改进的快速扩展随机树路径规划算法

Improved rapidly-exploring random tree path planning algorithm

针对快速扩展随机树(RRT)路径规划算法缺乏稳定性和偏离最优解的问题,提出了一基于RRT的偏向性路径搜索算法(m-RRT)。m-RRT采用生成随机点向量组的形式对随机点选取策略进行了优化,改善快速扩展随机树的不确定性,减少不必要的扩展,而加快向目标位置搜索的速度,且得到的路径优于RRT算法的结果。通过其在二维平面路径规划和三维机械臂路径规划的测试,表明其具有一定的应用价值。

Because the rapidly-exploring random tree（ RRT） path planning algorithm is unstable and not optimal,propose a biased path search strategy which is called m-RRT. By generating a random point vectors to optimize the strategy of random points selection,the uncertainty of RRT searching can be improved,meanwhile,the expansion of searching tree can also be reduced. So,it can improve the searching speed to the destination,and the path got by m-RRT is better than that by RRT. Through the two-dimensional path planning and three-dimensional manipulator path planning,the results show that it has certain application value.