Model-free reinforcement learning with ensemble for a soft continuum robot arm

Ryota Morimoto, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

3 被引用数 (Scopus)

抄録

Soft robots have more passive degrees of freedom (DoFs) than rigid-body robots, which makes controller design difficult. Model-free reinforcement learning (RL) is a promising tool to resolve control problems in soft robotics alongside detailed and elaborate modeling. However, the adaptation of RL to soft robots requires consideration of the unique nature of soft bodies. In this work, a continuum robot arm is used as an example of a soft robot, and we propose an Ensembled Light-weight model-Free reinforcement learning Network (ELFNet), which is an RL framework with a computationally light ensemble. We demonstrated that the proposed system could learn control policies for a continuum robot arm to reach target positions using its tip not only in simulations but also in the real world. We used a pneumatically controlled continuum robot arm that operates with nine flexible rubber artificial muscles. Each artificial muscle can be controlled independently by pressure control valves, demonstrating that the policy can be learned using a real robot alone. We found that our method is more suitable for compliant robots than other RL methods because the sample efficiency is better than that of the other methods, and there is a significant difference in the performance when the number of passive DoFs is large. This study is expected to lead to the development of model-free RL in future soft robot control.

本文言語英語
ホスト出版物のタイトル2021 IEEE 4th International Conference on Soft Robotics, RoboSoft 2021
出版社Institute of Electrical and Electronics Engineers Inc.
ページ141-148
ページ数8
ISBN(電子版)9781728177137
DOI
出版ステータス出版済み - 4月 12 2021
外部発表はい
イベント4th IEEE International Conference on Soft Robotics, RoboSoft 2021 - New Haven, 米国
継続期間: 4月 12 20214月 16 2021

出版物シリーズ

名前2021 IEEE 4th International Conference on Soft Robotics, RoboSoft 2021

会議

会議4th IEEE International Conference on Soft Robotics, RoboSoft 2021
国/地域米国
CityNew Haven
Period4/12/214/16/21

!!!All Science Journal Classification (ASJC) codes

  • 人工知能
  • 機械工学
  • 制御と最適化
  • モデリングとシミュレーション

フィンガープリント

「Model-free reinforcement learning with ensemble for a soft continuum robot arm」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル