Stable adaptive control of a bipedal walking; robot with CMAC neural networks

Abstract

We present a stable adaptive control approach for a bipedal walking robot. This approach utilizes a self-organizing CMAC neural network mechanism which has a fast training rate, high approximation accuracy and significant reduction in space complexity. In order to apply this control approach to a bipedal walking robot, a Cartesian virtual dynamics space is introduced based on the virtual model control concept. The adaptive CMAC neural network control approach identifies the unmodelled dynamics of the bipedal robot and ensures asymptotic system stability in a Lyapunov sense. It can also better accommodate unexpected external disturbances, enhancing the control robustness of the bipedal robot. The CMAC neural network structure, its training algorithm, and bipedal locomotion control are described. The simulation results for a walking robot are presented.