智慧交通系统

基于曲线组合与数值优化的狭窄通道平行泊车路径规划方法

  • 程国柱 ,
  • 薛道安 ,
  • 顾爽
展开
  • 东北林业大学 土木与交通学院,黑龙江 哈尔滨 150040
程国柱(1977—),男,教授,博士生导师,主要从事智能交通系统研究。E-mail: guozhucheng@126.com
顾爽(1994—),女,博士,讲师,主要从事交通运输规划与管理研究。E-mail: s.gu@nefu.edu.cn

收稿日期: 2024-12-13

  网络出版日期: 2025-07-01

基金资助

东北林业大学中央高校基本科研业务费专项资金项目(2572023CT21);黑龙江省重点研发计划项目(JD22A014)

Path Planning Method Integrating Curve Combination and Numerical Optimization for Parallel Parking on Narrow Road

  • CHENG Guozhu ,
  • XUE Daoan ,
  • GU Shuang
Expand
  • School of Civil Engineering and Transportation,Northeast Forestry University,Harbin 150040,Heilongjiang,China
程国柱(1977—),男,教授,博士生导师,主要从事智能交通系统研究。E-mail: guozhucheng@126.com

Received date: 2024-12-13

  Online published: 2025-07-01

Supported by

the Key Research and Development Program of Heilongjiang Province(JD22A014)

摘要

针对城市狭窄通道场景中平行泊车时存在的路径曲率突变、碰撞风险高及多次调整等问题,该文提出一种基于曲线组合与数值优化的三段式单步路径规划方法,以优化车辆的转向性能与动态避障能力,提升泊车效率和安全性。首先,基于圆弧与回旋曲线的曲率特性,设计CAC(回旋曲线‒圆弧‒回旋曲线)与CC(回旋曲线‒回旋曲线)两类曲线组合;然后,将泊车过程逆向化,采用CAC曲线组合设计终点段路径,再构建基于CC曲线组合的约束优化模型来规划起点段路径,并引入五次多项式曲线设计中间段路径;最后,采用Matlab在拟可行区域内进行多工况仿真试验。结果表明:该方法能够在通道宽度仅为3 m的狭窄场景中规划出无碰撞、曲率连续的可行路径,且占用的通道较窄;相较于五次多项式曲线和“圆弧‒回旋曲线‒直线”方法,该方法在路径平滑性、避障能力及空间利用率等方面均具有显著优势;模型预测控制跟踪实验显示,车辆能够精准跟踪规划路径且前轮转角连续变化,验证了该方法的有效性。所提出的三段式单步路径规划方法为狭窄通道场景中的平行泊车提供了高效、安全的解决方案,可提高泊车效率,从而有效缓解路边泊车造成的交通阻塞,对提升城市交通效率具有实际意义。

本文引用格式

程国柱 , 薛道安 , 顾爽 . 基于曲线组合与数值优化的狭窄通道平行泊车路径规划方法[J]. 华南理工大学学报(自然科学版), 2025 , 53(11) : 77 -89 . DOI: 10.12141/j.issn.1000-565X.240581

Abstract

To address the challenges of abrupt curvature changes, high collision risks, and repeated adjustments in parallel parking within narrow urban passages, this study proposes a three-segment one-step path planning method integrating curve combination and numerical optimization to enhance vehicle’s steering performance and dynamic obstacle avoidance capabilities, and to improve the parking efficiency and safety. Firstly, based on the curvature characteristics of arcs and spiral curves, two types of curve combinations, namely CAC (Clothoid Curve-Arc-Clothoid Curve) and CC (Clothoid Curve-Clothoid Curve), are designed. Secondly, the parking process is reversed, and the CAC curve combination is used to design the path of the end section. Then, a constrained optimization model based on the CC curve combination is constructed to plan the path of the starting section, and the middle section path is designed by introducing the quintic polynomial curve. Finally, multi-condition simulation tests are carried out in the quasi-feasible area through Matlab. The results show that the proposed method can plan a collision-free and continuously curved feasible path in a narrow scene with a channel width of only 3 meters, without occupying wide channel. Comparative analysis reveals significant advantages of the proposed method over quintic polynomial curve and arc-clothoid curve-straight methods in terms of path smoothness, obstacle avoidance and space utilization efficiency. Model predictive control validation confirms that the vehicle adopting the proposed method is of precise path tracking performance with continuous front-wheel steering angle changes. The proposed three-segment one-step path planning method provides an efficient and safe solution to narrow-space parallel parking, and effectively improves the parking efficiency, thus alleviating road congestion caused by roadside parking operations and improving urban traffic efficiency.

