Online Humanoid Walking Control and 3D Vision-based Locomotion

Koichi Nishiwaki, Satoshi Kagami, James J. Kuffner, Kei Okada, Yasuo Kuniyoshi, Masayuki Inaba, Hirochika Inoue

Abstract: Autonomous locomotion is one of the most important capabilities for humanoid robots operating within human environments. We present a walking control system that follows a given desired motion online using a layered control architecture, and implemented as a basic system of autonomous walking. A moving goal tracking function and reactive obstacle avoidance functions are implemented together with a stereo vision system, forming higher layer components of an autonomous locomotion system. Experiments using these layers are shown as basic examples of autonomous locomotion control.