改进RRT算法的无人驾驶车辆路径规划研究.pdf

机械设计与制造 第2期 276 Machinery Design Manufacture 2023年2月 改进RRT算法的无人驾驶车辆路径规划研究 樵永锋王瀚鑫1,周淑文1,杨贵军| (1.东北大学机械工程与自动化学院，辽宁沈阳110819;2.丹东东方测控技术股份有限公司，辽宁丹东118002) 摘 要:针对基础快速扩展随机树(Rapidly-exploring Random Trees,RRT)应用于无人驾驶车辆路径规划时缺乏导向性， 收敛速度慢，路径平滑性差及规划结果并非最优解等问题，提出了一种基于RRT的路径规划改进算法。首先，设计了启 发式采样策略:提出基于权重分配的目标指向的局部扩展方式，解决了节点盲目扩展的问题，避免了因目标偏向而出现 路径陷入局部最小值的情况，并通过设置转角阈值约束节点转角范围，同时采用变步长采样策略，提高了算法局部避障 能力；其次，对已得路径进行后处理:提出了节点优化策略，并用B样条曲线进行路径拟合，实现了路径长度的优化并满足 平滑性要求，路径末端与 目标点采用Reeds-Shepp曲线连接，解决了车辆抵达目标点时的航向问题。最后利用Matlab软 件，将改进算法与基础RRT及其衍生算法进行了对比分析，验证了所提算法的有效性和优越性。 关键词：无人驾驶车辆;路径规划;RRT算法;启发式采样;后处理 中图分类号:TH16;TP391.96 文献标识码:A 文章编号:1001-3997(2023)02-0276-06 Research on Driverless Vehicle Path Planning with Improved RRT Algorithm QIAO Yong-fengb2, WANG Han-xin1, ZHOU Shu-wen1, YANG Gui-jun1 (1.School o Mechanical Engineering and Automation, Northeastern University, Liaoning Shenyang 110819, China; 2.Dandong Dongfang Measurement Control Technology Co., Ltd., Liaoning Dandong 118002, China) Abstract: Aiming at the problem which is lack of guidance, slow convergence 9 poor smoothness and the planning result is not the optimal solution in RRT applied to driverless vehicle path planning, an improved path planning algorithm based on RRT is pro­ posed. Firstly 9 a heuristic sampling strategy is designed： The local expansion mode of target orientation based on weight redistri­ bution is proposed to solve the problem of blind expansion of nodes, the pathfalling into the local minimum due to the target orien­ tation is avoided, the steering angle range of the nodes is constrained by setting the steering angle threshold, and the variable step