高速公路货车换道冲突预测及其影响因素分析

doi:10.13229/j.cnki.jdxbgxb.20221569

摘要/Abstract

摘要：

为研究高速公路上货车的换道冲突特性，降低高速公路货车的换道风险，本文对货车换道行为特征中引发交通冲突的显著因素进行了研究。首先综合考虑时间和空间维度的交通冲突度量指标，提出了货车交通冲突的判定指标，对高速公路上货车换道过程中的交通冲突样本进行了提取；其次基于XGBoost算法对货车换道冲突进行预测并与随机森林（RF）和梯度提升树（GBDT）算法的性能进行对比；最后利用SHAP算法研究了货车的换道特征、车辆间的相对运动状态和交通流因素对货车换道冲突的影响。研究表明：XGBoost模型的预测效果更优，该模型预测货车换道冲突的准确率和F1-score分别为83.87%和84.85%，且货车的换道安全性受原车道和目标车道前车运动状态的影响较大，冲突的发生与货车长度和路段每分钟的交通量呈负相关；在多因素交互影响下，当路段每分钟交通量大于70 pcu时，货车换道时发生冲突的概率随着交通流中货车比例的增加而增大；当车辆长度小于8 m时，货车发生冲突的可能性与沿车道线方向速度呈正相关。

关键词: 交通工程, 高速公路, 货车换道行为, 冲突预测, XGBoost

Abstract:

In order to study the characteristics of lane changing conflicts involving trucks on the expressway， reduce the risk， and explore the significant factors that cause traffic conflicts among lane changing behaviors of trucks. Firstly， this paper considered the traffic conflict measurement indicators of time and space dimensions， proposed judgment indexes， and used the extracted traffic conflict indexes as a category of samples in the conflict prediction model. Secondly， the XGBoost algorithm was adopted to build the prediction model， and its performance was compared with the Random Forest （RF） and Gradient Boosting Decision Tree （GBDT） algorithms. Finally， the SHAP algorithm was used to study the impact of traffic conflicts on truck lane changes， including the lane changing characteristics of trucks， the relative motion state between different vehicles， and traffic flow. The results show that the XGBoost model has a better prediction effect， with an accuracy and F1-score of 83.87% and 84.85%， respectively. The lane changing safety of trucks is greatly affected by the motion status of the preceding vehicle in the original and target lanes， and the occurrence of collision is negatively correlated with the vehicle length and traffic volume of the road section per minute. Under the interaction of multiple factors， when the traffic volume of a section is more than 70 pcu per minute， the probability of collision when trucks change lanes increases with the increase of the proportion of trucks in the traffic flow. When the vehicle length is less than 8 m， the possibility of truck collision is positively correlated with the speed along the lane line.

Key words: traffic engineering, expressway, trucks lane changing behavior, conflict prediction, XGBoost

中图分类号:

U491.31

温惠英,何梓琦,李秋灵,赵胜. 高速公路货车换道冲突预测及其影响因素分析[J]. 吉林大学学报(工学版), 2024, 54(10): 2827-2836.

Hui-ying WEN,Zi-qi HE,Qiu-ling LI,Sheng ZHAO. Traffic conflict prediction and influencing factors analysis of truck lane change on expressway[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(10): 2827-2836.

