Abstract: A path planning method based on artificial potential field optimization is proposed. The ant algorithm is initialized by the planning result of the artificial potential field method as the prior knowledge, which improves the algorithm's efficiency. On the other hand, the path obtained by the artificial potential field method is optimized by the ant algorithm, which overcomes the local minima problem in the artificial potential field method. Results of computer simulation experiment indicate that the method can implement optimal path planning in complex environments. In order to improve the planning efficiency a feasible idea of combining traditional planning methods with statistic optimization is also presented.