吉林大学学报(工学版) ›› 2025, Vol. 55 ›› Issue (2): 456-467.doi: 10.13229/j.cnki.jdxbgxb.20240874

• 车辆工程·机械工程 • 上一篇    

自动驾驶汽车连续测试场景复杂度评估方法

朱冰1(),范天昕1,赵文博2,李伟男3,张培兴1()   

  1. 1.吉林大学 汽车底盘集成与仿生全国重点实验室,长春 130022
    2.国汽(北京)智能网联汽车研究院有限公司,北京 100176
    3.中国第一汽车集团股份有限公司研发总院,长春 130011
  • 收稿日期:2024-08-05 出版日期:2025-02-01 发布日期:2025-04-16
  • 通讯作者: 张培兴 E-mail:zhubing@jlu.edu.cn;zhangpeixing@jlu.edu.cn
  • 作者简介:朱冰(1982-),男,教授,博士. 研究方向:智能汽车技术. E-mail: zhubing@jlu.edu.cn
  • 基金资助:
    国家自然科学基金项目(U22A20247);中国博士后科学基金项目(2023M741354);国家资助博士后研究人员计划项目(GZC20230945)

Continuous test scenario complexity evaluation method for automated driving vehicles

Bing ZHU1(),Tian-xin FAN1,Wen-bo ZHAO2,Wei-nan LI3,Pei-xing ZHANG1()   

  1. 1.National Key Laboratory of Automotive Chassis Integration and Bionics,Jilin University,Changchun 130022,China
    2.China Intelligent and Connected Vehicles (Beijing) Research Institute Co. ,Ltd. ,Beijing 100176,China
    3.China First Automobile Corporation R&D Center,Changchun 130011,China
  • Received:2024-08-05 Online:2025-02-01 Published:2025-04-16
  • Contact: Pei-xing ZHANG E-mail:zhubing@jlu.edu.cn;zhangpeixing@jlu.edu.cn

摘要:

连续测试场景是自动驾驶汽车测试体系的重要内容,其测试公平性一直受到较多的争议。为此,本文提出一种自动驾驶汽车连续测试场景复杂度评估方法,以期解决测试场景公平性难题。基于六层场景模型建立场景要素重要性评估体系;分析场景要素与感知、决策、执行系统间的复杂度映射关系,建立自动驾驶系统层级的场景复杂度量化评价方法;建立系统影响传递权重系数,实现场景复杂度综合计算。搭建仿真交通环境对两种自动驾驶系统行驶过程复杂度进行计算,两车场景复杂度对比结果分别为1和0.765,与测试过程被测算法遭遇的场景难度趋势一致,证明了本文方法的有效性。

关键词: 车辆工程, 自动驾驶汽车, 连续测试场景, 场景复杂度

Abstract:

Continuous test scenario is an important content of automated driving vehicle scenario-based testing system, but its fairness has been disputed. For this reason, this paper proposes a real-time evaluation method for the continuous test scenario complexity of automated driving vehicle, with a view to solving the problem of test scenario fairness. Based on the six-layer scenario model, a scenario element importance assessment system is established; through analyzing the mapping relationship between scenario elements and perception, decision-making, and execution systems, a quantitative evaluation method of scenario complexity at the system layer is constructed; the impact transfer weighting coefficients of different system are calculated, which can be used to realize the comprehensive calculation of scenario complexity in real time. The traffic circle continuous test scenario is selected to analyze the scenario complexity of two black-box automated driving systems, the results of the scenario complexity of the two vehicles are 1 and 0.765, which are consistent with the scenario complexity encountered by the two tested systems in the test process. The results can prove the effectiveness of the method proposed in this paper.

