Trajectory Control of An Articulated Robot Based on Direct Reinforcement Learning

• Published in: Robotics (Basel) Vol. 11; no. 5; p. 116
• Main Authors: Tsai, Chia-Hao, Lin, Jun-Ji, Hsieh, Teng-Feng, Yen, Jia-Yush
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.10.2022
• Subjects: Algorithms; Anthropomorphism; Control methods; Control systems; Dynamic models; Inverse dynamics; Inverse kinematics; Learning; model predictive control; Neural networks; Predictive control; reinforcement learning; Reinforcement learning (Machine learning); Robot control; Robot dynamics; Robotics; Robots; Singularities; Torque; Training; Trajectory control; trajectory following; Unmanned aerial vehicles; Taiwan

Reinforcement Learning (RL) is gaining much research attention because it allows the system to learn from interacting with the environment. Yet, with all these successful applications, the application of RL in direct joint torque control without the help of an underlining dynamic model is not report...