Vision-based Navigation System of Autonomous Mobile Robot. (Navigation and Position Error Compensation Experiments Based on Ceiling Landmark Recognition for Autonomous Mobile Robot).

Abstract

In this paper, we propose a vision-based navigation system for autonomous mobile robots which recognizes air conditioning devices (anemo) located on the ceiling as landmarks. Because landmarks on the ceiling are not obstructed by other objects, robots can find them easier than landmarks on the floor. In the recognition process, gathering quadrangles in the image are regarded as anemo, then the gravity center and the slope of quadrangles are calculated. Then the navigation system can calculate the distance and the angle of the anemo from map information. As a result, the navigation system can identify the present robot's position and orientation. In the proposed algorithm, if the landmark is not observed completely, the landmark is inferred from partial information. In experiments, we compared the error made by a robot which is navigated by our system with the error made by a robot which moves by dead-reckoning.