A Reinforcement Learning Based Dynamic Walking Control
- 1 April 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164)
- No. 10504729,p. 3609-3614
- https://doi.org/10.1109/robot.2007.364031
Abstract
A quasi-passive dynamic walking robot is built to study natural and energy-efficient biped walking. The robot is actuated by MACCEPA actuators. A reinforcement learning based control method is proposed to enhance the robustness and stability of the robot's walking. The proposed method first learns the desired gait for the robot's walking on a flat floor. Then a fuzzy advantage learning method is used to control it to walk on uneven floor. The effectiveness of the method is verified by simulation results.Keywords
This publication has 7 references indexed in Scilit:
- Using a controller based on reinforcement learning for a passive dynamic walking robotPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Poincaré-Map-Based Reinforcement Learning For Biped WalkingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A Bipedal Walking Robot with Efficient and Human-Like GaitPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Efficient Bipedal Robots Based on Passive-Dynamic WalkersScience, 2005
- First Steps in Passive Dynamic WalkingPublished by Springer Science and Business Media LLC ,2005
- Fuzzy advantage learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Passive Dynamic WalkingThe International Journal of Robotics Research, 1990