基于改进RRT算法的无人车路径规划

Path Planning of Unmanned Vehicle Based on Improved RRT Algorithm

摘要:

针对无人车在复杂环境中进行全局路径规划时存在的盲目搜索、节点冗余、路径不光滑及不安全等问题，提出一种基于快速扩展随机树（Rapidly-Exploring Random Tree，RRT）的综合改进路径规划算法。首先引入目标动态概率采样策略和人工势场引导随机树扩展机制。其次根据汽车运动学模型，对规划的路径进行转角约束和碰撞检测，保证路径的安全性。然后引入Reeds-Sheep曲线用于直接与目标位姿进行连接，避免在终点处进行多余的位姿调整。最后对路径进行剪枝和平滑处理，得到一条更短更光滑的路径。在实验部分，针对不同仿真环境，以规划时间、路径长度和节点数目作为评价指标，对比了基本RRT算法、基本RRT*算法和本文算法的路径规划效果。实验结果显示本文算法在路径规划效率和路径质量上都具有一定优越性，规划的路径长度较优并且满足车辆运动学约束。

Abstract:

Aiming at the problems of blind search, node redundancy, unsmooth and unsafe path of unmanned vehicle in global path planning in complex environment, a comprehensive improved path planning algorithm based on rapid exploring random tree (RRT) is proposed. Firstly, the target dynamic probability sampling strategy and the artificial potential field guided random tree expansion mechanism are introduced. Secondly, according to the vehicle kinematics model, the angle constraint and collision detection are carried out on the planned path to ensure the safety of the path. Then the reeds sheet curve is introduced to connect directly with the target pose to avoid redundant pose adjustment. Finally, the path is pruned and smoothed to get a shorter and smoother path. In the experimental part, according to different simulation environments, taking the planning time, path length and number of nodes as evaluation indexes, the path planning effects of basic RRT algorithm, basic RRT * algorithm and this algorithm are compared. The experimental results show that this algorithm has certain advantages in path planning efficiency and path quality, the planned path length is better, and meets the vehicle kinematics constraints.