著者
丸山 淳一 松原 崇充 Joshua G. Hale 森本 淳
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.27, no.5, pp.527-537, 2009 (Released:2011-11-15)
参考文献数
25
被引用文献数
3 3

This paper presents a method to learn stepping motions for fall avoidance by reinforcement learning. In order to overcome the curse of dimensionality associated with the large number of degrees of freedom with a humanoid robot, we consider learning on a reduced dimension state space based on a simplified inverted pendulum model. The proposed method is applied to a humanoid robot in numerical simulations, and simulation results demonstrate the feasibility of the proposed method as a mean to acquire appropriate stepping motions in order to avoid falling due to external perturbations.