Reinforcement Learning Control for Biped Robot Walking on Uneven Surfaces

— Biped robots based on the concept of (passive) dynamic walking are far simpler than the traditional fullycontrolled walking robots, while achieving a more natural gait and consuming less energy. However, lightly actuated dynamic walking robots, which rely on the natural limit cycle of their mechanical structure, are very sensitive to ground disturbances. Already a very small step down can cause the robot to lose stability. In this paper, we investigate the use of reinforcement learning to make a dynamic walking robot more robust against ground disturbances. The learning controller is applied to a d two-link biped which is an abstraction of a mechanical prototype developed at the Delft Biorobotics Laboratory. The learning controller has been designed such that it can be applied as a straightforward extension of the proportional-derivative (PD) controller currently used to drive the robot’s pneumatic actuators. The learning controller is therefore suitable for the future implementa...

• Type: Conference
• Year: 2006
• Where: IJCNN
• Authors: Shouyi Wang, Jelmer Braaksma, Robert Babuska, Daan G. E. Hobbelen
• Keywords: Dynamic Walking, Dynamic Walking Robot, IJCNN 2006, Walking Robot