Vision Based Navigation System of Autonomous Mobiel Robot. Landmark Detection using Fuzzy Template Matching.

Abstract

In this paper, we propose a vision-based navigation system for autonomous mobile robots which recognizes outlets of the air conditioning system (anemo) located on the ceiling as landmarks. Because landmarks on the ceiling are not obstructed by other objects, robots can find them more easily than landmarks on the floor. To detect the landmark, we applied template matching whose template consists of fuzzy sets. The grades of fuzzy membership are input into a neural network (NN). NN leads a template to the landmark location. 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. By the proposed algorithm, precise and fast landmark detection becomes possible even if the landmark follows shadows.