In particular, an updated perception system based on dual-laser scanning was proposed to enable sequential localization of apples for the dual-arm robotic system. A sophisticated planning scheme was devised to coordinate the movement of the two manipulators, allowing them to approach the fruit effectively and share a centralized vacuum system for efficient fruit detachment. The robotic system has been evaluated through field trials in a challenging apple orchard with complex, dense canopy, and it achieved 60% successful picking rate. The dual-arm coordination algorithm resulted in 9% to 34% harvest time improvements, compared to the 1-arm robotic system design. The new dual-arm robotic system is compact in design and dexterous in movement, and with further improvements in hardware and software, it holds great potential for providing a commercially viable harvesting automation solution for the apple industry