A Modular Dual-Arm Apple Harvesting Robot with Enhanced Field Performance

2026-06-12

AI Summary

This study addresses key commercialization bottlenecks in orchard apple harvesting robots—namely low operational efficiency and poor environmental adaptability—by proposing a modular dual-arm picking system. The design features a vertically stacked dual-arm architecture enabling simultaneous harvesting in upper and lower canopy zones of a single tree. It integrates a vision pipeline combining Grounding-DINO with EfficientViT-SAM for robust perception, employs seventh-order jerk-bounded trajectory planning enhanced by Control Barrier Function–based safety filtering, and implements a temporal logic–driven coordination strategy with asynchronous scheduling of a shared vacuum source. Field trials demonstrate an 80.0% single-fruit harvesting success rate, an average cycle time of 7.53 seconds, 91.2% of harvested apples meeting USDA Extra Fancy grade standards, and a low fruit damage rate ranging from 2.4% to 4.9%.

Abstract

Robotic apple harvesting offers a promising solution to labor shortages in commercial orchards, but low throughput and poor performance in orchard environments hinder its commercial adoption. This paper presents a modular dual-arm apple harvesting robot that uses a vertically stacked arms to enable simultaneous operation in the upper and lower zones of a single tree, simplifying platform positioning from multi-tree lateral repositioning to single-tree stops. Compared to our prior horizontal dual-arm system, the platform integrates 5 advances: (1)a foundation-model-based perception pipeline combining Grounding-DINO and EfficientViT-SAM for robust fruit localization in unstructured outdoor environments; (2)7th-order jerk-bounded trajectory generation paired with a Control Barrier Function safety filter to achieve fast yet safe arm motions; (3)a linear sweep harvesting strategy with a 10cm approach buffer and rotational detachment that improves picking reliability; (4)a temporal-logic-based dual-arm coordination policy with vision-arm async scheduling that maximizes usage of a shared vacuum source; and (5)field validation in 2 commercial orchards covering different apple varieties and tree architectures during the 2025 harvest season. Across the 1738 arm cycles collected in these field trials, the system achieved an 80.0% per-attempt success rate and a mean per-arm cycle time of 7.53s. Fruit damage assessments confirmed that 91.2% of robotically harvested fruit retained the highest USDA grade (Extra Fancy), with bruise rates between 2.4% and 4.9%. With further improvements in the picking cycle time and handling of heavy foliage occlusions, this new modular robot design holds promise for commercial harvesting of apples.

Problem

• apple harvesting robot
• field performance
• labor shortage
• orchard automation
• fruit picking

Innovation

• modular dual-arm robot
• foundation-model-based perception
• jerk-bounded trajectory generation
• temporal-logic coordination
• field-validated harvesting