Research Of Path Planning For Mobile Robots Based On Particle Swarm Optimization

Particle Swarm Optimization (PSO) is a kind of novelty evolution algorithm. Similar to Genetic Algorithms (GAs), PSO also is a population based optimization tool. The system is initialized with a population of random solutions and searches for optima by updating generations. PSO has been successfully applied in many areas: function optimization, artificial neural network training, fuzzy system control, and other areas. Its superiority in solving complex problem has been manifested.The origin and the development of Particle Swarm Optimization are outlined in this paper. The principal, the topologic configuration, the standard Particle Swarm Optimization are presented. Meanwhile, some classical improved Particle Swarm Optimization to make up for the shortcomings of standard Particle Swarm Optimization and its widespread applications have been introduced. The origin and the development of mobile robot are also outlined in this paper. The mobile robot's prospect aspect in the future-intelligent robot has been presented. The path planning for mobile robots is the most important aspect of intelligent robot. The general conceptions, characteristic, classify based issue and some familiar methods of path planning are presented.On the basis of Particle Swarm Optimization, according to the characteristics of the path planning of mobile robots in the static environment, a new method was proposed. The standard Particle Swarm Optimization has been improved. Inertia Weight has been changed linear, meanwhile some invalid particle will be change into random valid particle once again. So extend the search range and keep part from get into local optima. The path planning of mobile robots based Particle Swarm Optimization includes two steps: the first step is adopting the grid theory to establish the free space model of the mobile robot; the second step is adopting the Particle Swarm Optimization to find out the global optimal path. The computer simulation experiment was carried out. By comparing with the path planning method based on the standard Particle Swarm Optimization, Constriction Factor Particle Swarm Optimization and Inertia Weight Particle Swarm Optimization, it has been confirmed that the proposed method has better performance in convergence speed, dynamic convergence behavior.