城市环形交叉口智能汽车接管过程事故风险预测

doi:10.16265/j.cnki.issn1003-3033.2022.12.2650

中国安全科学学报 ›› 2022, Vol. 32 ›› Issue (12): 150-157.doi: 10.16265/j.cnki.issn1003-3033.2022.12.2650

城市环形交叉口智能汽车接管过程事故风险预测

刘擎超¹^,²(), 徐天宇¹, 熊晓夏³, 赵晶娅¹^,⁴, 蔡英凤¹

¹ 江苏大学汽车工程研究院,江苏镇江 212013
² 南洋理工大学机械与航空航天工程学院,新加坡 639798
³ 江苏大学汽车与交通工程学院,江苏镇江 212013
⁴ 东南大学交通学院,江苏南京 210096

收稿日期:2022-07-21 修回日期:2022-10-12 出版日期:2022-12-28 发布日期:2023-06-28
作者简介:
刘擎超 (1987—),男,江苏盐城人,博士,副教授,主要从事高级自动驾驶、智能网联汽车、交通事故风险预测研究。E-mail:lqc@ujs.edu.cn。
基金资助:
国家自然科学基金资助(51905223); 国家自然科学基金资助(U20A20331); 国家自然科学基金资助(U20A20333); 国家自然科学基金资助(52225212); 江苏省重点研发计划项目(BE2020083-3); 江苏省重点研发计划项目(BE2019010-2); 江苏省重点研发计划项目(BE2021011-3); 中国博士后科学基金资助(2021M690069); 江苏省研究生实践创新计划项目(SJCX20_1425)

Accident risk prediction of intelligent vehicle takeover process at urban roundabout

LIU Qingchao¹^,²(), XU Tianyu¹, XIONG Xiaoxia³, ZHAO Jingya¹^,⁴, CAI Yingfeng¹

¹ Automotive Engineering Research Institute, Jiangsu University, Zhenjiang Jiangsu 212013, China
² School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore
³ School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang Jiangsu 212013, China
⁴ School of Transportation, Southeast University, Nanjing Jiangsu 210096, China

Received:2022-07-21 Revised:2022-10-12 Online:2022-12-28 Published:2023-06-28

摘要/Abstract

摘要：

为降低城市环形交叉口事故发生率,针对交叉口智能汽车接管过程中的事故风险问题,提出智能汽车事故风险预测模型。基于城市交通仿真软件(ToT),构建城市环形交叉口场景,分析智能驾驶汽车接管过程的事故数据,揭示道路区域及接管时间对智能汽车接管过程事故风险的影响机制;使用CatBoost对事故风险进行建模,以敏感性分析、曲线下面积(AUC)为评价指标,对比CatBoost与线性回归、XGBoost模型的预测性能。结果表明:速度对事故的影响重要度占比在47%以上,交叉口入口道事故率最高,且入口左侧车道事故率较右侧车道平均高8.63%左右;ToT时间在环形交叉口对汽车事故率影响约为8.5%,且环道区域的道路曲率、半径因素对事故影响因素占比小于5%;环道路段几乎不影响自动驾驶汽车在车辆接管过程的碰撞,CatBoost模型预测精度高于线性回归及XGBoost。

关键词: 环形交叉口, 智能汽车, 接管时间, 事故分析, CatBoost

Abstract:

Aiming at the accident risk in the process of intelligent vehicle takeover at the urban roundabout, a prediction model of intelligent vehicle accident risk at the roundabout was proposed to reduce the accident rate. Based on the urban traffic simulation software simulation of urban mobility (SUMO), the scene of urban roundabout was established, and the accident data of intelligent driving vehicle takeover process was analyzed to reveal the impact mechanism of road area and takeover time(ToT) on the accident risk of intelligent vehicle takeover process. CatBoost was used to model the accident risk, and the sensitivity analysis and Area Under the Curve (AUC) were used as evaluation indicators to compare the prediction performance with Linear Regression and XGBoost models. The results show that the impact of speed on the accident is more than 47%. The accident rate in the entrance lane of the intersection is the highest. The accident rate of the left lane of the entrance is 8.63% higher than that of the right lane on average. The influence of (ToT) on car accident rate at roundabouts is about 8.5%, and the proportion of road curvature and radius factors in the loop area on accident factors is less than 5%. The roundabout segment hardly affects the autonomous vehicle collision during the vehicle takeover process. The prediction accuracy of the CatBoost model is higher than that of linear regression and XGBoost.

Key words: intelligent vehicle, roundabout, takeover time, accident analysis, CatBoost

刘擎超, 徐天宇, 熊晓夏, 赵晶娅, 蔡英凤. 城市环形交叉口智能汽车接管过程事故风险预测[J]. 中国安全科学学报, 2022, 32(12): 150-157.

