Perceptual system for a mobile robot under a dynamic environment

This paper deals with a perceptual system for a mobile robot under a dynamic environment. The mobile robot is controlled by the coupling mechanism of perceptual system and action system. Action system of the mobile robot is based on fuzzy controller. In the proposed approach, evolutionary computation is adopted to generate functions used for perceptual system which translates sensing information into perceptual information. The mobile robot can adapt to its dynamic environment by the translation using those functions without modifying current behavioral knowledge. The effectiveness of the proposal approach is demonstrated by computer experiments for obstacle avoidance problem under a dynamic environment which contains several obstacles.