汽车工程 ›› 2023, Vol. 45 ›› Issue (3): 350-360.doi: 10.19562/j.chinasae.qcgc.2023.03.002

所属专题: 智能网联汽车技术专题-规划&决策2023年

• • 上一篇    下一篇

引入必经点约束的智能汽车全局路径规划

胡杰(),朱琪,陈锐鹏,张敏超,张志豪,刘昊岩   

  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.新能源与智能网联车湖北工程技术研究中心,武汉  430070
  • 收稿日期:2022-08-04 修回日期:2022-09-04 出版日期:2023-03-25 发布日期:2023-03-22
  • 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)

Global Path Planning of Intelligent Vehicle with Must-Pass Nodes

Jie Hu(),Qi Zhu,Ruipeng Chen,Minchao Zhang,Zhihao Zhang,Haoyan Liu   

  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.Hubei Technology Research Center of New Energy and Intelligent Connected Vehicle Engineering,Wuhan  430070
  • Received:2022-08-04 Revised:2022-09-04 Online:2023-03-25 Published:2023-03-22
  • Contact: Jie Hu E-mail:auto_hj@163.com

摘要:

目前对于智能车全局路径规划的研究多数只针对从起点到终点的情况。针对该问题,本文中融合改进A*和模拟退火算法,设计了一种引入必经点约束的全局路径规划算法。首先,基于A*算法计算关键节点间的最短路径并保存。然后,基于启发式算法中的模拟退火算法对过必经节点的全局路径进行迭代随机优化。接着,基于真实高精度地图对算法的有效性以及时间复杂度进行实验分析。结果表明,设计的算法在求解质量和求解速度方面都有较好的表现。最后,通过实车实验,进一步验证了算法的有效性和适应性。

关键词: 智能汽车, 全局路径规划, 必经节点, A*算法, 模拟退火算法

Abstract:

At present, most of the research on the global path planning of intelligent vehicles only focuses on the situation from the beginning to the end. To solve this problem, this paper combines the improved A* and simulated annealing algorithm, and designs a global path planning algorithm that introduces in the constraint of must-pass nodes. Firstly, the shortest path between key nodes is calculated and saved based on the A* algorithm. Then, based on the simulated annealing algorithm in the heuristic algorithm, the global path through the must-pass nodes is iteratively and randomly optimized. Then, the validity and time complexity of the algorithm are tested and analyzed based on the real high-precision map. The results show that the designed algorithm has good performance in solving speed and solving quality. Finally, the effectiveness and adaptability of the algorithm are further verified by the real vehicle test.

Key words: intelligent vehicle, global path planning, must-pass nodes, A* algorithm, simulated annealing algorithm