System Design and Control of an Apple Harvesting Robot

TL;DR

This paper presents the design and control of a robotic apple harvesting system integrating deep learning detection, a dexterous manipulator, and a vacuum end-effector, demonstrating promising experimental results for automated harvesting.

Contribution

It introduces a novel integrated robotic system with a deep learning-based detection, a hybrid actuation manipulator, and a nonlinear control scheme for efficient apple harvesting.

Findings

Successful fruit detection and localization using RGB-D camera

Effective manipulation and detachment of apples in tests

Robust and accurate motion control demonstrated

Abstract

There is a growing need for robotic apple harvesting due to decreasing availability and rising cost in labor. Towards the goal of developing a viable robotic system for apple harvesting, this paper presents synergistic mechatronic design and motion control of a robotic apple harvesting prototype, which lays a critical foundation for future advancements. Specifically, we develop a deep learning-based fruit detection and localization system using an RGB-D camera. A three degree-of-freedom manipulator is then designed with a hybrid pneumatic/motor actuation mechanism to achieve fast and dexterous movements. A vacuum-based end-effector is used for apple detaching. These three components are integrated into a robotic apple harvesting prototype with simplicity, compactness, and robustness. Moreover, a nonlinear velocity-based control scheme is developed for the manipulator to achieve accurate and agile motion control. Test experiments are conducted to demonstrate the performance of the developed apple harvesting robot.