A Fuzzy-CMAC Based Hybrid Intuitive Approach for Biped Robot’s Adaptive Dynamic Walking

Abstract

In this paper, we have proposed a new neural network based hybrid intuitive approach for biped robot's adaptive walking. Our approach takes advantage on the one hand from a Fuzzy-CMAC based stage and on the other hand from high level intuitive control strategy involving only the regulation of the robot’s average velocity. The main interest of this approach is to proffer to the walking robot autonomy and robustness, involving only one parameter: the average velocity. Experimental results validating the proposed intelligent hybrid control strategy have been presented and discussed.