Evolutionary Neuro Fuzzy Controllers for Mobile Robot Navigation in Unknown Environment
This paper presents an effective navigation control method for mobile robots in an unknown environment. The proposed behavior manager (BM) switches between two behavioral control patterns, wall-following behavior (WFB) and to-ward-goal behavior (TGB), based on the relationship between the mobile robot and the unknown environment. In the WFB learning process, the input signal of a controller is the distance between the wall and the sonar sensors, and its output signal is the speed of two wheels of a mobile robot. A fitness function, which operates on the total distance traveled by the mobile robot, distance from the side wall, angle to the side wall, and moving speed, evaluates the WFB performance of the mobile robot. Experimental results reveal that the proposed DGPSO is superior to other methods in WFB and navigation control.
Keywords - Mobile Robot, Type-2 Fuzzy Neural Controller, Particle Swarm Optimization, Navigation Control, Wall-Following Control.