A vision-based autonomous lane following system for a mobile robot

Abstract

In this paper, a vision-based autonomous lane following system for a mobile robot is presented. To achieve the autonomous lane following, the lane images are obtained in real time using a camera fixed mounted on the robot. Lane position is presented based on lane boundary pixel extractor (LBPE) and Hough transform in the image coordinate frame, and transformed to the mobile robot coordinate frame using photogrammetric techniques. The visibility of the lane information is checked by the lane width constraints and its parallel property. Path planning of the mobile robot is performed based on mobile robot's position and orientation with respect to the lanes obtained from the vision information. Experimental results demonstrated the feasibility of the approach.