Adaptive controller based PSO with virtual sensor for obstacle avoidance in dynamic environments

In this paper, an Adaptation of Advanced Artificial Potential Field (AAPF) controller based on Particle Swarm Optimization (PSO) algorithm is proposed. It plans the robot's motion in cluttered and dynamic environments to make the robot reaches to its goal. The PSO is used to optimize the factors of the forces applied on the robot to guide the robot towards to the right path. The optimization process is done by selecting the optimum values of these factors. A measure of smoothness is used to guide the PSO algorithm during the optimization process. The PSO is reused once a change in the environment is occurred. This scheme makes the robot able to reach to its target with shortest path and avoidance of the obstacles whatever changed environment. Shortest path means more smoothness and minimum time. The proposed adaptive AAPF controller uses the concept of virtual sensor. The virtual sensor's calculations are modified in this paper. The proposed system is simulated on Windows Vista using MATLAB Software at different workspaces, and compared with another not adaptive system.