A risk assessment method of driving behavior considering severity of safety-critical events and individual heterogeneity

doi:10.16265/j.cnki.issn1003-3033.2023.07.1120

Abstract

Abstract:

Aiming at the lack of risk degree measurement and insufficient consideration of individual differences in the driving behavior risk assessment method, the natural driving experimental data of 15 subjects were collected, and the paired T-test and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering were used to obtain the deviation of the indicator from the normal state in driving safety events and driver risk propensity level. The indicators were selected to quantify the severity of a single driving safety event, and the driving risk weights were corrected to construct a driving behavior risk assessment method that considered the severity of driving events and individual differences. The validity of the model was verified by using time head (TH). The results show that speed standard deviation, speed range and mean and maximum value of acceleration are more important for driving risk assessment. The risk score obtained by the optimized evaluation methods ranges from [21,42.6], with a mean value of 32.93 and a standard deviation of 6.62. The driving behavior risk score in this study is closer to the actual situation than the traditional score. The above indicators can be used to evaluate the comprehensive driving behavior risk and improve the accuracy of driving risk identification.

Key words: safety-critical events, severity, individual heterogeneity, driving behavior, risk identification, density-based spatial clustering of applications with noise (DBSCAN)

ZHANG Hui, LIU Yongjie, WU Chaozhong, DING Naikan, ZHANG Qi, XIAO Yiying. A risk assessment method of driving behavior considering severity of safety-critical events and individual heterogeneity[J]. China Safety Science Journal, 2023, 33(7): 24-31.

Figures/Tables 11

Tab.1

Fig.1

Tab.2

Fig.2

Fig.3

Tab.3

Tab.4

Fig.4

Tab.5

Tab.6

Fig.5

References 18

[1]	严新平, 张晖, 吴超仲, 等. 道路交通驾驶行为研究进展及其展望[J]. 交通信息与安全, 2013, 31(1):45-51.
	YAN Xinping, ZHANG Hui, WU Chaozhong, et al. Research progress and prospect of road traffic driving behavio[J]. Journal of Transport Information and Safety, 2013, 31(1):45-51.
[2]	张正. 基于车联网驾驶行为评分的安全驾驶卫士分析与设计[D]. 南京: 南京邮电大学, 2017.
	ZHANG Zheng. The analysis and design of driving safety guards based on the score of driving behavior in vehicle networking[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2017.
[3]	ELLISON A B, BLIEMER M C J, GREAVES S P. Evaluating changes in driver behaviour: a risk profiling approach[J]. Accident Analysis & Prevention, 2015, 75:298-309. doi: 10.1016/j.aap.2014.12.018
[4]	李平凡. 驾驶行为表征指标及分析方法研究[D]. 长春: 吉林大学, 2010.
	LI Pingfan. Research on indices and analysis of driving behavior[D]. Changchun: Jilin University, 2017.
[5]	SAIPRASERT C, PHOLPRASIT T, THAJCHAYAPONG S. Detection of driving events using sensory data on smartphone[J]. International Journal of Intelligent Transportation Systems Research, 2017, 15(1):17-28. doi: 10.1007/s13177-015-0116-5
[6]	GUO Feng, FANG Youjia. Individual driver risk assessment using naturalistic driving data[J]. Accident Analysis & Prevention, 2013, 61(6):3-9. doi: 10.1016/j.aap.2012.06.014
[7]	胥川, 裴赛君, 王雪松. 基于无侵入测量指标的个体差异化驾驶疲劳检测[J]. 中国公路学报, 2016, 29(10):118-125.
	XU Chuan, PEI Saijun, WANG Xuesong. Driver drowsiness detection based on non-intrusive metrics considering individual difference[J]. China Journal of Highway and Transport, 2016, 29(10):118-125.
[8]	秦雅琴, 李秋谷, 赵鹏燕, 等. 基于多分类Adaboost算法的驾驶人风险感知倾向研究[J]. 中国安全科学学报, 2022, 32(4):141-147. doi: 10.16265/j.cnki.issn1003-3033.2022.04.021
	QIN Yaqin, LI Qiugu, ZHAO Pengyan, et al. Research on risk perception tendency of drivers based on multi-class Ada-boost algorithm[J]. China Safety Science Journal, 2022, 32(4): 141-147. doi: 10.16265/j.cnki.issn1003-3033.2022.04.021
[9]	曾诚, 吴初娜, 孟兴凯. 驾驶人危险辨识进展研究[J]. 中国安全科学学报, 2016, 26(12): 74-79.
	ZENG Cheng, WU Chu'na, MENG Xingkai. A review of progress in studying drivers' hazard perception[J]. China Safety Science Journal, 2016, 26(12): 74-79.
[10]	乔洁, 徐鑫, 刘传攀, 等. 驾驶人危险感知能力影响因素及干预方式综述[J]. 中国安全科学学报, 2022, 32(2): 34-41. doi: 10.16265/j.cnki.issn1003-3033.2022.02.006
	QIAO Jie, XU Xin, LIU Chuanpan, et al. Review on affecting factors and intervention methods of drivers' hazard perception ability[J]. China Safety Science Journal, 2022, 32(2): 34-41. doi: 10.16265/j.cnki.issn1003-3033.2022.02.006
[11]	AKSAN N, SAGER L, HACKER S, et al. Individual differences in cognitive functioning predict effectiveness of a heads-up lane departure warning for younger and older drivers[J]. Accident Analysis & Prevention, 2017, 99: 171-183. doi: 10.1016/j.aap.2016.11.003
[12]	ENEV M, TAKAKUWA A, KOSCHER K, et al. Automobile driver fingerprinting[J]. Proceedings on Privacy Enhancing Technologies, 2015, 2016(1): 34-50. doi: 10.1515/popets-2015-0029
[13]	EBOLI L, MAZZULLA G, PUNGILLO G. Combining speed and acceleration to define car users' safe or unsafe driving behavior[J]. Transportation Research Part C: Emerging Technologies, 2016, 68: 113-125. doi: 10.1016/j.trc.2016.04.002
[14]	BIAN Yiyang, YANG Chen, ZHAO J, et al. Good drivers pay less: a study of usage-based vehicle insurance models[J]. Transportation Research Part A: Policy and Practice, 2018, 107: 20-34. doi: 10.1016/j.tra.2017.10.018
[15]	WILDE G J S. The theory of risk homeostasis: implications for safety and health[J]. Risk Analysis, 1982, 2(4): 209-225. doi: 10.1111/risk.1982.2.issue-4
[16]	ZHANG Xiaoxuan, LU Guangquan, CHENG Bo. Parameters calibration for car-following model based desired safety margin[C]. International Conference on Optoelectronics & Image Processing. IEEE, 2011: 97-100.
[17]	吕能超, 任泽远, 段至诚, 等. Near-crash事件中驾驶人行为特征分析[J]. 中国安全科学学报, 2017, 27(6): 19-24. doi: 10.16265/j.cnki.issn1003-3033.2017.06.004
	LYU Nengchao, REN Zeyuan, DUAN Zhicheng, et al. Analysis of driving behavior characteristics of drivers in near-crash events[J]. China Safety Science Journal, 2017, 27(6): 19-24. doi: 10.16265/j.cnki.issn1003-3033.2017.06.004
[18]	张新生, 蔡宝泉. 基于改进随机森林模型的海底管道腐蚀预测[J]. 中国安全科学学报, 2021, 31(8): 69-74. doi: 10.16265/j.cnki.issn1003-3033.2021.08.010
	ZHANG Xinsheng, CAI Baoquan. Corrosion prediction of submarine pipelines based on improved random forest model[J]. China Safety Science Journal, 2021, 31(8): 69-74. doi: 10.16265/j.cnki.issn1003-3033.2021.08.010

