Variable template matching for autonomous mobile robot with hierarchical control system

We present a vision based navigation system which has an error recovery function for an autonomous mobile robot. A misrecognition of landmark causes the robot to dislocate itself. When this happens, the robot is unable to perform its primary objective. In order to solve this kind of problem, we have proposed a hierarchical control architecture "HALAS"(Hierarchical Adaptive and Learning Architecture System). This consists of some modules which are arranged hierarchically and each module means a single function of this robot. In this paper, we deal with the Variable Template Matching method (VTM) in Anemo Perception Module which is one of the modules in HALAS. The VTM is able to adapt the template to change of the landmark size. The robot detects the landmark correctly in spite of the change of the landmark size caused by error of the dead reckoning, the zooming of the cameras and the design changes.