A fuzzy potential approach with the cache genetic learning algorithm for robot path planning

Abstract

The authors previously (1994) showed that the potential field method combined with the navigating fuzzy logic controller (NFLC) can produce a safe and smooth paths for a robot. When the robot is trapped in undesired local minimum, the fuzzy tracking controller (FTC) can be employed to escape the trapping. Since the rules of the NFLC and the FTC is developed by expert's experiences, the learning of the rules is necessary to improve the performance. In this paper, an auto tuning technique called the cache genetic algorithm (CGA) is proposed to adjust the rules. The proposed CGA performs the fast operation of selection, crossover and mutation in a cache pool to obtain best fuzzy parameters. Computer simulations showed that the proposed fuzzy potential approach (FP) with the proposed cache genetic learning algorithm can improve the overall performance with fast tuning speed.