基于避险脱离的自动驾驶路测安全影响因素

doi:10.13229/j.cnki.jdxbgxb.20221144

Abstract

Abstract:

This study uses the risk-avoiding disengagement to represent the risk. This study first uses the LSTM method to identify the risk-avoiding disengagement of autonomous vehicles in the road-testing phase based on a large scale of realistic road-testing data， then use the Tobit model to analyze the impacts of factors on the risk-avoiding disengagement rate， and the risk analysis model of autonomous vehicle road testing was established. This method can avoid the accidents of autonomous vehicle road testing in advance， and promote the autonomous vehicle road testing in a safe and regulated way.

Key words: transportation engineering, autonomous vehicle road testing, risk-avoiding disengagement, risk factors, Tobit model

CLC Number:

U491

Hui-zhao TU,Chang LU,Miao-jia LU,Hao LI. Risk factors for autonomous vehicle road testing based on risk-avoiding disengagement[J].Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 1935-1943.

Figures/Tables 7

Fig.1

Fig.2

Table 1

Fig.3

Table 2

Fig.4

Table 3

References 47

1	Saifuzzaman M, Zheng Z. Incorporating human-factors in car-following models: a review of recent developments and research needs[J]. Transportation Research Part C: Emerging Technologies, 2014, 48: 379-403.
2	Hoogendoorn R, Van Arerm B, Hoogendoom S. Automated driving, traffic flow efficiency, and human factors: literature review[J]. Transportation Research Record, 2014, 2422(1): 113-120.
3	Favarò F M, Nader N, Eurich S O, et al. Examining accident reports involving autonomous vehicles in California[J]. PLoS one, 2017, 12(9):No. e0184952.
4	Randazzo R. A slashed tire, a pointed gun, bullies on the road: why do Waymo self-driving vans get so much hate?[N]. Arizona Republic, 2018-07-12(5).
5	王雪松, 宋洋, 黄合来, 等. 基于分层负二项模型的城郊公路安全影响因素研究[J]. 中国公路学报,2014(1): 100-106.
	Wang Xue-song, Song Yang, Huang He-lai, et al. Analysis of risk factors for suburan highways using hierarchical negative binomial model[J]. China Journal of Highway and Transport, 2014(1): 100-106.
6	殷炬元, 李铁男, 孙剑. 基于贝叶斯空间相关模型的城市快速路安全影响因素研究[J]. 交通信息与安全,2016,34(3): 27-33, 40.
	Yin Ju-yuan, Li Tie-nan, Sun Jian. An analysis of effective factors of safety for urban expressways based on Bayesian spatial models[J]. Journal of Transport Information and Safety. 2016(3): 27-33, 40.
7	Lord D, Mannering F. The statistical analysis of crash-frequency data: a review and assessment of methodological alternatives[J]. Transp Resarch Part A: Policy and Practice, 2010, 44(5): 291-305.
8	Miaou S P, Lum H. Modeling vehicle accidents and highway geometric design relationships[J]. Accident Analysis & Prevention, 1993, 25(6): 689-709.
9	Miaou S P. The relationship between truck accidents and geometric design of road sections - poisson versus negative binomial regressions[J]. Accident Analysis & Prevention, 1994, 26(4): 471-482.
10	Malyshkina N V, Mannering F. Empirical assessment of the impact of highway design exceptions on the frequency and severity of vehicle accidents[J]. Accident Analysis & Prevention, 2010, 42(1): 131-139.
11	Geedipally S R, Lord D, Dhavala S S. The negative binomial-Lindley generalized linear model: characteristics and application using crash data[J]. Accident Analysis & Prevention, 2012, 45: 258-265.
12	Lord D, Miranda-Moreno L F. Effects of low sample mean values and small sample size on the estimation of the fixed dispersion parameter of Poisson-Gamma models for modeling motor vehicle crashes: a Bayesian perspective[J]. Safety Science, 2008, 46(5): 751-770.
13	Heydari S, Fu L P, Thakali L, et al. Benchmarking regions using a heteroskedastic grouped random parameters model with heterogeneity in mean and variance: applications to grade crossing safety analysis [J]. Analytic Methods in Accident Research, 2018, 19: 33-48.
14	Yu R, Wang Y, Quddus M, et al. A marginalized random effects hurdle negative binomial model for analyzing refined-scale crash frequency data[J]. Analytic Methods in Accident Research, 2019, 22:No. 100092.
15	Lord D, Washington S, Ivan J N. Further notes on the application of zero-inflated models in highway safety[J]. Accident Analysis & Prevention, 2007, 39(1): 53-57.
16	Xie Y C, Zhang Y L. Crash frequency analysis with generalized additive models[J]. Transportation Research Record, 2008, 2061(1): 39-45.
17	Zhang Y L, Xie Y C, Li L H. Crash frequency analysis of different types of urban roadway segments using generalized additive model[J]. Journal of Safety Research, 2012, 43(2): 107-114.
18	Quddus M A. Time series count data models: an empirical application to traffic accidents[J]. Accident Analysis & Prevention, 2008, 40(5): 1732-1741.
19	Guo F, Wang X S, Abdel-Aty M A. Modeling signalized intersection safety with corridor-level spatial correlations[J]. Accident Analysis & Prevention, 2010, 42(1): 84-92.
20	Zou Y J, Lin B, Yang X X, et al. Application of the Bayesian model averaging in analyzing freeway traffic incident clearance time for emergency management [J]. Journal of Advanced Transportation, 2021, 2021: No.6671983.
