Fuzzy logic-based 'perception-action' behavior control of a mobile robot in uncertain environments

摘要

This paper presents a method for fuzzy logic-based 'perception-action' behavior control of a mobile robot in uncertain environments. A key problem in 'perception-action' behavior control is to coordinate and integrate more reactive behaviors when the mobile robot executes tasks in complex environments. The main idea of the paper is to formulate 'perception-action' behaviors and to coordinate their conflicts and competitions by fuzzy sets and fuzzy rules. An advantage of this method is that the coordination of more reactive behaviors is very robust (nearly independent of dynamic environments). The simulation results show that the proposed method, only using dynamic information acquired by ultrasonic sensors, can perform robot navigation in complex and uncertain environments by efficiently weighting reactive behaviors, such as obstacle avoidance, edge following, and moving to the target.