吉林大学学报(工学版) ›› 2026, Vol. 56 ›› Issue (8): 2077-2083.doi: 10.13229/j.cnki.jdxbgxb.20250060

• 交通运输工程·土木工程 • 上一篇    

自动驾驶汽车接管模式与事故严重程度关联性分析

潘义勇(),杨赛赛   

  1. 南京林业大学 汽车与交通工程学院,南京 210037
  • 收稿日期:2025-01-12 出版日期:2026-08-01 发布日期:2026-09-02
  • 作者简介:潘义勇(1980-),男,副教授,博士.研究方向:交通运输规划与管理.E-mail:uoupanyg@njfu.edu.cn
  • 基金资助:
    国家自然科学基金项目(51508280)

Analysis of correlation between self⁃driving car takeover mode and accident severity

Yi-yong PAN(),Sai-sai YANG   

  1. College of Automotive and Transportation Engineering,Nanjing Forestry University,Nanjing 210037,China
  • Received:2025-01-12 Online:2026-08-01 Published:2026-09-02

摘要:

为探究自动驾驶汽车事故伤害严重程度影响因素,构建了考虑中介效应的结构方程模型,并对自动驾驶汽车接管模式与事故严重程度进行关联性影响因素分析。采用AVOID数据集中的自动驾驶汽车事故数据,从车辆特性、天气特性、道路特性和碰撞状况4个方面选取17个影响因素,利用中介效应和因子结构分析探究各因素对自动驾驶事故严重程度的影响。结果表明:交叉路口和街道可以显著降低自动驾驶汽车交通事故严重程度;路面状况、多云、雨、碰撞(左后方)和白天通过中介效应对事故严重程度产生间接影响,其中路面状况可以显著降低交通事故严重程度,天气(雨)明显增加了交通事故严重程度;自动驾驶汽车发生交通事故时的接管模式对事故严重程度具有显著负作用,且二者具有复杂的关联性。

关键词: 交通运输系统工程, 事故严重程度, 结构方程模型, 自动驾驶汽车, 接管模式, 中介效应

Abstract:

In order to investigate the factors influencing the severity of injury in self-driving car accidents, a structural equation model considering mediating effects was constructd to analyze the correlation between the takeover mode of self-driving cars and the severity of accidents. Using the self-driving car accident data in AVOID dataset, 17 influencing factors were selected from four aspects: vehicle characteristics, weather characteristics, road characteristics and collision conditions, and the mediating effect and factor structure analysis were used to explore the influence of each factor on the severity of self-driving accidents. The results show that road type can significantly reduce the severity of self-driving car accidents. Road condition, weather-cloudy, weather-rain, collision-left rear and lighting-daylight indirectly affect the severity of self-driving car accidents through the mediating effect. Among them, road condition can significantly reduce the severity of traffic accidents. Weather-rain significantly increases the severity of traffic accidents of self-driving cars. The takeover mode of the self-driving car when it is involved in a traffic accident has a significant negative effect on accident severity and the two have a complex correlation.

Key words: engineering of communications and transportation system, accident severity, structural equation modelling, self-driving cars, car takeover, mediating effects

中图分类号: 

  • U491

表1

自变量描述表"

分类自变量自变量描述频数
车辆特性汽车品牌本田11
通用28
福特31
本田47
捷豹110
斯巴鲁21
特斯拉38
丰田24
其他(宝马/奥迪/奔驰/现代/凯迪拉克/雷克萨斯)82
接管模式ADS模式194
ADAS模式86
人工接管112
车型年份2015~201628
2017~201827
2019~2020119
2021~2022200
其他(2023/未知)8

自动系统

使用年份

少于2年228
2~5年122
5年以上35
其他(未知)7
天气特性14
377
多云27
365
道路特性道路类型高速公路93
交叉路口135
街道102
其他62
路面状况干燥369
湿润23
道路照明白天278
黄昏和黎明15
夜晚99
碰撞状况

碰撞区域

(前方)

73
319

碰撞区域

(左前方)

68
324

碰撞区域

(右前方)

69
323

碰撞区域

(后方)

98
294

碰撞区域

(左后方)

80
312

碰撞区域

(右后方)

89
303

碰撞区域

(左方)

31
361

碰撞区域

(右方)

25
367

表2

结构方程模型拟合指标"

拟合

指标

χ2χ2/dfPTLIRMRAGFI
参考值>0.05>1;<3<0.05>0.9<0.05>0.9
指标值18.9412.7060.0080.5920.0220.922

表3

Bootstrap抽样检验结果"

