Motion Planning of Obstacle Avoidance for Autonomous Mobile Robot Using Hierarchical Fuzzy Rules and Learning Automata.

Abstract

We show how an autonomous mobile robot can acquire the optimal action through the interaction with the real world. We propose a new architecture using the hierarchical fuzzy rules, fuzzy evaluation system and learning automaton. By using our proposed method, the robot acquires how to approach the goal avoiding a moving obstacle, using the steering and velocity control inputs, simultaneously. We also show the experimental results to confirm the feasibility of our method.