21	Lao Y T, Wu Y J, Corey J, et al. Modeling animal-vehicle collisions using diagonal inflated bivariate Poisson regression[J]. Accident Analysis & Prevention, 2011, 43(1): 220-227.
22	Huang H L, Chang F R, Zhou H C, et al. Modeling unobserved heterogeneity for zonal crash frequencies: a Bayesian multivariate random-parameters model with mixture components for spatially correlated data [J]. Analytic Methods in Accident Research, 2019, 24: No.100105.
23	Wang K, Ivan J N, Ravishanker N, et al. Multivariate Poisson lognormal modeling of crashes by type and severity on rural two lane highways[J]. Accident Analysis & Prevention, 2017, 99: 6-19.
24	Lao Y T, Zhang G H, Wang Y H, et al. Generalized nonlinear models for rear-end crash risk analysis[J]. Accident Analysis & Prevention, 2014, 62: 9-16.
25	Wu L T, Zou Y J, Lord D. Comparison of sichel and negative binomial models in hot spot identification [J]. Transportation Research Record, 2014, 2460(1): 107-116.
26	Saha D, Alluri P, Dumbaugh E, et al. Application of the Poisson-Tweedie distribution in analyzing crash frequency data[J]. Accident Analysis & Prevention, 2020, 137: No.100105. .
27	Wu L T, Meng Y, Kong X Q, et al. Incorporating survival analysis into the safety effectiveness evaluation of treatments: jointly modeling crash counts and time intervals between crashes[J]. Journal of Transportation Safety & Security, 2022, 14(2): 338-358.
28	Chang L Y, Chen W C. Data mining of tree-based models to analyze freeway accident frequency[J]. Journal of Safety Research, 2005, 36(4): 365-375.
29	Xie Y C, Lord D, Zhang Y L. Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis[J]. Accident Analysis & Prevention, 2007, 39(5): 922-933.
30	Li X G, Lord D, Zhang Y L, et al. Predicting motor vehicle crashes using support vector machine models [J]. Accident Analysis & Prevention, 2008, 40(4): 1611-1618.
31	Abdel-Aty M, Haleem K. Analyzing angle crashes at unsignalized intersections using machine learning techniques[J]. Accident Analysis & Prevention, 2011, 43: 461-470.
32	Haleem K, Gan A, Lu J Y. Using multivariate adaptive regression splines (MARS) to develop crash modification factors for urban freeway interchange influence areas[J]. Accident Analysis & Prevention, 2013, 55: 12-21.
33	Zeng Q, Huang H L, Pei X, et al. Rule extraction from an optimized neural network for traffic crash frequency modeling[J]. Accident Analysis & Prevention, 2016, 97: 87-95.
34	Zhang X, Waller S T, Jiang P. An ensemble machine learning-based modeling framework for analysis of traffic crash frequency[J]. Computer-Aided Civil and Infrastructure Engineering, 2020, 35(3): 258-76.
35	Pu Z Y, Li Z B, Ke R M, et al. Evaluating the nonlinear correlation between vertical curve features and crash frequency on highways using random forests [J]. Journal of Transportation Engineering, Part A: Systems, 2020, 146(10): No.4020115.
36	Wen X, Xie Y, Wu L, et al. Quantifying and comparing the effects of key risk factors on various types of roadway segment crashes with LightGBM and SHAP[J]. Accident Analysis & Prevention, 2021, 159: No.106261.
37	Anastasopoulos P C, Tarko A P, Mannering F L. Tobit analysis of vehicle accident rates on interstate highways[J]. Accident Analysis & Prevention, 2008, 40: 768-775.
38	Guo Y, Li Z, Liu P, et al. Modeling correlation and heterogeneity in crash rates by collision types using full Bayesian random parameters multivariate Tobit model[J]. Accident Analysis & Prevention, 2019, 128: 164-174.
39	Zeng Q, Wen H, Huang H, et al. A Bayesian spatial random parameters Tobit model for analyzing crash rates on roadway segments[J]. Accident Analysis & Prevention, 2017, 100: 37-43.
40	Xu C, Ding Z, Wang C, et al. Statistical analysis of the patterns and characteristics of connected and autonomous vehicle involved crashes[J]. Journal of Safety Research, 2019, 71: 41-47.
41	Chen H, Chen H, Liu Z, et al. Analysis of factors affecting the severity of automated vehicle crashes using XGBoost model combining POI data[J]. Journal of Advanced Transportation, 2020, 2020:No.8881545.
42	Boggs A M, Wali B, Khattak A J. Exploratory analysis of automated vehicle crashes in California: a text analytics & hierarchical Bayesian heterogeneity-based approach[J]. Accident Analysis & Prevention, 2020, 135:No. 105354.
43	涂辉招, 崔航, 鹿畅, 等. 面向自动驾驶路测驾驶能力评估的避险脱离率模型 [J]. 同济大学学报:自然科学版,2020,48(11): 1562-1569.
	Tu Hui-zhao, Cui Hang, Lu Chang, et al. A risk-avoiding disengagement frequency model for assessing driving ability of autonomous vehicles in road testing[J]. Journal of Tongji University (Natural Science),2020,48(11):1562-1569.
44	Kingma D P, Ba J. Adam: a method for stochastic optimization[J]. arXiv preprint arXiv:, 2014.
45	Ordóñez F J, Roggen D. Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition[J]. Sensors, 2016, 16(1): No.e115.
46	Hou Q, Meng X, Leng J, et al. Application of a random effects negative binomial model to examine crash frequency for freeways in China[J]. Physica A: Statistical Mechanics and its Applications, 2018, 509: 937-944.
47	Hair J F, Black W C, Babin B J, et al. Multivariate Data Analysis[M].London: Pearson Education Limited, 2013.

