Niche Genetic Algorithm for Robot Path Planning

Abstract

Robot path planning has been an active research area, and many methods have been developed to tackle this problem recently, especially traditional GA is applied in path planning for mobile robots successfully, but traditional genetic algorithm (GA) has some common drawbacks, one is time-consuming when dealing with a large population, and the other is premature convergence. In this paper, robot path planning method based on niche genetic algorithm (NGA) is first presented, and to make NGA more effective, four specialized operators are designed. Experimental results indicate that presented method has more capability and higher speed of obtaining an optimal or near-optimal collision free path planning than the traditional GA.