参考文献

[1] 张家旭,赵健,施正堂,等 .基于回旋曲线的平行泊车路径规划和跟踪控制[J].吉林大学学报(工学版)202050(6):2247-2257.
  ZHANG Jia-xu, ZHAO Jian, SHI Zheng-tang,et al .Path planning and tracking control for parallel parking based on clothoid curve[J].Journal of Jilin University (Engineering and Technology Edition)202050(6):2247-2257.
[2] YU L, CAI Y, FENG X,et al .Parallel parking path planning and tracking control based on simulated annealing algorithm[J].International Journal of Automotive Technology202425(4):867-880.
[3] CAI L, GUAN H, ZHOU Z,et al .Parking planning under limited parking corridor space[J].IEEE Transactions on Intelligent Transportation Systems202324(2):1962-1981.
[4] 胡杰,朱令磊,陈瑞楠,等 .狭小车位平行泊车路径规划方法研究[J].汽车工程202244(7):1040-1048.
  HU Jie, ZHU Linglei, CHEN Ruinan,et al .Research on parallel parking path planning method for narrow parking space[J].Automotive Engineering202244(7):1040-1048.
[5] 刘平,陈卓,刘明杰,等 .阶段约束下Gauss配点离散化平行车位自动泊车轨迹规划[J].汽车工程202345(7):1163-1173.
  LIU Ping, CHEN Zhuo, LIU Mingjie,et al .Gauss allocation points parameterization parallel automatic parking trajectory planning for vehicle under multi-stage constraints[J].Automotive Engineering202345(7):1163-1173.
[6] 陈晓明,李柏,范丽丽,等 .基于半空间约束理论的自动泊车高性能轨迹优化方法[J].机械工程学报202460(10):273-288.
  CHEN Xiaoming, LI Bai, FAN Lili,et al .High-performance trajectory optimization for automated parking via half-space constraining theory[J].Journal of Mechanical Engineering202460(10):273-288.
[7] 秦东晨,张文灿,王婷婷,等 .受限泊车通道下自动驾驶平行泊车的路径规划方法[J].郑州大学学报(工学版)202445(5):1-7.
  QING Dongchen, ZHANG Wencan, WANG Tingting,et al .Path planning method for automated parallel parking in restricted parking lanes[J].Journal of Zhengzhou University (Engineering Science)202445(5):1-7.
[8] 任秉韬,王淅淅,邓伟文,等 .基于混合A*和可变半径RS曲线的自动泊车路径优化方法[J].中国公路学报202235(7):317-327.
  REN Bing-tao, WANG Xi-xi, DENG Wei-wen,et al .Path optimization algorithm for automatic parking based on hybrid A* and Reeds-Shepp curve with variable radius[J].China Journal of Highway and Transport202235(7):317-327.
[9] 曹彦博,颜京才,李旭升,等 .基于改进混合A*算法的自动泊车系统路径搜索方法[J].汽车技术2023(6):37-41.
  CAO Yanbo, YAN Jingcai, LI Xusheng,et al .A method of path search for automatic parking system based on improved hybrid A* algorithm[J].Automobile Technology2023(6):37-41.
[10] 胡杰,张敏超,徐文才,等 .自动驾驶车辆的平行泊车轨迹规划[J].汽车工程202244(3):330-339.
  HU Jie, ZHANG Minchao, XU Wencai,et al .Parallel parking trajectory planning for autonomous vehicles[J].Automotive Engineering202244(3):330-339.
[11] 姚智龙,张小俊,王金刚 .改进Bi-RRT*算法的自动泊车路径规划[J].机械科学与技术202443(6):1063-1071.
  YAO Zhilong, ZHANG Xiaojun, WANG Jingang .Automatic parking path planning with improved Bi-RRT* algorithm[J].Mechanical Science and Technology for Aerospace Engineering202443(6):1063-1071.
[12] 张家旭,刘晔,郭崇,等 .基于批处理先验知识树的自主代客泊车路径规划[J].华中科技大学学报(自然科学版)202149(9):77-82.
  ZHANG Jiaxu, LIU Ye, GUO Chong,et al .Autonomous valet parking path planning based on batch informed tree[J].Journal of Huazhong University of Science and Technology (Nature Science Edition)202149(9):77-82.
[13] SUN Hongwei, CHEN Hui, SONG Shaoyu .A motion planning method based on reinforcement learning for automatic parallel parking in small slot[J].Automobile Technology2021(9):17-26.
  孙宏伟,陈慧,宋绍禹 .一种基于强化学习的小库位自动平行泊车运动规划方法[J].汽车技术2021(9):17-26.
[14] ZHANG J, CHEN H, SONG S,et al .Reinforcement learning-based motion planning for automatic parking system[J].IEEE Access20208:154485-154501.
[15] CHAI R, LIU D, LIU T,et al .Deep learning-based trajectory planning and control for autonomous ground vehicle parking maneuver[J].IEEE Transactions on Automation Science and Engineering202320(3):1633-1647.
[16] 程国柱,冯思鹤,冯天军 .占用车行道的路内停车泊位设置条件[J].吉林大学学报(工学版)201949(6):1858-1864.
  CHENG Guo-zhu, FENG Si-he, FENG Tian-jun .Setting condition of on-street parking space occupied vehicle lane[J].Journal of Jilin University (Engineering and Technology Edition)201949(6):1858-1864.
文章导航

/