A T-S Fuzzy Logic Controller for biped robot walking based on adaptive network fuzzy inference system

Abstract

A neuro-fuzzy learning algorithm is applied to design a Takagi-Sugeno type Fuzzy Logic Controller (T-S FLC) for a biped robot walking problem. The control design considers an output function imposed on the feedback and several TS-FLC models are determined each by ANFIS, which represent a piece-wise control inputs that together to perform a walking cycle. Two simulations of the closed-loop system for generation of walking motions are given, where we assume that the joint positions and the whole state of the system are available for controller feedback respectively.