路径估计值SE

95% BCa

置信区间

P
接管模式→路面状况0.0930.057[0.040, 0.281]0.002
接管模式→天气(多云)0.1280.051[0.080, 0.301]0.000
接管模式→天气(雨)0.0060.088[-0.178, 0.189]0.869
接管模式→碰撞(左后方)0.1050.053[0.006, 0.213]0.026
接管模式→照明(白天)-0.1610.045[-0.239, -0.058]0.000
事故严重程度→接管模式-0.1190.043[-0.179, -0.009]0.034
事故严重程度→街道-0.1910.046[-0.247, -0.062]0.001
事故严重程度→交叉路口-0.2460.040[-0.268, -0.103]0.000

表4

结构方程模型估计结果"

路径估计值SEZP
接管模式→路面状况5.2960.31017.1000.000
接管模式→天气(多云)1.1130.5342.0870.037
接管模式→天气(雨)-4.3840.311-14.0950.000
接管模式→碰撞(左后方)0.4140.1952.1280.033
接管模式→照明(白天)-0.5430.174-3.1210.002
事故严重程度→接管模式-0.1530.077-1.9920.046
事故严重程度→街道-0.7190.226-3.1850.001
事故严重程度→交叉路口-0.7750.218-3.5510.000

图1

结构方程模型结果路径图"

图2

交通事故严重程度影响变量关系图"

表5

中介效应检验结果"

