Path Planning for Nonholonomic Car-like Mobile Robots Using Genetic Algorithms

This paper aims to solve the problem of path planning for nonholonomic car-like mobile robots in unstructured obstacle environments. A path planner utilizing evolutionary computation techniques is proposed. While sharing many benefits of evolutionary computation, the control based sampling strategy is applied in the evolution process to handle nonholonomic problems. Specific operators and evaluation methods are developed instead of traditional genetic algorithm. Simulation results show that the proposed algorithm is effective handling path planning problems of nonholonomic car-like mobile robots, and the generated paths are nice which is shown by a comparison study