An Inverse Kinematics Solution for a Series-Parallel Hybrid Banana-Harvesting Robot Based on Deep Reinforcement Learning

• Published in: Agronomy (Basel) Vol. 12; no. 9; p. 2157
• Main Authors: Lin, Guichao, Huang, Peichen, Wang, Minglong, Xu, Yao, Zhang, Rihong, Zhu, Lixue
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2022
• Subjects: Algorithms; banana-harvesting robot; Bananas; Data mining; Deep learning; deep reinforcement learning; Field tests; Fruits; Harvesting; Inverse kinematics; Kinematics; Learning algorithms; Machine learning; Optimization techniques; Reinforcement; Robotics; Robots; series-parallel hybrid robot; twin-delayed deep deterministic policy gradient; Workspace; China
• ISSN: 2073-4395; 2073-4395
• DOI: 10.3390/agronomy12092157

A series-parallel hybrid banana-harvesting robot was previously developed to pick bananas, with inverse kinematics intractable to an address. This paper investigates a deep reinforcement learning-based inverse kinematics solution to guide the banana-harvesting robot toward a specified target. Because deep reinforcement learning algorithms always struggle to explore huge robot workspaces, a practical technique called automatic goal generation is first developed. This draws random targets from a dynamic uniform distribution with increasing randomness to facilitate deep reinforcement learning algorithms to explore the entire robot workspace. Then, automatic goal generation is applied to a state-of-the-art deep reinforcement learning algorithm, the twin-delayed deep deterministic policy gradient, to learn an effective inverse kinematics solution. Simulation experiments show that with automatic goal generation, the twin-delayed deep deterministic policy gradient solved the inverse kinematics problem with a success rate of 96.1% and an average running time of 23.8 milliseconds; without automatic goal generation, the success rate was just 81.2%. Field experiments show that the proposed method successfully guided the robot to approach all targets. These demonstrate that automatic goal generation enables deep reinforcement learning to effectively explore the robot workspace and to learn a robust and efficient inverse kinematics policy, which can, therefore, be applied to the developed series-parallel hybrid banana-harvesting robot.