基于OnSite平台的自动泊车测评工具的研究与设计

doi:10.3969/j.issn.1674-8484.2025.02.017

摘要/Abstract

摘要：

为了完善“公开自然驾驶智能汽车仿真测试环境（OnSite）”平台功能，提出了一种自动泊车的测评工具。该工具采用实车数据采集与建模还原的场景构建方法，依据行业标准与停车位数据，建立了更为全面的测试场景库。提出了一种以完成率为核心，兼顾安全性、效率与精准度的多维评价体系。该测评工具经硬件在环仿真，并与CARLA仿真平台及实车测试结果对比。通过分析第2届OnSite自动驾驶算法挑战赛泊车测试前10名队伍的得分，讨论了未来测评工具及OnSite平台发展。结果表明：该工具不仅为自动泊车功能优化提供科学依据，也可为自动驾驶测评工具研发提供参考。

关键词: 自动驾驶, 仿真测试, 自动泊车, 测试评价, 测评工具, 场景生成

Abstract:

An automated parking evaluation tool was developed to enhance the functionality of the platform OnSite (Open Naturalistic Simulation and Testing Environment) for autonomous driving. This tool used a scenario construction method based on real vehicle data collection and modeling reconstruction. A more comprehensive test scenario library was established according to industry standards and parking space data. A multidimensional evaluation system was proposed, focusing on completion rate while considering safety, efficiency, and accuracy. The evaluation tool underwent hardware-in-the-loop simulation and was compared with results from the CARLA simulation platform and real vehicle tests. Scores of the top 10 teams in the parking test of the 2nd OnSite Autonomous Driving Algorithm Challenge were analyzed to discuss the future development of the evaluation tool and the OnSite platform. The results show that the tool provides a scientific basis for optimizing automated parking functions and serves as a reference for developing autonomous driving evaluation tools.

Key words: autonomous driving, simulation testing, automated parking, testing and evaluation, evaluation tool, scenario generation

中图分类号:

U467.1

杨俊儒, 郑四发, 许述财, 田野, 孙剑, 孙川, 李浩然. 基于OnSite平台的自动泊车测评工具的研究与设计[J]. 汽车安全与节能学报, 2025, 16(2): 334-343.

YANG Junru, ZHENG Sifa, XU Shucai, TIAN Ye, SUN Jian, SUN Chuan, LI Haoran. Design and research of an automated parking evaluation tool based on the OnSite platform[J]. Journal of Automotive Safety and Energy, 2025, 16(2): 334-343.

