Reinforcement learning for balancer embedded humanoid locomotion

Akihiko Yamaguchi, Sang Ho Hyon, Tsukasa Ogasawara

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

Reinforcement learning (RL) applications in robotics are of great interest because of their wide applicability, however many RL applications suffer from large learning costs. We study a new learning-walking scheme where a humanoid robot is embedded with a primitive balancing controller for safety. In this paper, we investigate some RL methods for the walking task. The system has two modes: double stance and single stance, and the selectable action spaces (sub-action spaces) change according to the mode. Thus, a hierarchical RL and a function approximator (FA) approaches are compared in simulation. To handle the sub-action spaces, we introduce the structured FA. The results demonstrate that non-hierarchical RL algorithms with the structured FA is much faster than the hierarchical RL algorithm. The robot can obtain appropriate walking gaits in around 30 episodes (20∼30 min), which is considered to be applicable to a real humanoid robot.

本文言語English
ホスト出版物のタイトル2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010
ページ308-313
ページ数6
DOI
出版ステータスPublished - 2010
外部発表はい
イベント2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010 - Nashville, TN, United States
継続期間: 2010 12月 62010 12月 8

出版物シリーズ

名前2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010

Other

Other2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010
国/地域United States
CityNashville, TN
Period10/12/610/12/8

ASJC Scopus subject areas

  • 人工知能
  • ハードウェアとアーキテクチャ
  • 人間とコンピュータの相互作用

フィンガープリント

「Reinforcement learning for balancer embedded humanoid locomotion」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