基于区域采样随机树的客车局部路径规划算法  

Local path planning of bus based on RS-RRT algorithm

作　　者：韩小健 赵伟强[1] 陈立军 郑宏宇[1] 刘阳[1] 宗长富[1] HAN Xiao—jian;ZHAO Wei-qiang;CHEN Li-jun;ZHENG Hong-yu;LIU Yang;ZONG Chang-fu(State Key Laboratory of Automobile Simulation and Control,Jilin University,Changchun 130022,China;Big Data and Network Management Center,Jilin University,Changchun 130022,China)

机构地区：[1]吉林大学汽车仿真与控制国家重点实验室,长春130022 [2]吉林大学大数据和网络管理中心,长春130022

出　　处：《吉林大学学报（工学版）》2019年第5期1428-1440,共13页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金项目(51575224);吉林省科技发展计划项目(20170414045GH)

摘　　要：为解决结构化道路环境下自动驾驶客车的路径规划问题,针对双车道避障工况提出了一种区域采样随机树RS-RRT算法。在采样阶段,集成高斯分布采样和局部偏向性采样来提高路径规划算法的搜索效率。在随机树扩展阶段,考虑了客车和障碍物的实际尺寸,利用分离轴定律(SAT)实时检测客车和周围障碍物的碰撞风险。在后处理阶段,结合安全性和舒适性的目标,融合了驾驶共识、安全距离模型和路径平滑算法对规划的路径进行修正。为验证RSRRT算法的有效性,搭建了商用车电液转向系统硬件在环试验台,利用TruckSim构建仿真场景,通过MATLAB和TruckSim的联合仿真实现算法的验证。试验结果表明:与基本RRT和目标偏向性RRT(Goal-biasing RRT)相比,本文算法在节点数量、路径长度和运行时间上均有优势,生成的路径满足客车动力学和路径跟踪要求。In order to solve the path planning problem of self-driving bus in the structured roadenvironment,an improved path planning algorithm,named Regional-Sampling Rapidly-exploring RandomTree(RS-RRT)algorithm,was proposed for obstacle avoidance conditions.In the sampling phase,Gaussian distribution sampling and local biasing sampling were integrated to improve the search efficiencyof the path planning algorithm.In the expansion phase of the random tree,considering the actual size of busand obstacles,the Separating Axis Theorem(SAT)was used to detect the collision of bus andsurrounding obstacles in real time.In the post-processing stage,considering the goal of safety and comfort,the driver's driving consensus,the safety distance model and path smoothing algorithm were combined tocorrect the planning path.In order to verify the effectiveness of the RS-RRT algorithm,the hardware-in-the-loop test bench of electro-hydraulic steering system for commercial vehicle was built.The simulation scenario was built by TruckSim,and the proposed algorithm was verified by the co-simulation software ofMATLAB and TruckSim.The results show that compared with basic RRT and Goal-biasing RRT,theproposed RS--RRT algorithm has advantages in terms of number of nodes,path length and running time.The generated path can meet the dynamics and path tracking requirements of the bus.

关 键 词：车辆工程 局部路径规划 区域采样 碰撞检测 路径平滑 

分 类 号：U461.1[机械工程—车辆工程] U469.1[交通运输工程—载运工具运用工程]