A Fuzzy–Braitenberg Navigation Strategy for Differential Drive Mobile Robots

Abstract

In this paper, a novel algorithm is developed to achieve efficient and smooth navigation for a differential drive mobile robot in unknown environments. The algorithm takes advantage of the essential characteristics of a differential drive robot and combines fuzzy logic with the ideas of Braitenberg vehicles. We have also proposed and tested a new technique for tuning a membership function referred to as NEAR, representing the closeness of the robot to an obstacle. The tuning scheme is obtained based on the distribution directives of the range sensors on the robot. The resulting navigation algorithm has been implemented on a real mobile robot and tested in various environments. Some problems in the implemented algorithm are identified and effective solutions are proposed. Experimental results are presented which demonstrate the effectiveness and improved performance of the resulting Fuzzy---Braitenberg navigation scheme.