Key words: automotive engineering, automated driving vehicle, continuous test scenario, scenario complexity

中图分类号: 

  • U461

图1

场景复杂度评估框架"

表1

场景要素分类表"

一级分类二级分类三级分类

静态

场景

要素

道路层道路类型
道路质量
车道数量
道路标线
……
交通设施层信号灯
标志牌
其他设施
……
临时操作层交通事故
临时停放
道路施工
……

动态

场景

要素

目标层机动车
非机动车
行人
……
天气要素自然环境层光照
……

图2

点云密度与相对距离的关系曲线图"

表2

天气要素影响系数分布 (%)"

天气要素

传感器类型

传感器类型
相机毫米波雷达激光雷达
光照10--
0--
5--
402530
704770
755380
20550
403280
606090
101050
252080
604090

图3

场景要素势场示意图"

图4

自动驾驶汽车可达域"

图5

自动驾驶汽车决策规划裕度示意图"

图6

自动驾驶子系统影响传递关系图"

图7

连续测试场景图"

表3

自动驾驶汽车综合性能评价指标表"

总指标层权重指标层权重系统A系统B
安全性0.48避障平均车速118.1914.89
效率0.16平均变道时间15.448.72
智能性0.07避障平均最小TTC0.348.4012.56
车道保持距离道路中线最大距离0.660.720.63
舒适性0.29纵向加速度最大值0.622.572.10
横向加速度最大值0.382.061.53

表4

场景要素评分表"

一级

分类

二级

分类

重要权重

系数

三级分类

重要权重

系数

属性特征评分
静态场景要素道路层0.1748道路类型0.356 53
道路质量0.113 61
车道数量0.265 02
道路标线0.265 01
交通设施层0.0828信号灯0.722 92
标志牌0.201 12
其他设施0.076 0-
临时操作层0.0667交通事故0.439 1-
临时停放0.318 7-
道路施工0.242 2-
动态场景要素目标层0.6757机动车0.128 83
非机动车0.260 94
行人0.610 33

图8

归一化自动驾驶汽车决策规划裕度图"

图9

自动驾驶汽车行驶路段对比图"

表5

要素-系统复杂度映射表"

复杂度系统A系统B
感知系统8.030 26.849 7
决策系统0.525 10.295 8
执行系统1.478 41.327 0

表6

自动驾驶汽车性能综合评价表"