Related Articles 15

[1]	Qing-jin XU,Rui FU,Ying-shi GUO,Fu-wei WU. Roadside prediction method for truck rollover on the curve [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1302-1310.
[2]	Zhao-zheng HU,Xun-pei SUN,Jia-nan ZHANG,Ge HUANG,Yu-ting LIU. Vehicle-infrastructure-map cooperative localization method based on spatial-temporal graph model [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1246-1257.
[3]	Hui-zhao TU,Wan-jin WANG,Peng QIAO,Jing-qiu GUO,Chang LU,Hai-fei WU. Analysis of drivers′ intervention behavior in autonomous truck road testing [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(3): 727-740.
[4]	Can-can SONG,Di-fei JING,Jun-feng XIE,Ke-xin KANG. Analysis on driving behaviors on flat curved sections of highways with advertising signs [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(5): 1345-1354.
[5]	Jin LI,Yu-tong SUN,Xiao-zhong WEI,Yu-ling JIAO. Design of bus priority signal considering flexible lane setting [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 448-456.
[6]	Wen-yong LI,Cong-ruo MA,Qing-wei HU,Cheng-kun LIU,Guan LIAN,Guo-bin GU,Dan ZHOU. Bus speed guidance model based on station capacity limit and section green wave control [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(11): 3088-3103.
[7]	XU Hong-feng, GAO Shuang-shuang, ZHENG Qi-ming, ZHANG Kun. Hybrid dynamic lane operation at signalized intersection [J]. 吉林大学学报(工学版), 2018, 48(2): 430-439.
[8]	WANG Hai-wei, WEN Hui-ying, LIU Min. Experimental evaluation of nighttime driver's physiological characteristics in driving simulator [J]. 吉林大学学报(工学版), 2017, 47(2): 420-428.
[9]	JIANG Gui-yan, LIU Bin, SUI Xiao-yan, MA Ming-fang. Real time information collection of passenger flow in public transportation based on bus IC card charging system [J]. 吉林大学学报(工学版), 2016, 46(4): 1076-1082.
[10]	LI Shi-wu, XU Yi, SUN Wen-cai, WANG Lin-hong, GUO Meng-zhu, CHAI Meng. Pupil diameter based construction conflict self-feedback discrimination method [J]. 吉林大学学报(工学版), 2016, 46(2): 418-425.
[11]	ZHAO Shu-zhi, LIANG Shi-dong, MA Ming-hui, LIU Hua-sheng, ZHU Yong-gang. Real-time queue length estimation at signalized intersection [J]. 吉林大学学报(工学版), 2016, 46(1): 85-91.
[12]	ZHU Jin-cheng, XIAO Feng, SHUAI Bin, LIU Xiao-bo. Impact and feasibility of charging taxis in pricing zone [J]. 吉林大学学报(工学版), 2015, 45(1): 89-96.
[13]	ZHAO Shu-zhi, TIAN Qing-fei, CAO Yang. Transit efficiency network design model based on the restriction of station capacity [J]. 吉林大学学报(工学版), 2011, 41(增刊1): 81-84.
[14]	HU Hong-yu, WANG Qing-nian, QU Zhao-wei, LI Zhi-hui. Spatial pattern recognition and abnormal traffic behavior detection of moving object [J]. 吉林大学学报(工学版), 2011, 41(6): 1598-1602.
[15]	YU De-Xin, ZHANG Mao-Lei, YANG Zhao-Sheng. Dynamic traffic assignment model based on emergency evacuation passageway under the condition of disaster [J]. 吉林大学学报(工学版), 2010, 40(增刊): 138-0141.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