参数类型	采集设备	说明
TH/s	Mobileye	采样频率8 Hz,TH超过2.5 s 时为0,数据范围[0,2.5]
车速值/(km·h^-1)	原车控制器区域网络(Controller Area Network,CAN)输出	采样频率>20 Hz
加速度/(m·s^-2)	原车CAN输出	采样频率>20 Hz
方向盘转角/(°)	方向盘转角传感器	转向角度,正中央往左为负,往右为正
方向盘转角加速度/(°·s^-1)	方向盘转角传感器	转向加速度,正中央向左为负,右为正
刹车踏板	原车CAN输出	0或1(0表示未刹车,1表示刹车)
左转向灯	原车CAN输出	0或1(1表示开启左转向灯)
右转向灯	原车CAN输出	0或1(1表示开启右转向灯)

操纵能力	指标	驾驶行为表征指标
车速保持能力	速度	速度均值、速度标准差、速度最大值、速度极差
车速保持能力	加速度	加速度均值、减速度均值、加速度标准差、加速度最大值、减速度最大值
转向盘控制能力	方向盘转角	右向方向盘转角均值、左向方向盘转角均值、方向盘转角标准差、方向盘转角最大值
转向盘控制能力	方向盘转角加速度	右向方向盘转角加速度均值、左向方向盘转角加速度均值、方向盘转角加速度标准差、方向盘转角加速度最大值

指标名称	超速事件 i₁	急加速事件 i₂	急减速事件 i₃	急转弯事件 i₄	风险评估重要度	指标名称	超速事件 i₁	急加速事件i₂	急减速事件i₃	急转弯事件i₄	风险评估重要度
速度均值	3	1	1	1	6	方向盘转角均值(右)	1	1	1	2	5
速度标准差	1	3	3	1	8	方向盘转角均值(左)	1	1	2	1	5
速度最大值	3	1	1	1	6	方向盘转角标准差	1	1	1	3	6
速度极差	1	3	3	1	8	方向盘转角最大值	1	1	1	3	6
加速度均值	1	3	3	1	8	方向盘转角加速度均值(右)	2	1	1	3	7
减速度均值	1	2	3	1	7	方向盘转角加速度均值(左)	1	1	1	3	6
加速度标准差	1	2	3	1	7	方向盘转角加速度标准差	2	1	1	3	7
加速度最大值	1	3	3	1	8	方向盘转角加速度最大值	1	1	1	3	6
减速度最大值	1	2	3	1	7	—	—	—	—	—	—

事件类别i	事件严重程度量化评估指标k
超速	速度均值、速度最大值
急加速	加速度均值、加速度最大值
急减速	速度标准差、速度极差、减速度均值、减速度最大值
急转弯	方向盘转角加速度标准差、方向盘转角加速度最大值

被试	i₁	i₂	i₃	i₄	风险度	被试	i₁	i₂	i₃	i₄	风险度	被试	i₁	i₂	i₃	i₄	风险度
1	1	2	3	2	8	6	1	1	1	1	4	11	1	2	1	1	5
2	1	2	1	1	5	7	1	2	1	1	5	12	3	3	2	1	9
3	1	2	1	1	5	8	1	2	1	1	5	13	1	2	1	1	5
4	1	2	1	3	7	9	2	2	2	1	7	14	1	2	1	1	5
5	1	2	1	1	5	10	1	2	1	1	5	15	1	2	1	1	5