LIU Qingchao, XU Tianyu, XIONG Xiaoxia, ZHAO Jingya, CAI Yingfeng. Accident risk prediction of intelligent vehicle takeover process at urban roundabout[J]. China Safety Science Journal, 2022, 32(12): 150-157.

图/表 11

图1

图2

图3

表1

图4

图5

表2

表3

表4

表5

图6

参考文献 10

[1]	LU Zhenji, HAPPE R, DE WINTER J C. Take over! a video-clip study measuring attention, situation awareness, and decision-making in the face of an impending hazard[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2020, 72:211-225. doi: 10.1016/j.trf.2020.05.013
[2]	DU Na, ZHOU Feng, PULVER E M, et al. Predicting driver takeover performance in conditionally automated driving[J]. Accident Analysis & Prevention, 2020, 148: DOI:10.1016/j.aap.2020.105748. doi: 10.1016/j.aap.2020.105748
[3]	NAUJOKS F, PURUCKER C, WIEDEMANN K, et al. Noncritical state transitions during conditionally automated driving on german freeways: effects of non-driving related tasks on takeover time and takeover quality[J]. Human Factors, 2019, 61(4): 596-613. doi: 10.1177/0018720818824002 pmid: 30689440
[4]	WU Yanbin, KIHARA K, TAKEDA Y, et al. Eye movements predict driver reaction time to takeover request in automated driving: a real-vehicle study[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2021, 81: 355-363. doi: 10.1016/j.trf.2021.06.017
[5]	张磊, 彭金栓, 陈晓利. 驾驶分心行为量表设计与影响因素分析[J]. 中国安全科学学报, 2021, 31(11):39-46. doi: 10.16265/j.cnki.issn 1003-3033.2021.11.006
	ZHANG Lei, PENG Jinshuan, CHEN Xiaoli. Design of driving distraction behavior scale and analysis of influencing factors[J]. China Safety Science Journal, 2021, 31(11):39-46. doi: 10.16265/j.cnki.issn 1003-3033.2021.11.006
[6]	BRANDENBURG S, CHUANG L. Take-over requests during highly automated driving: how should they be presented and under what conditions?[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2019, 66: 214-225. doi: 10.1016/j.trf.2019.08.023
[7]	吴超仲, 吴浩然, 吕能超. 人机共驾智能汽车的控制权切换与安全性综述[J]. 交通运输工程学报, 2018, 18(6):131-141.
	WU Chaozhong, WU Haoran, LYU Nengchao. Review of control switch and safety of human-computer driving intelligentvehicle[J]. Journal of Transportation Engineering, 2018, 18(6):131-141.
[8]	ZHENG Qikang, XU Chengcheng, LIU Pan, et al. Investigating the predictability of crashes on different freeway segments using the real-time crash risk models[J]. Accident Analysis & Prevention, 2021, 159: DOI: 10.1016/j.aap.2021.106213. doi: 10.1016/j.aap.2021.106213
[9]	姚志洪, 金玉婷, 王思琛, 等. 混入智能网联汽车的交通流稳定性与安全性分析[J]. 中国安全科学学报, 2021, 31(10):136-143. doi: 10.16265/j.cnki.issn1003-3033.2021.10.019
	YAO Zhihong, JIN Yuting, WANG Sichen, et al. Stability and safety analysis on traffic flow mixed with ICV[J]. China Safety Science Journal, 2021, 31(10):136-143. doi: 10.16265/j.cnki.issn1003-3033.2021.10.019
[10]	MILANES V, SHLADOVER S E. Modeling cooperative and autonomous adaptive cruise control dynamic responses using experimental data[J]. Transportation Research Part C: Emerging Technologies, 2014, 48: 285-300. doi: 10.1016/j.trc.2014.09.001

变量	释义	变量	释义
R_n	车辆所处道路	D_f	接管车辆前车距离
R_c	子路段道路曲率	T_f	接管车辆前车车头时距
R_r	子路段曲线半径	V_b	接管车辆后车速度
R_l	子路段曲线长度	D_b	接管车辆后车距离
V_t	接管车辆速度	T_b	接管车辆后车车头时距
ToT	ToT	V_f	接管车辆前车速度

区域	40 km/h		45 km/h		50 km/h		55 km/h		60 km/h
区域	事故数	事故率/%	事故数	事故率/%	事故数	事故率/%	事故数	事故率/%	事故数	事故率/%
入口1	1	1.78	4	7.14	18	32.14	42	75.00	45	80.36
入口2	—	—	12	20.34	17	28.81	44	74.58	47	79.66
入口3	1	1.43	5	7.14	28	40.00	46	65.71	58	82.86
入口4	—	—	4	8.89	27	60.00	40	88.89	43	95.56

