A low cost microcontroller implementation of fuzzy logic based hurdle avoidance controller for a mobile robot

Abstract

This paper describes the design of a fuzzy logic based hurdle avoidance controller for mobile robot navigation in noisy and uncertain environments. The employed controller is a two input, two output system. The inputs to the controller are `distance to hurdle' information from two SRF05 ultrasonic sensors mounted in front of the robot. The outputs from controller are speed commands for two drive wheels. The controller is first designed in MATLAB <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">®</sup> and its rule base is optimized for best possible results. It is then implemented using a cheap and readily available AT89C52 microcontroller. The robot with the proposed controller is finally tested in various environments containing obstacles and is found to avoid the obstacles in its way successfully.