Neuro-fuzzy network control for a mobile robot

Abstract

A control structure that makes possible the integration of a kinematic controller and a neuro-fuzzy network (NFN) dynamic controller for mobile robots is presented. A combined kinematic/dynamic control law is developed using backstepping and stability is guaranteed by Lyapunov theory. The NFN controller proposed in this work can deal with unmodeled bounded disturbances and/or unstructured unmodeled dynamic in the mobile robot. On-line NFN parameter tuning algorithms do no require off-line learning yet guarantee small tracking errors and bounded control signals are utilized.