评价项目系统A系统B
不考虑场景复杂度的评分0.840.94
场景相对复杂度10.765
考虑场景复杂度的评分0.840.72
1 赵祥模教授国家重点研发计划( 2021 YFB2501200 )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 Xiang-mo's team supported by the National Key Research and Development Program of China( 2021 YFB2501200). Research progress in testing and evaluation technologies for autonomous driving[J]. Journal of Traffic and Transportation Engineering, 2023, 23(6): 10-77.
2 朱冰, 张培兴, 赵健, 等. 基于场景的自动驾驶汽车虚拟测试研究进展[J].中国公路学报, 2019, 32(6): 1-19.
Zhu Bing, Zhang Pei-xing, Zhao Jian, et al. Review of scenario-based virtual validation methods for automated vehicles[J]. China Journal of Highway and Transport, 2019, 32(6): 1-19.
3 Shadrin S S, Ivanov A M, Makarova D A. Methods of parameter verification and scenario generation during virtual testing of highly automated and autonomous vehicles[C]∥Intelligent Technologies and Electronic Devices in Vehicle and Road Transport, New York, USA, 2022: 1-6.
4 Amirul I A B, Mohd A A, Mohd F M S. Synthesis of autonomous vehicle guideline for public road-testing sustainability[J]. Sustainability, 2022, 14(3): 1-18.
5 Dixit V V, Chand S, Nair D J. Autonomous vehicles: disengagements, accidents and reaction times[J]. Plos One, 2016, 11(12): 1-14.
6 王荣, 孙亚夫, 宋娟. 自动驾驶汽车道路测试场景评价方法与试验验证[J].汽车工程, 2021, 43(4): 620-628.
Wang Rong, Sun Ya-fu, Song Juan. Evaluation method and test verification of road test scenes for autonomous vehicles[J]. Automotive Engineering, 2021, 43(4): 620-628.
7 李江坤, 邓伟文, 任秉韬, 等. 一种智能汽车测试场景复杂度的评估方法[C]∥中国汽车工程学会年会论文集, 北京, 中国, 2020: 106-113.
8 董汉, 舒伟, 陈超, 等. 危险驾驶工况场景的复杂度评估方法研究[J].汽车工程, 2020, 42(6): 808-814.
Dong Han, Shu Wei, Chen Chao, et al. Research on complexity evaluation method of dangerous driving scenes[J]. Automotive Engineering, 2020, 42(6): 808-814.
9 Liu Y K, Hansen J H L. Towards complexity level classification of driving scenarios using environmental information[C]∥IEEE Intelligent Transportation Systems Conference, New York, USA, 2019: 810-819.
10 Kim I Y, Kang D Y, Jeong H. Method of evaluating multiple scenarios in a single simulation run for automated vehicle assessment[J]. Sensors, 2023, 23(19): 1-19.
11 Lu C R, Dong J, Houchin A. Incorporating the standstill distance and time headway distributions into freeway car-following models and an application to estimating freeway travel time reliability[J]. Journal of Intelligent Transportation Systems, 2021, 25(1): 21-40.
12 Winner H, Lemmer K, Form T, et al. Pegasus- first steps for the safe introduction of automated driving[C]∥Road Vehicle Automation 5, Heidelberg, Germany, 2019: 185-195.
13 Xu T F, Zhao P. Image motion-blur-based object's speed measurement using an interlaced scan image[J]. Measurement Science and Technology, 2010, 21(7): 1-10.
14 王战古. 不良天气条件下车辆检测方法研究[D]. 长春:吉林大学汽车工程学院, 2022.
Wang Zhan-gu. Research on vehicle detection method under adverse weather conditions[D]. Changchun: College of Automotive Engineering, Jilin University, 2022.
15 李鑫. 面向汽车智能驾驶的毫米波雷达建模与仿真研究[D]. 长春: 吉林大学汽车工程学院, 2020.
Li Xin. Research on modeling and simulation of millimeter wave radar for vehicle intelligent driving[D]. Changchun: College of Automotive Engineering, Jilin University, 2020.
16 赵轩. 基于路侧激光雷达的交通目标感知方法与实现[D].西安:西安工业大学电子信息工程学院, 2023.
Zhao Xuan.Roadside lidar-based traffic target sensing method and implementation[D]. Xi'an: College of Electronic Information Engineering, Xi'an Technological University, 2023.
17 葛平淑, 郭烈, 齐国栋, 等. 变光照环境下车道标识线的识别方法[J].激光与光电子学进展, 2020, 57(16): 1-6.
