一种面向泊车场景智能车辆轨迹规划方法

doi:10.16183/j.cnki.jsjtu.2021.443

上海交通大学学报 ›› 2023, Vol. 57 ›› Issue (3): 345-353.doi: 10.16183/j.cnki.jsjtu.2021.443

所属专题：《上海交通大学学报》2023年“电子信息与电气工程”专题

一种面向泊车场景智能车辆轨迹规划方法

林淳, 贺越生(), 方兴其, 王春香

上海交通大学自动化系,上海 200240

收稿日期:2021-11-03 接受日期:2022-01-11 出版日期:2023-03-28 发布日期:2023-03-30
通讯作者: 贺越生,助理研究员;E-mail:heyuesh@sjtu.edu.cn.
作者简介:林淳(1997-),硕士生,主要研究方向为机器人.
基金资助:
国家自然科学基金(61873165);国家自然科学基金(U1764264)

A Method for Autonomous Driving Trajectory Planning in Parking Environments

LIN Chun, HE Yuesheng(), FANG Xingqi, WANG Chunxiang

Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2021-11-03 Accepted:2022-01-11 Online:2023-03-28 Published:2023-03-30

摘要/Abstract

摘要：

局部轨迹规划是自主代客泊车系统的关键技术之一,在该场景下,现有智能车辆的局部轨迹规划方法存在规划耗时长、曲率不连续、安全性不足等问题.针对该类问题,提出一种面向泊车场景的智能车辆轨迹规划方法.该方法通过改进混合A^*算法的解析扩展以及引入风险函数,提升了初始路径搜索的实时性和安全性.进一步,结合初始路径以及二次规划方法实现路径平滑和速度规划,最终完成轨迹生成.仿真实验表明,所提方法能够提升智能车辆轨迹规划实时性、平滑性以及安全性,并且在实车试验上验证所提方法在实际泊车场景的可行性.

关键词: 智能车辆, 泊车场景, 轨迹规划, 混合A^*算法, 二次规划

Abstract:

Local trajectory planning is one of the key technologies of the autonomous valet parking system. In this scenario, there exist problems such as long planning time, discontinuous curvature, and insufficient safety in local trajectory planning methods for intelligent vehicles. Aimed at these problems, this paper proposes a trajectory planning method for intelligent vehicles in parking scenarios. This method improves the real-time performance and security of the initial path search by improving the analytic expansions of the hybrid A^* algorithm and introducing the risk function. Further, according to the initial path, the quadratic programming method is used to realize path smoothing and speed planning. Finally, the trajectory generation is completed. Simulation experiments show that the method can improve the real-time, smoothness, and safety of intelligent vehicle trajectory planning. In addition, in actual parking environment, the feasibility of the method is verified in real-world vehicle experiments.

Key words: autonomous vehicles, parking environments, trajectory planning, hybrid A^* algorithm, quadratic programming

中图分类号:

TP242.6

林淳, 贺越生, 方兴其, 王春香. 一种面向泊车场景智能车辆轨迹规划方法[J]. 上海交通大学学报, 2023, 57(3): 345-353.

LIN Chun, HE Yuesheng, FANG Xingqi, WANG Chunxiang. A Method for Autonomous Driving Trajectory Planning in Parking Environments[J]. Journal of Shanghai Jiao Tong University, 2023, 57(3): 345-353.