图/表 13

参考文献 23

[1]	李平飞, 金思雨, 胡文浩, 等. 用于自动驾驶仿真测试的车—车事故场景复杂度评价[J]. 汽车安全与节能学报, 2022, 13(4): 697-704.
	LI Pingfei, JIN Siyu, HU Wenhao, et al. Complexity evaluation of vehicle-vehicle accident scenarios for autonomous driving simulation tests[J]. J Autom Safe Energ, 2022, 13(4): 697-704. (in Chinese)
[2]	Steimle M, Weber N, Maurer M. Toward generating sufficiently valid test case results: A method for systematically assigning test cases to test bench configurations in a scenario-based test approach for automated vehicles[J]. IEEE Access, 2022, 10: 6260-6285.
[3]	张培兴. 基于场景的自动驾驶汽车虚拟仿真加速测试与评价方法研究[D]. 长春: 吉林大学, 2023.
	ZHANG Peixin. Research on scenario-based accelerated simulation test and evaluation method for automated vehicle[D]. Changchun: Jilin University, 2023. (in Chinese)
[4]	王之中, 皮大伟, 吴兵. 国家自然科学基金委员会交通与运载工程学科2021年度管理工作综述与未来工作展望[J]. 交通运输工程学报, 2021, 21(6): 1-7.
	WANG Zhizhong, PI Dawei, WU Bing. Management summary of transportation and vehicle engineering discipline in NSFC: review and prospects in 2021[J]. J Traf Transport Eng, 2021, 21(6): 1-7. (in Chinese)
[5]	王之中, 田野, 孙剑, 等. 自动驾驶测试公共服务平台建设与思考[J]. 交通运输工程学报, 2023, 23(6): 1-9.
	WANG Zhizhong, TIAN Ye, SUN Jian, et al. Construction and rethinking on public service platform for autonomous driving test[J]. J Traf Transport Eng, 2023, 23(6): 1-9. (in Chinese)
[6]	赵祥模国家重点研发计划团队. 自动驾驶测试与评价技术研究进展[J]. 交通运输工程学报, 2023, 23(6): 10-77.
	ZHAO Xiangmo’s team supported by the National Key Research and Development Program of China (2021YFB2501200). Research progress in testing and evaluation technologies for autonomous driving[J]. J Traf Transport Eng, 2023, 23(6): 10-77. (in Chinese)
[7]	孙剑, 黄䶮, 田野, 等. 自动驾驶测试公共服务平台构建技术及应用[J]. 中国公路学报, 2024, 37(8): 248-258.
	SUN Jian, HUANG Yan, TIAN Ye, et al. Development and Application of a Public Service Platform for Autonomous Driving Testing[J]. China J Highw Transport, 2024, 37(8): 248-258. (in Chinese)
[8]	熊璐, 吴建峰, 冯天悦, 等. 面向自动驾驶逻辑场景评价的危险域识别方法[J]. 中国公路学报, 2024, 37(5): 371-382.
	XIONG Lu, WU Jianfeng, FENG Tianyue, et al. Danger field identification method for evaluation of autonomous driving logic scenarios[J]. China J Highw Transport, 2024, 37(5): 371-382. (in Chinese)
[9]	赵树廉, 来飞, 李克强, 等. 基于数字孪生技术的智能汽车测试方法研究[J]. 汽车工程, 2023, 45(1): 42-51.
	ZHAO Shulian, LAI Fei, LI Keqiang, et al. Research on intelligent vehicle test method based on digital twin technology[J]. Autom Engineering, 2023, 45(1): 42-51. (in Chinese)
[10]	赵锦涛, 李亮, 薛仲瑾, 等. 基于混合A星的停车场内巡航分层运动规划方法[J]. 机械工程学报, 2023, 59(24): 290-298.
	ZHAO Jintao, LI Liang, XUE Zhongjin, et al. Hierarchical motion planning method based on hybrid A-star for cruising in parking area[J]. J Mech Engi, 2023, 59(24): 290-298. (in Chinese)
[11]	修国涛, 谢辉, 宋康, 等. 基于驾驶员经验的无人驾驶车辆平行泊车操作模型[J]. 汽车安全与节能学报, 2023, 14(2): 191-201.
	XIU Guotao, XIE Hui, SONG Kang, et al. Parallel parking operation model for driverless vehicles based on driver experiences[J]. J Autom Safe Energ, 2023, 14(2): 191-201. (in Chinese)
[12]	Kneissl M, Madhusudhanan A K, Molin A, et al. A multi-vehicle control framework with application to automated valet parking[J]. IEEE Trans Intel Transport Syst, 2021, 22(9): 5697-5707.
[13]	ZHANG Jiawei, LI Zhiheng, LI Li, et al. A bi-level cooperative operation approach for AGV based automated valet parking[J]. **Transport Res Part C: Emerg Tech, 2021, 128**: 103140.
[14]	HUANG Jiang, YANG Yifan, DING Dailin, et al. Automatic parking paths planning research based on scattering points six-degree polynomial and easement curve[J]. **Proc Inst of Mech Engi, Part D: J Autom Engi, 2023, 237**(2-3): 529-543.
[15]	王元民, 王亚飞, 秦文刚, 等. 基于SMPA的半挂车自动泊车运动规划方法研究[J]. 汽车工程, 2024, 46(4): 691-702.
	WANG Yuanmin, WANG Yafei, QIN Wengang, et al. Study on automatic parking motion planning method for tractor-semitrailer based on SMPA[J]. Autom Engineering, 2024, 46(4): 691-702. (in Chinese)
[16]	王永胜, 罗禹贡, 黄晨, 等. 基于拓扑地图的自主泊车路径协调与优化策略[J]. 中国公路学报, 2021, 34(1): 177-187.
	WANG Yongsheng, LUO Yugong, HUANG Chen, et al. A topological map-based path coordination and optimization strategy for autonomous parking[J]. China J Highw Transport, 2021, 34(1): 177-187. (in Chinese)
[17]	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, 2022, 35(7): 317-327.
	REN Bingtao, WANG Xixi, DENG Weiwen, et al. Path optimization algorithm for automatic parking based on hybrid A* and Reeds-Shepp curve with variable radius[J]. China J Highw Transport, 2022, 35(7): 317-327. (in Chinese)
[18]	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, 2024, 60(10): 273-288.
	CHEN Xiaoming, LI Bai, FAN Lili, et al. High-performance trajectory optimization for automated parking via half-space constraining theory[J]. J Mech Engi, 2024, 60(10): 273-288. (in Chinese)
[19]	马天飞, 李波, 朱冰, 等. 考虑大气条件影响的自动泊车系统超声波雷达建模[J]. 汽车工程, 2023, 45(9): 1646-1654.
	MA Tianfei, LI Bo, ZHU Bing, et al. Ultrasonic radar modeling of automatic parking system considering atmospheric conditions effect[J]. Autom Engineering, 2023, 45(9): 1646-1654. (in Chinese)
[20]	田杰, 叶青. 自动泊车发展现状及运动规划研究进展[J]. 科学技术与工程, 2024, 24(21): 8825-8836.
	TIAN Jie,YE Qing. Review of automatic parking and research progress of motion planning[J]. Sci Tech Engi, 2024, 24(21): 8825-8836. (in Chinese)
[21]	丁飞, 张楠, 李升波, 等. 智能网联车路云协同系统架构与关键技术研究综述[J]. 自动化学报, 2022, 48(12): 2863-2885.
	DING Fei, ZHANG Nan, LI Shengbo, et al. A survey of architecture and key technologies of intelligent connected vehicle-road-cloud cooperation system[J]. Acta Auto Sinica, 2022, 48(12): 2863-2885. (in Chinese)
[22]	王文佳, 侯忠生. 基于无模型自适应控制的自动泊车方案[J]. 控制与决策, 2022, 37(8): 2056-2066.
	WANG Wenjia, HOU Zhongsheng. Model-free adaptive control based automatic parking scheme[J]. Contr Dec, 2022, 37(8): 2056-2066. (in Chinese)
[23]	Dosovitskiy A, Ros G, Codevilla F, et al. CARLA: An open urban driving simulator[C]// Proc Annua Conf Robot Learn. PMLR, 2017, 78: 1-16.