变量ACMEADEPM
估计值P估计值P估计值P
路面状况-0.030 10.0120.063 10.436-0.911 80.718
天气(多云)-0.031 80.0040.077 20.318-0.699 00.602
天气(雨)-0.026 40.0140.085 80.348-0.444 80.556
碰撞(左后方)-0.012 80.042-0.088 00.0200.126 90.046
照明(白天)0.017 90.0100.035 10.3500.337 40.130
街道-0.021 20.016-0.065 90.0740.243 70.032
交叉路口0.006 00.330-0.122 20.000-0.051 40.330
[1] 李立, 徐志刚, 赵祥模, 等.智能网联汽车运动规划方法研究综述[J].中国公路学报, 2019, 32(6): 20-33.
Li Li, Xu Zhi-gang, Zhao Xiang-mo, et al. Review on motion planning methods of intelligent and connected vehicles[J]. China Journal of Highway and Transport, 2019, 32(6): 20-33.
[2] J3016_201401. Taxonomy and definitions for terms related to on-road motor vehicle automated driving systems [S].
[3] Lym Y, Chen Z. Influence of built environment on the severity of vehicle crashes caused by distracted driving: a multi-state comparison[J]. Accident Analysis & Prevention, 2021, 150: No.105920.
[4] Islam S, Jones S L. Pedestrian at-fault crashes on rural and urban roadways in Alabama[J]. Accident Analysis & Prevention, 2014, 72: 267-276.
[5] 潘义勇, 吴静婷, 施颖, 等.建成环境对老年人交通事故严重程度异质性影响[J].交通运输系统工程与信息, 2022, 22(3): 224-230.
Pan Yi-yong, Wu Jing-ting, Shi Ying, et al. Heterogeneous effects of built environment on elderly traffic accident injury severities[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(3): 224-230.
[6] Hou Q, Huo X, Leng J, et al. Examination of driver injury severity in freeway single-vehicle crashes using a mixed logit model with heterogeneity-in-means[J]. Physica A: Statistical Mechanics and its Applications, 2019, 531: No.121760.
[7] Chen C, Zhang G, Liu X C, et al. Driver injury severity outcome analysis in rural interstate highway crashes: a two-level Bayesian logistic regression interpretation[J]. Accident Analysis & Prevention, 2016, 97: 69-78.
[8] 陈坚, 邱智宣, 彭涛, 等.建成环境对城市交通事故严重程度影响研究[J]. 重庆交通大学学报: 自然科学版, 2023, 42(3): 105-111, 150.
Chen Jian, Qiu Zhi-xuan, Peng Tao, et al. Influence of built environment on the severity of urban traffic accidents[J]. Journal of Chongqing Jiaotong University(Natural Science), 2023, 42(3): 105-111, 150.
[9] Khattak Z H, Fontaine M D, Smith B L. Exploratory investigation of disengagements and crashes in autonomous vehicles under mixed traffic: an endogenous switching regime framework[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(12): 7485-7495.
[10] 赵丹, 马社强, 张雨萌, 等. 农村公路交叉口交通事故特征关联性与风险因素分析[J]. 中国安全科学学报, 2020, 30(7): 146-151.
Zhao Dan, Ma She-qiang, Zhang Yu-meng, et al. Correlation and risk factors analysis of traffic crash at intersections on rural highways[J]. China Safety Science Journal, 2020, 30(7): 146-151.
[11] 刘强, 严修, 谢谦, 等.基于事故综合强度的公交事故严重程度分析[J].交通运输系统工程与信息,2022, 22(6): 152-159.
Liu Qiang, Yan Xiu, Xie Qian, et al. Bus accident severity analysis based on comprehensive accident intensity[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(6): 152-159.
[12] Jin M, Lu G, Chen F, et al. Modeling takeover behavior in level 3 automated driving via a structural equation model: considering the mediating role of trust[J]. Accident Analysis & Prevention, 2021, 157: No.106156.
[13] Sinha A, Vu V, Chand S, et al. A crash injury model involving autonomous vehicle: investigating of crash and disengagement reports[J]. Sustainability, 2021, 13(14): No.7938.
[14] Zheng O, Abdel-Aty M, Wang Z, et al. Avoid: autonomous vehicle operation incident dataset across the globe[J/OL]. [2024-01-05]. .
[15] Zhang Y, Carballo A, Yang H, et al. Perception and sensing for autonomous vehicles under adverse weather conditions: a survey[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 196: 146-177.
[16] Wu Q, Zhang G, Zhu X, et al. Analysis of driver injury severity in single-vehicle crashes on rural and urban roadways[J]. Accident Analysis & Prevention, 2016,94: 35-45.
[1] 冯天军,郝延铭,李飞燕,高赫遥,刘一贤,刘楠,李金凤. 考虑驾驶风格的网联自动驾驶车辆集聚换道模型[J]. 吉林大学学报(工学版), 2026, 56(7): 1834-1844.
[2] 孟云伟,李智鹏,张引,全振宇,杨光清,陈芳,赖思静,乔俊. 基于纵向间距和亮度差的隧道群驾驶舒适度[J]. 吉林大学学报(工学版), 2026, 56(7): 1904-1914.
[3] 张玉召,丁欣茹,侯长啸,陈虎林. 交通运输网络韧性研究现状及展望[J]. 吉林大学学报(工学版), 2026, 56(3): 585-602.
[4] 慈玉生,黄轶康. 基于文献计量的交叉口车路协同研究综述[J]. 吉林大学学报(工学版), 2026, 56(2): 313-332.
[5] 张文会,叶梅茹,席聪,宋子文. 混合交通流环境下车辆编队与碳排放特性[J]. 吉林大学学报(工学版), 2026, 56(2): 416-430.
[6] 潘义勇,曹天宇,刘宇. 随机交通网络约束最可靠路径乘子交替方向法[J]. 吉林大学学报(工学版), 2026, 56(2): 455-463.
[7] 孙宇,李世武,郭梦竹,金桐彤,宋会军,刘德志,高雯. 多模态数据在驾驶疲劳监测中的有效性分析[J]. 吉林大学学报(工学版), 2026, 56(2): 473-479.
[8] 李坤宸,袁伟,王畅,张会明,穆雨薇. 基于驾驶风险和驾驶能力的人机控制权分配[J]. 吉林大学学报(工学版), 2026, 56(2): 575-584.
[9] 马壮林,毕宇明,周备,邓亚娟,兆雪. 公交换乘优惠政策下居民换乘意向的异质性分析[J]. 吉林大学学报(工学版), 2026, 56(1): 158-169.
[10] 王琳虹,刘宇阳,刘子昱,鹿应佳,张宇恒,黄桂树. 基于YOLOv5的轻量化桥梁缺陷识别[J]. 吉林大学学报(工学版), 2025, 55(9): 2958-2968.
[11] 曲昭伟,王铭阳,王喆,宋现敏,张云翔,黄镜尘. 基于自动驾驶模块化车辆主辅功能分配的公交自适应调度方法[J]. 吉林大学学报(工学版), 2025, 55(9): 2946-2957.
[12] 张云翔,宋现敏,谢渝,湛天舒. 基于用户满意度的停车预约服务智能体行为仿真[J]. 吉林大学学报(工学版), 2025, 55(9): 2978-2984.
[13] 穆长儒,徐亮,程国柱. 基于能量合理分配的外包U型钢-混凝土组合护栏防撞性能[J]. 吉林大学学报(工学版), 2025, 55(8): 2669-2680.
[14] 柴树山,周志强,李海涛,徐炅旸. 基于图时空模式学习网络的路网实时交通事件自动检测方法[J]. 吉林大学学报(工学版), 2025, 55(7): 2145-2161.
[15] 李艳波,汪静远,陈圆媛,程绍峰,吕浩楠,陈俊硕. 面向高速公路服务区自洽能源系统的RAMS评价方法[J]. 吉林大学学报(工学版), 2025, 55(7): 2243-2250.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!