图/表 12

图1

图2

表1

图3

表2

表3

图4

图5

表5

表6

图6

图7

参考文献 17

[1]	胡兵, 杨明, 郭林栋, 等. 基于地面快速鲁棒特征的智能车全局定位方法[J]. 上海交通大学学报, 2019, 53(2): 203-208.
	HU Bing, YANG Ming, GUO Lindong, et al. Global localization for intelligent vehicles using ground SURF[J]. Journal of Shanghai Jiao Tong University, 2019, 53(2): 203-208.
[2]	WERLING M, ZIEGLER J, KAMMEL S, et al. Optimal trajectory generation for dynamic street scenarios in a Frenét Frame[C]// 2010 IEEE International Conference on Robotics and Automation. Anchorage, AK, USA: IEEE, 2010: 987-993.
[3]	CHEN S T, JIAN Z Q, HUANG Y H, et al. Autonomous driving: Cognitive construction and situation understanding[J]. Science China Information Sciences, 2019, 62(8): 1-27.
[4]	MA L, YANG J, ZHANG M. A two-level path planning method for on-road autonomous driving[C]// 2012 Second International Conference on Intelligent System Design and Engineering Application. Sanya, China: IEEE, 2012: 661-664.
[5]	MAEKAWA T, NODA T, TAMURA S, et al. Curvature continuous path generation for autonomous vehicle using B-spline curves[J]. Computer-Aided Design, 2010, 42(4): 350-359. doi: 10.1016/j.cad.2009.12.007 URL
[6]	PIVTORAIKO M, KNEPPER R A, KELLY A. Differentially constrained mobile robot motion planning in state lattices[J]. Journal of Field Robotics, 2009, 26(3): 308-333. doi: 10.1002/rob.v26:3 URL
[7]	DOLGOV D, THRUN S, MONTEMERLO M, et al. Path planning for autonomous vehicles in unknown semi-structured environments[J]. The International Journal of Robotics Research, 2010, 29(5): 485-501. doi: 10.1177/0278364909359210 URL
[8]	KUWATA Y, FIORE G A, TEO J, et al. Motion planning for urban driving using RRT[C]// 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems. Nice, France: IEEE, 2008: 1681-1686.
[9]	BANZHAF H, NIENHÜSER D, KNOOP S, et al. The future of parking: A survey on automated valet parking with an outlook on high density parking[C]// 2017 IEEE Intelligent Vehicles Symposium. Los Angeles, CA, USA: IEEE, 2017: 1827-1834.
[10]	王旭东, 王春香, 杨明, 等. 一种基于环视相机的自动泊车方法[J]. 上海交通大学学报, 2013, 47(7): 1077-1081.
	WANG Xudong, WANG Chunxiang, YANG Ming, et al. Automatic parking based on bird’s eye view cameras[J]. Journal of Shanghai Jiao Tong University, 2013, 47(7): 1077-1081.
[11]	LIN L T, ZHU J J. Path planning for autonomous car parking[C]// Proceedings of ASME 2018 Dynamic Systems and Control Conference. Atlanta, Georgia, USA: ASME, 2018: 1-10.
[12]	MOON J, BAE I, CHA J G, et al. A trajectory planning method based on forward path generation and backward tracking algorithm for Automatic Parking Systems[C]// 17th International IEEE Conference on Intelligent Transportation Systems. Qingdao, China: IEEE, 2014: 719-724.
[13]	齐尧, 徐友春, 李华, 等. 一种基于改进混合A^的智能车路径规划算法[J]. 军事交通学院学报*, 2018, 20(8): 85-90.
	QI Yao, XU Youchun, LI Hua, et al. Hybrid A^* algorithm-based path planning for intelligent vehicle[J]. Journal of Military Transportation University, 2018, 20(8): 85-90.
[14]	陈鑫鹏, 徐彪, 胡满江, 等. 一种基于等步长分层拓展的混合A^路径规划方法[J]. 控制与信息技术*, 2021(1): 17-22.
	CHEN Xinpeng, XU Biao, HU Manjiang, et al. A hybrid-A^* path planning method based on equal step hierarchical expansion[J]. Control and Information Technology, 2021(1): 17-22.
[15]	ZHANG S Y, CHEN Y, CHEN S T, et al. Hybrid A^-based curvature continuous path planning in complex dynamic environments[C]// 2019 IEEE Intelligent Transportation Systems Conference*. Auckland, New Zealand: IEEE, 2019: 1468-1474.
[16]	MIZUNO N, OHNO K, HAMADA R, et al. Enhanced path smoothing based on conjugate gradient descent for firefighting robots in petrochemical complexes[J]. Advanced Robotics, 2019, 33(14): 687-698. doi: 10.1080/01691864.2019.1632221 URL
[17]	ZHANG X J, LINIGER A, SAKAI A, et al. Autonomous parking using optimization-based collision avoidance[C]// 2018 IEEE Conference on Decision and Control. Miami, FL, USA: IEEE, 2018: 4327-4332.

参数	取值
位置离散分辨率/m	0.5
角度离散分辨率/(°)	7.5
前轮转角离散数	5.0
步长/m	0.8

算法	路径长度/m	拓展节点	档位切换	搜索时间/ms
文献[15]算法	13.5	1769	3	84
本文算法	13.7	478	3	18

参数	取值
离散状态点数	50
一阶差分权重	1
最大曲率	5
二阶差分权重	1000

实验组	平滑前的J_κ	本文方法的J_κ	文献[16]的J_κ
实验一	0.01707	0.01383	0.01372
实验二	0.02042	0.01434	0.01545

参数	取值
离散状态点数	24
最大速度/(m·s^-1)	1.0
最大加速度/(m·s^-2)	1.0
最大加加速度/(m·s^-3)	0.5
距离权重	10000
加速度权重	10
加加速度权重	10

一种面向泊车场景智能车辆轨迹规划方法

A Method for Autonomous Driving Trajectory Planning in Parking Environments

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 17

相关文章 11

编辑推荐

Metrics

本文评价

[1]	张凯波1，陈丽1，董琦2. 输入受限的超冗余移动医疗机械臂混合控制[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(3): 348-359.
[2]	黄宇昊, 韩超, 赵明辉, 杜乾坤, 王石刚. 考虑安全飞行通道约束的无人机飞行轨迹多目标优化策略[J]. 上海交通大学学报, 2022, 56(8): 1024-1033.
[3]	胡益恺, 王春香, 杨明. 智能车辆决策方法研究综述[J]. 上海交通大学学报, 2021, 55(8): 1035-1048.
[4]	李岳明，王小平，张军军，曹建，张英浩. 基于改进二次规划算法的X舵智能水下机器人控制分配[J]. 上海交通大学学报, 2020, 54(5): 524-531.
[5]	王树凤，张钧鑫，张俊友. 基于人工势场和虚拟领航者的智能车辆编队控制[J]. 上海交通大学学报, 2020, 54(3): 305-311.
[6]	黄鲁豫, 徐胜利, 张明环. 基于序列二次规划法的导弹鸭舵/尾舵复合控制技术研究[J]. 空天防御, 2019, 2(3): 38-43.
[7]	杨荣武,许劲松,王鑫. 船舶自主避碰的慎思型轨迹规划[J]. 上海交通大学学报, 2019, 53(12): 1411-1419.
[8]	袁德虎,金惠良，孟国香，冯正进. 机器人yoyo轨迹规划与控制[J]. 上海交通大学学报（自然版）, 2010, 44(07): 940-0945.
[9]	王宣银，吴乐彬. 广义负载模拟器的广义力误差最小轨迹规划[J]. 上海交通大学学报（自然版）, 2010, 44(07): 887-0891.
[10]	伍舜喜，杨明. 基于自然柱状特征地图的智能车定位[J]. 上海交通大学学报（自然版）, 2008, 42(10): 1745-1748.
[11]	杨洪杰, 葛修润, 王建华, 傅德明. 序列二次规划（SQP)算法在三维下限分析中的应用[J]. 上海交通大学学报, 2004, 38(06): 992-995.