车位类型	车位场景	自动泊车系统试验标准			本文研究团队
车位类型	车位场景	ISO 16787	GB/T 41630-2022	IVISTA-SM-IPI.PA-TP-A0-2023	本文研究团队
1 平行车位	1.1 双边界平行车位	●	●	●	●
	1.2 白色标线平行车位	●	●	●	●
	1.3 弯道平行车位				●
2 垂直车位	2.1 双边界垂直车位	●	●	●	●
	2.2 白色标线垂直车位	●	●	●	●
	2.3 左侧方柱垂直车位			●	●
	2.4 右侧方柱垂直车位				●
	2.5 两侧方柱垂直车位				●
3 斜向车位	3.1 双边界斜向车位			●	●
3 斜向车位	3.2 白色标线斜向车位			●	●

车位类型	车位场景	自动泊车系统试验标准			本文研究团队
车位类型	车位场景	ISO 16787	GB/T 41630-2022	IVISTA-SM-IPI.PA-TP-A0-2023	本文研究团队
1 平行车位	1.1 双边界平行车位	●	●	●	●
	1.2 白色标线平行车位	●	●	●	●
	1.3 弯道平行车位				●
2 垂直车位	2.1 双边界垂直车位	●	●	●	●
	2.2 白色标线垂直车位	●	●	●	●
	2.3 左侧方柱垂直车位			●	●
	2.4 右侧方柱垂直车位				●
	2.5 两侧方柱垂直车位				●
3 斜向车位	3.1 双边界斜向车位			●	●
3 斜向车位	3.2 白色标线斜向车位			●	●

评价内容	指标	分值	得分标准
1 泊车效率 (60分)	1.1 泊车路程	30分	20×(目标车位参考路程/实际行驶路程)，最低0分
1 泊车效率 (60分)	1.2 揉库次数	30分	揉库1次不扣分，每多1次扣2分，扣完为止
2 位置姿态 (40分)	2.1 停车位置	20分	车辆中心点与停车位中心点的距离偏差，每差2 cm 扣1分，扣完为止
2 位置姿态 (40分)	2.2 停车姿态	20分	车辆最终航向角与停车位航向角偏差，每差0.5° 扣2分，扣完为止

评价内容	指标	分值	得分标准
1 泊车效率 (60分)	1.1 泊车路程	30分	20×(目标车位参考路程/实际行驶路程)，最低0分
1 泊车效率 (60分)	1.2 揉库次数	30分	揉库1次不扣分，每多1次扣2分，扣完为止
2 位置姿态 (40分)	2.1 停车位置	20分	车辆中心点与停车位中心点的距离偏差，每差2 cm 扣1分，扣完为止
2 位置姿态 (40分)	2.2 停车姿态	20分	车辆最终航向角与停车位航向角偏差，每差0.5° 扣2分，扣完为止