Fuzzy controller tuning of a mobile robot for exploration and safe navigation in constrained environment

In this paper we present a novel fuzzy controller structure for a mobile robot with the purpose for exploration of a constrained environment with obstacles. The proposed fuzzy rule base contains redundancy in some of the fuzzy rules, i.e., several consequents could be used. At each step we make random selection of one of these consequents. This is called in our paper Random Selection Fuzzy Rule Base. The simulation results show that the proposed fuzzy rule base makes the robot more agile compared with the results based on the fixed fuzzy rule base. Further on we applied a modified version of the particle swarm optimization in order to tune the fuzzy controller parameters. The simulations show that the optimized fuzzy controller allows the robot to navigate more safely, avoiding obstacles and to travel longer trajectories. Thus, the robot with the tuned fuzzy controller is able to explore wider area of the environment than the robot with the untuned controller.