Designing Fuzzy Controller and Real Time Experimental Studies on a Nonholonomic Robot

This paper recommends a design and implementation of a fuzzy control system based on a hierarchical scheme for an autonomous robot. The problem addressed is the diagonal parking in a constrained space which is a typical problem in nonlinear motion control of nonholonomic robots. The fuzzy controller is a combination of two fuzzy modules. The rules of each module have been obtained from heuristic knowledge and numerical data (with geometric information). The goal of the control system is to provide short paths with continuous curvature. Approximated trajectories are composed of circular arcs of minimum turning radii and straight line segments. Also, we have proposed a vision based approach for estimating the robot position and direction. Real time experimental results of mobile robot in compared with simulation results demonstrate the efficiency of the described controller.