Ge Ping-shu, Guo Lie, Qi Guo-dong, et al. Lane marker line identification method in variable light environment[J]. Laser and Optoelectronics Progress, 2020, 57(16): 1-6.
18 蒋渊德, 孙朋朋, 秦孔建, 等. 雨雪天气对自动驾驶视觉图像质量的影响[J].中国公路学报, 2022, 35(3): 307-316.
Jiang Yuan-de, Sun Peng-peng, Qin Kong-jian, et al. Influence of rain and snow on autonomous vehicles' camera[J].China Journal of Highway and Transport, 2022, 35(3): 307-316.
19 Elizabeth E, Andrew B, Bani H N, et al. Experimental investigation of the effects of fog on optical camera-based VLC for a vehicular environment[C]∥15th International Conference on Telecommunications, New York, USA, 2019: 1-5.
20 Zang S Z, Ding M, Smith D, et al. The impact of adverse weather conditions on autonomous vehicles: how rain, snow, fog, and hail affect the performance of a self-driving car[J].IEEE Vehicular Technology Magazine, 2019, 14(2): 103-111.
21 白雪松, 邓伟文, 任秉韬, 等. 一种自动驾驶仿真场景要素的提取方法[J].汽车工程, 2021, 43(7): 1031-1036.
Bai Xue-song, Deng Wei-wen, Ren Bing-tao, et al. An extraction method of scenario elements for autonomous driving simulation[J].Automotive Engineering, 2021, 43(7): 1031-1036.
22 Keisuke Y, Naoki S, Ryo Y, et al. Automated driving recognition technologies for adverse weather conditions[J].IATSS Research, 2019, 43: 253-262.
23 孙朋朋, 赵祥模, 蒋渊德, 等. 降雨条件对车载激光雷达性能影响的试验研究[J].中国公路学报, 2022, 35(11): 318-328.
Sun Peng-peng, Zhao Xiang-mo, Jiang Yuan-de, et al. Experimental study of influence of rain on performance of automotive lidar[J]. China Journal of Highway and Transport, 2022, 35(11): 318-328.
24 何俊南, 姜京秀, 孙朋朋. 降雪环境对激光雷达性能的影响分析与试验研究[J]. 时代汽车, 2323, 12: 20-22.
He Jun-nan, Jiang Jing-xiu, Sun Peng-peng. Analysis and experimental research on the influence of lidar performance in snowfall environment[J]. Auto Time, 2323, 12: 20-22.
25 Kutila M, Pyykönen P, Holzhüter H, et al. Automotive lidar performance verification in fog and rain[C]∥21st International Conference on Intelligent Transportation Systems, New York, USA, 2018: 1695-1707.
26 Wang W, Wu L G, Li X, et al. An evaluation method for automated vehicles combining subjective and objective factors[J]. Machines, 2023, 11(6): 1-22.
[1] 曲俊龙,史文库,玄圣夷,陈志勇. 面向汽车传动系统多挡共振的多级吸振器参数设计方法[J]. 吉林大学学报(工学版), 2025, 55(2): 444-455.
[2] 胡宏宇,张争光,曲优,蔡沐雨,高菲,高镇海. 基于双分支和可变形卷积网络的驾驶员行为识别方法[J]. 吉林大学学报(工学版), 2025, 55(1): 93-104.
[3] 王军年,曹宇靖,罗智仁,李凯旋,赵文伯,孟盈邑. 基于双目视觉的道路水深在线检测算法[J]. 吉林大学学报(工学版), 2025, 55(1): 175-184.
[4] 谭草,任浩鑫,葛文庆,宋亚东,陆佳瑜. 直驱阀控液压振动平台改进自抗扰控制[J]. 吉林大学学报(工学版), 2025, 55(1): 84-92.
[5] 李寿涛,杨路,屈如意,孙鹏鹏,于丁力. 基于模型预测控制的滑移率控制方法[J]. 吉林大学学报(工学版), 2024, 54(9): 2687-2696.
[6] 吴量,顾义凡,邢彪,马芳武,倪利伟,贾微微. 基于线性二次型调节器的四轮转向与分布式集成控制方法[J]. 吉林大学学报(工学版), 2024, 54(9): 2414-2422.
[7] 王玉海,李晓之,李兴坤. 面向高速工况的混合动力卡车预见性节能算法[J]. 吉林大学学报(工学版), 2024, 54(8): 2121-2129.
[8] 常胜,刘宏飞,邹乃威. 汽车变曲率路径循迹H回路成形鲁棒控制[J]. 吉林大学学报(工学版), 2024, 54(8): 2141-2148.
[9] 刘建泽,柳江,李敏,章新杰. 基于最小二乘的车速解耦路面辨识方法[J]. 吉林大学学报(工学版), 2024, 54(7): 1821-1830.
[10] 谢宪毅,张明君,金立生,周彬,胡涛,白宇飞. 考虑舒适度的智能汽车人工蜂群轨迹规划方法[J]. 吉林大学学报(工学版), 2024, 54(6): 1570-1581.
[11] 刘从臻,陈高,刘洪柱,马强,徐成伟,孟辉,王国林. 湿滑路面轮胎接地力学特性模型[J]. 吉林大学学报(工学版), 2024, 54(6): 1501-1511.
[12] 黄玲,崔躜,游峰,洪佩鑫,钟浩川,曾译萱. 适用于多车交互场景的车辆轨迹预测模型[J]. 吉林大学学报(工学版), 2024, 54(5): 1188-1195.
[13] 郭洪艳,王连冰,赵旭,戴启坤. 考虑侧向运动的整车质量与道路坡度估计[J]. 吉林大学学报(工学版), 2024, 54(5): 1175-1187.
[14] 陆玉凯,袁帅科,熊树生,朱绍鹏,张宁. 汽车漆面缺陷高精度检测系统[J]. 吉林大学学报(工学版), 2024, 54(5): 1205-1213.
[15] 汪少华,张启睿,施德华,殷春芳,李春. 双行星排式混合动力传动系统非线性振动响应特性分析[J]. 吉林大学学报(工学版), 2024, 54(4): 890-901.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!