区域	50 km/h		55 km/h		60 km/h
区域	事故数	事故率/%	事故数	事故率/%	事故数	事故率/%
入口1-右	7	33.33	15	71.43	16	76.19
入口1-左	11	31.43	27	77.14	29	82.86
入口2-右	8	33.33	16	66.67	17	70.83
入口2-左	9	25.71	28	80.00	30	85.71
入口3-右	10	34.48	19	65.52	22	75.86
入口3-左	18	43.90	27	65.85	36	87.80
入口4-右	10	58.82	14	82.35	15	88.24
入口4-左	17	60.71	26	92.86	28	100.00

ToT/s	40 km/h		45 km/h		50 km/h		55 km/h		60 km/h
ToT/s	事故数	事故率/%	事故数	事故率/%	事故数	事故率/%	事故数	事故率/%	事故数	事故率/%
1.5	0	0	3	15.00	12	63.16	18	90.00	22	95.65
2.0	1	4.17	2	11.11	6	37.5.0	19	73.08	19	95.00
2.5	0	0	3	11.11	9	40.91	15	71.43	25	76.92
3.0	0	0	1	5.88	5	33.33	21	77.78	19	95.00
3.5	1	5.88	1	5.26	8	50.00	28	93.33	28	90.32
4.0	0	0	2	10.53	12	60.00	17	80.95	18	90.00
4.5	0	0	5	20.00	10	38.46	22	71.43	20	83.33
5.0	0	0	3	20.00	14	40.00	18	72.00	20	83.33
5.5	0	0	3	15.00	10	35.71	12	80.00	18	94.74
6.0	0	0	2	18.18	6	46.15	5	71.43	11	100

[1]	罗崎瑞, 张道文, 周华, 庞劭荣, 李哓艳, 王朝健. 面向智能汽车预期功能安全的驾驶场景评价*[J]. 中国安全科学学报, 2022, 32(8): 140-145.
[2]	梁新苗, 肖凌云, 王澎, 董红磊, 曲现国, 刘川. 数据挖掘与现场调查结合的电动汽车事故分析[J]. 中国安全科学学报, 2022, 32(1): 180-187.
[3]	孙志春, 宫广正, 张艳亮, 肖海平, 白翎, 闫卫东. 基于失效模式的电力企业事故分析系统构建[J]. 中国安全科学学报, 2021, 31(S1): 1-7.
[4]	尹德志, 帅斌, 黄文成, 张玥, 张锐, 左博睿. Tropos-FRAM法在道路客运事故分析中的应用[J]. 中国安全科学学报, 2020, 30(8): 151-157.
[5]	闫旭, 彭其渊, 殷勇, 李文新. 区域铁路运输安全态势表征与评估方法[J]. 中国安全科学学报, 2020, 30(4): 33-40.
[6]	李末, 燕飞, 牛儒, 宋晗炜, 王艳梅, 向楠楠. 基于安全指标监控的事故致因分析方法^*[J]. 中国安全科学学报, 2019, 29(S2): 35-40.
[7]	裴红蕾. 智能汽车换道避障路径规划与跟踪方法[J]. 中国安全科学学报, 2018, 28(9): 26-32.
[8]	徐晟, 倪清清. 跨省承包对施工安全状况演变的影响研究[J]. 中国安全科学学报, 2018, 28(9): 103-108.
[9]	聂细亮, 刘强, 李国帅, 戴冉. LNG船舶海上运输安全研究现状及进展[J]. 中国安全科学学报, 2017, 27(5): 87-92.
[10]	甘旭升，崔浩林，吴亚荣. 基于功能共振事故模型的航空事故分析[J]. 中国安全科学学报, 2013, 23(7): 67-.
[11]	梁磊，李永树，马磊. 基于AE的燃气管网事故分析模块设计与实现[J]. 中国安全科学学报, 2011, 21(1): 124-.
[12]	李鹏程，戴立操，张力，陈国华，赵明. 组织定向的人因失误因果模型及影响关系研究[J]. 中国安全科学学报, 2010, 20(4): 75-.
[13]	高敏，刘志强. 现代环形交叉口安全性分析和安全设计[J]. 中国安全科学学报, 2010, 20(4): 92-.
[14]	毛喆，严新平，陈辉，初秀民，袁雄. 水上交通事故分析研究进展[J]. 中国安全科学学报, 2010, 20(12): 86-.
[15]	张国宗，井水兰. 医疗安全事故的组织因素研究[J]. 中国安全科学学报, 2009, 19(10): 166-.

城市环形交叉口智能汽车接管过程事故风险预测

Accident risk prediction of intelligent vehicle takeover process at urban roundabout

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 10

相关文章 15

编辑推荐

Metrics

本文评价