FUZZY LOGIG AND REINFORCEMENT LEARNING BASED APPROACHES FOR MOBILE ROBOT NAVIGATION IN UNKNOWN ENVIRONMENT

Abstract

Fuzzy logic controller promises an efficient solution for the mobile robot navigation. However, it is difficult to maintain the correctness, consistency and completeness ofthe fuzzy rule_base constructed and tuned by a human operator. Reinforcement leaming qgthod is a ÿpe of machine leaming. This approach is often used in the field of robotics. It aims of learnlng itre nrzzy rules automatically and to generate a control law for a mobile robot in unknown environment when we æsume that the onlv obtained information is a scalar signal which is a reward ü punishment. The process of leaming consists to improve the choice of actions to maximize rewards. It is an intelligent navigation method for an autonomous mobile robot. kr this paler, the Q-learning algorithm of reinforcement leaming and'fuzzy controllers are used for the mobile robot navigation. In order to improve the mobile robot performanc.., an opti-iration of fuzzy conhollers will be discussed for the robot navigation; based on prior knowledge introduced by a finzy inference system so that the initial behavior is acceptable. Simulation results show the obtained behaviors using the three approaches and the effectiveness of the optimization method presenting significant improvements of the robot behaviors and the speed of leaming. The results are compared and discussed.