Navigation System for Air Conditioning Equipment Inspection Robot

Abstract

We have previously proposed a navigation system for autonomous mobile robots that can recognize regular ceiling landmarks. This system can find square air diffusers on ceilings by sensing their multiple-quadrangle characteristics. We have now developed a new system that is able to recognize circular air diffusers. In addition, certain lighting conditions which obstructed recognition in the original system do not interfere with the newly proposed system. Here we applied Fuzzy and Neural Network Logic technology. A pre-processed image of a landmark is compared with a fuzzy template made from the fuzzy membership function. In order to find specific landmarks, the system determines the degrees of similarity by comparing the sited object with a variety of templates stored in its memory. Then a Neural Network uses results of this calculation to hone in on its target. So, the system can recognize many different kinds of landmarks. This paper shows the principle of this system and experimental results.