Stereo-Based Autonomous Navigation and Obstacle Avoidance*

Abstract This paper presents a stereo vision-based autonomous navigation system using a GPS and a modified version of the VFH algorithm. In order to obtain a high-accuracy disparity map and meet the time constraints of the real time navigation system, this work proposes the use of a semi-global stereo method. By not suffering the same issues of the regularly used local stereo methods, the employed stereo technique enables the generation of a highly dense, efficient, and accurate disparity map. Obstacles are detected using a method that checks for relative slopes and heights differences. Experimental tests using an electric vehicle in an urban environment were performed to validate the proposed approach.