Goal seeking of mobile robot using fuzzy actor critic learning algorithm

Abstract

In this paper, we present a study of a basic behavior of mobile robot, which is goal seeking. Firstly, we use the heuristics approaches to develop a controller based on fuzzy logic to control the robot and bring it from an initial position to a final position. Secondly, we use the learning technique-Fuzzy actor critic learning algorithm (FACL)-. The reinforcement learning FACL has to select the actions available in each fuzzy rule. The main advantage of the proposed method is the automatic construction of these rules. So far, simulation has shown that the controller is able to perform successful navigation task in known environments, and it has smooth action and exceptionally good robustness.