Adaptive Gaussian parameter particle swarm optimization and its implementation in mobile robot path planning

Path planning based on heuristic optimization method is developed to simplify the path planning issues into optimization problems. Particle Swarm Optimization (PSO) is one of the heuristic optimization methods often used because of its simplicity, easy to implement and has few parameters to set. However, the basic PSO algorithm has difficulties balancing exploration and exploitation, and suffer from premature convergence, it efficiency to solve path planning problem may be restricted. Aiming to overcome these drawbacks and solving the path planning problem efficiently, this paper proposed the Gaussian parameter updating rule use to speed up the convergence by maintaining exploration and exploitation of the particle. Then, particle re-initialization is proposed after analyzing the behavior of PSO algorithm to prevent premature convergence. Simulation result shows in benchmark test with Adaptive Inertia (AIW) PSO and standard PSO that the proposed PSO algorithm can find optimal solution faster than the other algorithm which can convergence in less than 150 iterations. Furthermore, particle re-initialization can find optimal solution efficiently which result in 3% more shortest, 10% more smooth and guaranteed to collision free path.