Action learning of a mobile robot with structured intelligence in a dynamic environment

Abstract

This paper deals with a controlling method of mobile robot with structured intelligence. Modular neural networks are applied for action control based on perceiving-acting cycle of ecological psychology. In the proposed method, the perceptual system and action system restrict each other through interaction with its environment We conduct several experiments using a mobile robot we developed. Experimental results show the robot can acquire actions in a dynamic environment Finally, we discuss the relationship between the complicatedness of a changing environment and the number of action patterns of modular neural networks.