Advancement and field evaluation of a dual-arm apple harvesting robot

Abstract

Apples are among the most widely consumed fruits worldwide. Currently, apple harvesting fully relies on manual labor. Recently, robotic harvesting technology has attracted increasing attention. However, existing systems still fall short in terms of robust perception, harvesting efficiency, and reliability for operating in complex orchard environments. In this work, we present the development and evaluation of a dual-arm apple harvesting robot. The system integrates a Time-of-Flight (ToF) camera, two 4-degree-of-freedom robotic arms, a centralized vacuum system, and a fruit post-harvest handling module. During harvesting, suction force is dynamically assigned to either arm via the centralized vacuum system, enabling efficient apple detachment while significantly reducing power consumption and noise. Compared to our previous design, we incorporated a platform movement mechanism that enables both in-out and up-down adjustments, enhancing the robot's dexterity and adaptability to varying canopy structures. We developed a robust apple localization pipeline that combines a foundation-model-based detector, pixel-wise segmentation, and clustering-based depth estimation, which improves performance in outdoor conditions. Additionally, a novel dual-arm coordination strategy was introduced to respond to harvest failures based on sensor feedback, further improving picking efficiency. Field demonstrations were conducted in two commercial orchards in Michigan, USA, with different canopy structures, where over 100 apple trees and 1500 apples are attempted, respectively. The system achieved success rates of 80.7% and 79.7%, with an average picking cycle time of 5.97 seconds. The proposed coordination strategy reduced harvest time by 28% compared to a single-arm baseline. The proposed dual-arm harvesting robot enhances the reliability and efficiency of apple picking. With further advancements in hardware and software, the system holds strong potential for fully autonomous operation and future commercialization to support the apple industry.