Fuzzy logic control of an obstacle avoidance robot

Abstract

A fuzzy controller is used to control an obstacle avoidance mobile robot. In this classical problem, the aim is to guide a mobile robot along its path to avoid any static obstacles in front of it. Obstacle avoidance in real-time is a mandatory feature for mobile robots in a dynamically unknown environment. The controller presented here uses three sub-controllers. The outputs are summed to produce a concerted effort to control the motors steering the robot away from obstacles. This fuzzy controller was implemented on a miniature robot. This robot is able to overcome its limitation on range accuracy to follow a left wall, maintaining a short distance from it, to avoid obstacles in front of it, and to decide whether a gap is wide enough for a "side-step" manoeuvre.