主催: 一般社団法人 日本機械学会
会議名: ロボティクス・メカトロニクス 講演会2021
開催日: 2021/06/06 - 2021/06/08
Pneumatic artificial muscles are advantageous owing to dynamic stiffness. However, the drawback of this is their poor controllability. In this paper, a reinforcement learning-based control system using a real robot is proposed to improve controllability. The proposed system is aimed to generate dynamic motion patterns that utilize the body structure and variable stiffness characteristics. We propose a reinforcement learning-based realistic drum-playing robot, and confirm its effectiveness through experiments.