考虑风险时空分布特征的跟驰工况行车风险预测

doi:10.19562/j.chinasae.qcgc.2024.05.003

Abstract

Abstract:

Risk prediction of driving is very important for improving the driving safety of intelligent vehicles. In this paper， a car-following risk prediction model （CRPM） is proposed. The deceleration of the vehicle in a car-following process can reflect the driver's cognitive risk， so longitudinal accelerations are taken as the basis for the car-following risk level labeling， and the risk spatiotemporal distribution characteristics based on the anisotropic driving risk field are constructed and used as input of the CRPM. The CRPM extracts the spatial distribution characteristics through Convolutional Neural Network， and processes the temporal dependence relationship by bidirectional Long Short-Term Memory network and attention mechanism， and finally outputs the car-following risk level. The CRPM is trained and tested on the aerial driving dataset AD4CHE. The results show that the CRPM has good prediction accuracy and long advanced prediction time， with a prediction accuracy of 99.67%， and a prediction accuracy of 96.73% within 2 s before the occurrence of risk.

Key words: driving risk prediction, risk spatiotemporal distribution, car-following, aerial data

Dongjian Song,Jian Zhao,Bing Zhu,Jing Tong,Jiayi Han,Bin Liu. Driving Risk Prediction Under Car-Following Conditions Considering Risk Spatiotemporal Distribution Characteristics[J].Automotive Engineering, 2024, 46(5): 766-775.

Figures/Tables 17

CRL	$a x e$ 取值范围/（m·s^-2）	车辆数目	数据帧数
0	$a x e > 0$	35 084	9 927 291
1	$- 0.5 < a x e ≤ 0$	36 933	7 078 844
2	$- 1 < a x e ≤ - 0.5$	13 004	786 153
3	$a x e ≤ - 1$	3 877	137 018

References 27

1	SINGH S. Critical reasons for crashes investigated in the national motor vehicle crash causation survey［J］. Traffic Safety Facts-Crash Stats， 2015.
2	CHIA W M D， KEOH S L， GOH C， et al. Risk assessment methodologies for autonomous driving： a survey［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（10）： 16923-16939。
3	程国柱，王婉琦，王连震，等. 车辆换道行为风险评价方法研究进展［J］. 哈尔滨工业大学学报， 2023， 55（3）： 139-150.
	CHENG G Z， WANG W Q， WANG L Z， et al. Research progress on risk assessment of vehicle lane-changing behavior［J］. Journal of Harbin Institute of Technology， 2023， 55（3）： 139-150.
4	SHI X， WONG Y D， LI M Z F， et al. Key risk indicators for accident assessment conditioned on pre-crash vehicle trajectory［J］. Accident Analysis and Prevention， 2018， 117： 346-356.
5	MAHAJAN V， KATRAKAZAS C， ANTONIOU C. Crash risk estimation due to lane changing a data-driven approach using naturalistic data［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（4）： 3756-3765.
6	ZHANG J B， LEE J， ABDEL-ATY M， et al. Enhanced index of risk assessment of lane change on expressway weaving segments： a case study of an expressway in China［J］. Accident Analysis and Prevention， 2023， 180： 106909.
7	CHEN T Y， SHI X P， WONG Y D. A lane-changing risk profile analysis method based on time-series clustering［J］. Physica A： Statistical Mechanics and Its Applications， 2021， 565： 125567.
8	KATRAKAZAS C， QUDDUS M， CHEN W H. A new integrated collision risk assessment methodology for autonomous vehicles［J］. Accident Analysis and Prevention， 2019， 127： 61-79.
9	GOERLANDT F， RENIERS G. On the assessment of uncertainty in risk diagrams［J］. Safety Science， 2016， 84： 67-77.
10	熊晓夏，陈龙，梁军，等. 基于驾驶员避撞行为的行车风险判别方法的仿真研究［J］. 汽车工程， 2019， 41（2）： 153-160，169.
	XIONG X X， CHEN L， LIANG J， et al. Simulation study on driving risk discrimination based on driver’s collision avoidance behavior［J］. Automotive Engineering， 2019， 41（2）： 153-160，169.
11	CHEN T Y， SHI X P， WONG Y D， et al. Predicting lane-changing risk level based on vehicles’ space-series features： a pre-emptive learning approach［J］. Transportation Research Part C-Emerging Technologies， 2020， 116： 102646.
12	YU S Y， MALAWADE A V， MUTHIRAYAN D， et al. Scene-graph augmented data-driven risk assessment of autonomous vehicle decisions［J］. IEEE Transactions on Intelligent Transportation Systems， 2021， 23（7）： 7941-7951.
13	LIU Q C， LI C， JIANG H B， et al. Transfer learning-based highway crash risk evaluation considering manifold characteristics of traffic flow［J］. Accident Analysis and Prevention， 2022， 168： 106598.
14	WANG Y B， XU W， ZHANG W P， et al. SafeDrive： a new model for driving risk analysis based on crash avoidance［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（3）： 2116-2129.
15	HU H Y， WANG Q， CHENG M， et al. Cost-sensitive semi-supervised deep learning to assess driving risk by application of naturalistic vehicle trajectories［J］. Expert Systems with Applications， 2021， 178： 115041.
16	宋东鉴，朱冰，赵健，等. 基于驾驶行为生成机制的智能车类人行为决策［J］. 汽车工程， 2022， 44（12）： 1797-1808.
	SONG D J， ZHU B， ZHAO J， et al. Human-like behavior decision-making of intelligent vehicles based on driving behavior generation mechanism［J］. Automotive Engineering， 2022， 44（12）： 1797-1808.
17	AZEVEDO-SA H， ZHAO H J， ESTERWOOD C， et al. How internal and external risks affect the relationships between trust and driver behavior in automated driving systems［J］. Transportation Research Part C-Emerging Technologies， 2021， 123： 102973.
18	WANG J Q， HUANG H Y， LI Y， et al. Driving risk assessment based on naturalistic driving study and driver attitude questionnaire analysis［J］. Accident Analysis and Prevention， 2020， 145： 105680.
19	BAO N， CARBALLO A， MIYAJIMA C， et al. Personalized subjective driving risk analysis and prediction［J］. Journal of Robotics and Mechatronics， 2020， 32（3）： 503-519.
20	ZHAO C Q， WANG W S， LI S P， et al. Influence of cut-in maneuvers for an autonomous car on surrounding drivers： experiment and analysis［J］. IEEE Transactions on Intelligent Transportation Systems， 2020， 21（6）： 2266-2276.
21	崔格格，吕超，李景行，等. 数据驱动的智能车个性化场景风险图构建［J］. 汽车工程， 2023， 45（2）： 231-242.
	CUI G G， LV C， LI J X， et al. Data-driven personalized scenario risk map construction for intelligent vehicles［J］. Automotive Engineering， 2023， 45（2）： 231-242.
22	ZHANG Y X， QUAN W， GAO Y L， et al. Aerial dataset for China congested highway & expressway a and its potential applications in automated driving systems development［EB/OL］. TechRxiv. Preprint. https：//doi.org/10.36227/techrxiv.20236698.v1.
23	LI J H， LU C， LI P H， et al. Driver-specific risk recognition in interactive driving scenarios using graph representation［J］. IEEE Transactions on Vehicular Technology， 2023， 72（4）： 4453-4465.
24	WANG J Q， ZHENG Y， LI X F， et al. Driving risk assessment using near-crash database through data mining of tree-based model［J］. Accident Analysis and Prevention， 2015， 84： 54-64.
25	HAN J Y， ZHAO J， ZHU B， et al. Spatial-temporal risk field for intelligent connected vehicle in dynamic traffic and application in trajectory planning［J］. IEEE Transactions on Intelligent Transportation Systems， 2023， 24（3）： 2963-2975.
26	LI L H， GAN J， JI X K， et al. Dynamic driving risk potential field model under the connected and automated vehicles environment and its application in car-following modeling［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（1）： 122-141.
27	OTHERSEN I， PETERMANN-STOCK I， SCHOEMIG N.， et al. Method development and interaction cognitive driver take-over ability after piloted driving［J］. ATZelektronik Worldwide， 2018， 13（2）： 28-33

