汽车工程 ›› 2023, Vol. 45 ›› Issue (7): 1123-1133.doi: 10.19562/j.chinasae.qcgc.2023.07.003

所属专题: 智能网联汽车技术专题-规划&决策2023年

• 专题:汽车智能化关键技术 • 上一篇    下一篇

基于改进混合A*的智能汽车时空联合规划方法

胡杰1,2,3(),张志豪1,2,3,陈瑞楠1,2,3,陈锐鹏1,2,3,刘昊岩1,2,3,朱琪1,2,3,陈晖4   

  1. 1.武汉理工大学,现代汽车零部件技术湖北省重点实验室,武汉 430070
    2.武汉理工大学,汽车零部件技术湖北省协同创新中心,武汉 430070
    3.武汉理工大学,新能源与智能网联汽车湖北省工程技术中心,武汉 430070
    4.东风汽车股份有限公司商品研发院,武汉 430000
  • 收稿日期:2023-01-12 修回日期:2023-02-23 出版日期:2023-07-25 发布日期:2023-07-25
  • 通讯作者: 胡杰 E-mail:auto_hj@163. com
  • 基金资助:
    湖北省科技重大专项(2020AAA001)

Spatio-temporal Joint Planning Method of Intelligent Vehicles Based on Improved Hybrid A

Jie Hu1,2,3(),Zhihao Zhang1,2,3,Ruinan Chen1,2,3,Ruipeng Chen1,2,3,Haoyan Liu1,2,3,Qi Zhu1,2,3,Hui Chen4   

  1. 1.Wuhan University of Technology,Hubei Key Laboratory of Modern Auto Parts Technology,Wuhan 430070
    2.Wuhan University of Technology,Auto Parts Technology Hubei Collaborative Innovation Center,Wuhan 430070
    3.Wuhan University of Technology,Hubei Technology Research Center of New Energy and Intelligent Connected Vehicle Engineering,Wuhan 430070
    4.Commercial Product R&D Institute,Dongfeng Automobile Co. ,Ltd. ,Wuhan 430000
  • Received:2023-01-12 Revised:2023-02-23 Online:2023-07-25 Published:2023-07-25
  • Contact: Jie Hu E-mail:auto_hj@163. com

摘要:

运动规划是自动驾驶系统生成轨迹的关键模块,现有运动规划多采用路径和速度解耦的方法,但解耦的规划方法在复杂动态场景下易陷入轨迹次优。本文提出了一种基于搜索和数值优化结合的时空联合运动规划方法,直接求解可行驶轨迹。首先使用改进混合A*在时空范围内进行轨迹粗搜索获得初始轨迹,然后以初始轨迹为参考构建可行驶时空走廊,并综合考虑车辆动力学和轨迹连续性约束等条件,使用数值优化的方法进一步平滑初始轨迹。选取换道超车和旁车切入两类典型复杂动态场景进行仿真测试,结果表明,所提时空联合规划方法相较于传统时空解耦规划方法更加灵活、规划结果更加合理,同时具有较好的计算实时性。

关键词: 时空联合规划, 改进混合A*, 时空走廊, 数值优化

Abstract:

Motion planning is the critical module of trajectory generation in autopilot system. The existing motion planning mostly adopts path-velocity decomposition method, which is easy to fall into trajectory suboptimal in complex dynamic scenarios. In this paper, a spatio-temporal joint motion planning method based on the combination of search and numerical optimization is proposed to solve the drivable trajectory directly. Firstly, the improved hybrid A* is used to search for the initial rough trajectory in the spatio-temporal range. Secondly, a drivable spatio-temporal corridor is constructed based on the initial trajectory, and considering vehicle dynamics and trajectory continuity constraints, the numerical optimization method is used to further smooth the initial trajectory. Finally, two typical complex dynamic scenarios of lane change overtaking and side-vehicle cut-in are selected for simulation test. The results show that the proposed planning method is more flexible and more reasonable than the traditional spatio-temporal decoupling planning method, and has better real-time computing performance.

Key words: spatio-temporal joint planning, improved hybrid A*, spatio-temporal corridor, numerical optimization