汽车工程 ›› 2022, Vol. 44 ›› Issue (3): 330-339.doi: 10.19562/j.chinasae.qcgc.2022.03.004

所属专题: 智能网联汽车技术专题-规划&控制2022年

• • 上一篇    下一篇

自动驾驶车辆的平行泊车轨迹规划

胡杰(),张敏超,徐文才,陈瑞楠,钟鑫凯,朱令磊   

  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.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:2021-10-21 修回日期:2021-12-08 出版日期:2022-03-25 发布日期:2022-03-25
  • 通讯作者: 胡杰 E-mail:auto_hj@163.com
  • 基金资助:
    湖北省技术创新专项(2019AEA169);湖北省科技重大专项(2020AAA001)

Parallel Parking Trajectory Planning for Autonomous Vehicles

Jie Hu(),Minchao Zhang,Wencai Xu,Ruinan Chen,Xinkai Zhong,Linglei Zhu   

  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.Hubei Technology Research Center of New Energy and Intelligent Connected Vehicle Engineering,Wuhan  430070
  • Received:2021-10-21 Revised:2021-12-08 Online:2022-03-25 Published:2022-03-25
  • Contact: Jie Hu E-mail:auto_hj@163.com

摘要:

根据对自动驾驶车辆的平行泊车场景的分析,提出一种基于采样的自动驾驶车辆平行泊车轨迹规划方法。该方法把自动驾驶车辆平行泊车的轨迹规划解耦成路径规划和速度规划。通过对泊车起始点区域采样,生成一系列曲率连续、满足路径约束的泊车路径曲线,利用多目标评价函数选取最优的泊车路径。然后,在最优泊车路径基础上,通过对时间采样选取时间最短、满足约束的S-t曲线生成泊车轨迹。最后,通过仿真和实车试验验证了该方法的可行性和有效性,成功实现自动驾驶车辆的平行泊车。

关键词: 自动驾驶, 平行泊车, 轨迹规划, 有序采样规划

Abstract:

Based the analysis on the parallel parking scenes of autonomous vehicles, a parallel parking trajectory planning method based on sampling is proposed, which decouples the parallel parking trajectory planning of autonomous vehicles into path planning and speed planning. By sampling the parking starting point region, a series of parking path curves with continuous curvature and meeting the path constraint are generated, and the optimal parking path is selected by using multi-objective evaluation function. Then on the basis of the optimal parking path, the S-t curve with the shortest selecting time and meeting the constraint is selected by time sampling to generate the trajectory. Finally, simulation and real vehicle test verify the feasibility and effectiveness of the method proposed and the parallel parking of autonomous vehicles is successfully realized.

Key words: autonomous driving, parallel parking, trajectory planning, orderly-sampling-based planning