Abstract: The probabilistic roadmap approach is one of the leading motion planning techniques.This paper provides an improved PRM method，the new method using two different sampling strategies in different stage，and it can overcome the PRM’s shortcoming（low connectivity in complex environment）.At last this paper tests the new method by several experiments，the result suggests that the improved method can increase the planning efficiency.

摘要： 概率路径图法（PRM）是最主要的运动规划算法之一，针对概率路径图法在复杂环境中规划效率低下的缺点提出了一种改进的概率路径图法，新方法的采样采用了分阶段混合采样策略。最后通过与传统的PRM方法进行仿真实验比较，结果表明改进后的PRM方法能够较大的提高规划效率。