编号	变量名	变量表示	变量解释
1	车道宽度	1	>3.25 m
		2	（2.75，3.25］ m
		3	［0，2.75］ m
2	道路线形	0	直线
2	道路线形	1	曲线
3	道路平整度	0	平整
3	道路平整度	1	一般
4	坡度	0	无坡路段
4	坡度	1	有坡路段
5	限速	1	40 km/h
		2	60 km/h
		3	80 km/h
6	交叉口	0	非交叉口路段
6	交叉口	1	交叉口路段
7	接入点数量	0	无接入点
7	接入点数量	1	有接入点
8	机非分隔带	0	有机非分隔带
8	机非分隔带	1	无机非分隔带
9	道路等级	1	二级公路
		2	主干路
		3	次干路
		4	支路
10	流量等级	1	［0，200］ veh/（h·lane）
		2	（200，350］ veh/（h·lane）
		3	（350，500］ veh/（h·lane）
		4	（500，+∞） veh/（h·lane）
11	大车比例	1	［0，10%］
11	大车比例	2	（10%，100%］
12	天气	0	好天气
12	天气	1	雨雪天气
13	车道数	1	无
		2
		3
		4

项目	城市道路	高快速路
避险脱离占比/%	38	13
非避险脱离占比/%	62	87

变量	Coef.	Std. Err.	t	P>\|t\|	Sig	VIF
年份	-205.9029	22.289 15	-9.24	0.000	***	1.084
车道宽度	67.6387	25.854 07	2.62	0.009	**	1.260
道路线形	-46.5872	29.958 71	-1.56	0.120		1.070
道路平整度	77.310 74	32.798 59	2.36	0.019	*	1.478
坡度	23.264 99	153.3146	0.15	0.879		1.048
限速	69.840 58	14.426 88	4.84	0.000	***	1.890
交叉口	107.9475	22.9303	4.71	0.000	***	1.149
接入点数量	14.854 44	23.880 86	0.62	0.534		1.273
车道数	155.6237	35.821 78	4.34	0.000	***	2.878
机非隔离带	202.6348	33.043 63	6.13	0.000	***	2.169
道路等级	-4.915 709	10.145 39	-0.48	0.628		1.822
流量等级	-19.710 59	12.2432	-1.61	0.108		1.142
大车比例	-43.256 92	29.406 83	-1.47	0.142		1.702
天气	55.610 79	21.388 54	2.60	0.009	**	1.021
间距	41 5496.8	45 034.13	9.23	0.000	***	N/A

Risk factors for autonomous vehicle road testing based on risk-avoiding disengagement

RICH HTML

PDF (PC)