基本参数	数值
自车平均速度/（m·s^-1）	8.371 4
自车平均加速度/（m·s^-2）	0.112 5
自车与前车平均距离/m	16.231 4
自车与前车平均速度差/（m·s^-1）	-0.183 9

CRL	样本数量	样本占比
0	3 397 026	98.94%
1	27 855	0.81%
2	6 684	0.19%
3	1 852	0.06%

训练设置	具体情况
学习框架	Python TensorFlow 2.0
优化器	Adam
训练硬件	Nvidia Titan RTX
学习率	0.01
Minibatch大小	50
训练回合数	100
训练集样本数	6 281
测试集样本数	1 571

CRL	指标	模型类别
CRL	指标	CRPM	LightGBM	CNN-LSTM
0	精确率	0.893 5	0.899 8	0.883 6
	召回率	0.994 0	0.889 0	0.940 9
	F1分数	0.941 1	0.894 4	0.915 1
1	精确率	0.992 7	0.856 9	0.825 5
	召回率	0.881 5	0.880 0	0.841 0
	F1分数	0.933 8	0.868 3	0.831 6
2	精确率	0.998 5	0.881 7	0.893 3
	召回率	0.997 5	0.879 5	0.829 0
	F1分数	0.998 0	0.880 6	0.860 0
3	精确率	0.997 8	0.928 3	0.912 9
	召回率	0.998 4	0.915 8	0.888 8
	F1分数	0.998 1	0.922 0	0.900 7
准确率		0.967 3	0.890 6	0.876 7

[1]	Xin Shi,Jian Zhu,Xiangmo Zhao,Fei Hui,Junyan Ma. Car-Following Model for Connected Vehicles Based on Multiple Vehicles with State Change Features [J]. Automotive Engineering, 2023, 45(8): 1309-1319.
[2]	Zhu Bing, Li Weinan, Wang Zhen, Zhao Jian, He Rui, Han Jiayi. Identification Strategy of Driving Style Based on Random Forest [J]. , 2019, 41(2): 213-218.

Driving Risk Prediction Under Car-Following Conditions Considering Risk Spatiotemporal Distribution Characteristics

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 27

Related Articles 2

Metrics

Comments

Recommended 0