Verification of stereo vision based localization system

It is important for a robot to be able to self localize during real world operation. This paper presents a verification for a localization method based on stereo cameras and a know grid based map. Verification is achieved by moving the robot through the real world while collecting vision and odometry data over a 200 [m] path. After moving the robot, we manually measured the coordinates of the start point and several way points. The pathway was estimated by the localization process and compared to the measured value to examine the localization effectiveness.