图/表 15

图1

表1

表2

图2

图3

表3

图4

表4

表5

表6

表7

图5

图6

图7

图8

参考文献 23

1	陈永恒, 王新慧, 曲昭伟, 等. 基于移动瓶颈交通波理论的上坡路段货车对客车干扰建模[J]. 吉林大学学报:工学版, 2014, 44(5): 1290-1295.
	Chen Yong-heng, Wang Xin-hui, Qu Zhao-wei, et al. Modeling of buses interference with trucks based on kinematic wave theory of moving bottlenecks[J]. Journal of Jilin University(Engineering and Technology Edition), 2014, 44(5): 1290-1295.
2	Ahmed M M, Franke R, Ksaibati K, et al. Effects of truck traffic on crash injury severity on rural highways in Wyoming using Bayesian binary logit models[J]. Accident Analysis & Prevention, 2018, 117: 106-113.
3	胥川, 谢琨, 杨迪,等. 货车重量对事故严重程度的影响研究[J]. 交通运输工程与信息学报, 2019, 17(2): 10-15, 22.
	Xu Chuan, Xie Kun, Yang Di, et al. Analysis the impact of truck weight levels on injury severity[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 17(2): 10-15, 22.
4	Uddin M, Huynh N. Injury severity analysis of truck-involved crashes under different weather conditions[J]. Accident Analysis & Prevention, 2020, 141: No.105529.
5	张驰, 胡涛, 侯宇迪,等. 基于制动毂温升的连续下坡货车事故风险评价模型[J]. 华南理工大学学报:自然科学版, 2020, 48(11): 19-29.
	Zhang Chi, Hu Tao, Hou Yu-di, et al. Crash risk evaluation model based on brake heating for trucks under continuous downhill road conditions[J]. Journal of South China University of Technology(Natural Science Edition), 2020, 48(11): 19-29.
6	Hyun K K, Jeong K, Tok A, et al. Assessing crash risk considering vehicle interactions with trucks using point detector data[J]. Accident Analysis & Prevention, 2019, 130: 75-83.
7	戢晓峰, 耿昭师. 山区双车道公路货车碰撞预测的双变量冲突极值模型[J]. 交通运输系统工程与信息, 2022, 22(2): 230-238.
	Ji Xiao-feng, Geng Zhao-shi. Bivariate traffic conflict extreme value model of truck collision prediction on two-lane mountain highway[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(2): 230-238.
8	Doran J W, Linn D M. Proceedings of the first workshop on traffic conflicts[J]. Accident Analysis & Prevention, 1979, 11(4): 317-318.
9	朱顺应, 蒋若曦, 王红, 等. 机动车交通冲突技术研究综述[J]. 中国公路学报, 2020, 33(2): 15-33.
	Zhu Shun-ying, Jiang Ruo-xi, Wang Hong, et al. Review of research on traffic conflict techniques[J]. China Journal of Highway and Transport, 2020, 33(2): 15-33.
10	Wu J, Wen H, Qi W. A new method of temporal and spatial risk estimation for lane change considering conventional recognition defects[J]. Accident Analysis & Prevention, 2020, 148: No.105796.
11	Oh C, Park S, Ritchie S G. A method for identifying rear-end collision risks using inductive loop detectors[J]. Accident Analysis & Prevention, 2006, 38(2): 295-301.
12	Son H D, Kweon Y J, Park B B. Development of crash prediction models with individual vehicular data[J]. Transportation Research Part C: Emerging Technologies, 2011, 19(6): 1353-1363.
13	Wu Y, Abdel-Aty M, Cai Q, et al. Developing an algorithm to assess the rear-end collision risk under fog conditions using real-time data[J]. Transportation Research Part C: Emerging Technologies, 2018, 87: 11-25.
14	Chen Q, Gu R, Huang H, et al. Using vehicular trajectory data to explore risky factors and unobserved heterogeneity during lane-changing[J]. Accident Analysis & Prevention, 2021, 151: No.105871.
15	Park H, Oh C, Moon J, et al. Development of a lane change risk index using vehicle trajectory data[J]. Accident Analysis & Prevention, 2018, 110: 1-8.
16	ISO. 2008-17387. Intelligent transport systems-lane change decision aid systems (LC )-Performance requirements and test procedures[S].
17	Chen T, Guestrin C. XGBoost: a scalable tree boosting system[C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, 2016: 785-794.
18	Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
19	Friedman J H. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2001, 29(5): 1189-1232.
20	Krajewski R, Bock J, Kloeker L, et al. The highD dataset: a drone dataset of naturalistic vehicle trajectories on German highways for validation of highly automated driving systems[C]∥IEEE International Conference on Intelligent Transportation Systems(ITSC),Maui, USA, 2018: 2118-2125.
21	, 公路路线设计规范 [S]. 北京:人民交通出版社, 2017.
22	. 收费公路车辆通行费车型分类 [S].
23	Lundberg S M, Erion G G, Lee S I. Consistent individualized feature attribution for tree ensembles[J/OL].[2020-05-18]. arXiv preprint arXiv:, 2018.

相关文章 15

[1]	周荣贵,高沛,李雨璇,周建. 基于轨迹数据的高速公路小客车异常驾驶行为[J]. 吉林大学学报(工学版), 2024, 54(9): 2581-2587.
[2]	何永明,权聪,魏堃,冯佳,万亚楠,陈世升. 超高速公路车路协同路侧单元感知融合方法[J]. 吉林大学学报(工学版), 2024, 54(7): 1923-1934.
[3]	马庆禄,闫浩,聂振宇,李杨梅. 匝道合流区智能网联车辆协同控制方法[J]. 吉林大学学报(工学版), 2024, 54(5): 1332-1346.
[4]	许清津,付锐,郭应时,吴付威. 载货汽车弯道侧翻路侧预测方法[J]. 吉林大学学报(工学版), 2024, 54(5): 1302-1310.
[5]	蒲云,徐银,刘海旭,谭一帆. 考虑多车影响的智能网联车跟驰模型[J]. 吉林大学学报(工学版), 2024, 54(5): 1285-1292.
[6]	曹倩,李志慧,陶鹏飞,李海涛,马永建. 面向交通事故检测及预防的异质传感器布设方法[J]. 吉林大学学报(工学版), 2024, 54(4): 969-978.
[7]	赵晓华,刘畅,亓航,欧居尚,姚莹,郭淼,杨海益. 高速公路交通事故影响因素及异质性分析[J]. 吉林大学学报(工学版), 2024, 54(4): 987-995.
[8]	邬岚,赵乐,李根. 基于方差异质性随机参数模型的汇合行为分析[J]. 吉林大学学报(工学版), 2024, 54(4): 883-889.
[9]	张鑫,胡启洲,何君,吴啸宇. 考虑交通梗塞的合流区交通状况诊断[J]. 吉林大学学报(工学版), 2024, 54(2): 478-484.
[10]	张卫华,刘嘉茗,解立鹏,丁恒. 网联混合环境快速路交织区自动驾驶车辆换道模型[J]. 吉林大学学报(工学版), 2024, 54(2): 469-477.
[11]	徐进,陈正欢,廖祺硕,郑展骥,张河山. 基于心电数据的高速公路高密度互通立交驾驶负荷[J]. 吉林大学学报(工学版), 2024, 54(10): 2807-2818.
[12]	潘义勇,吴静婷,缪炫烨. 老年驾驶员事故严重程度影响因素时间不稳定性分析[J]. 吉林大学学报(工学版), 2024, 54(10): 2819-2826.
[13]	高海龙,徐一博,刘坤,李春阳,卢晓煜. 基于多源数据融合的高速公路路网短时交通流参数实时预测[J]. 吉林大学学报(工学版), 2024, 54(1): 155-161.
[14]	杜筱婧,姚荣涵. 智能网联公交车出站强制换道的演化博弈机制[J]. 吉林大学学报(工学版), 2024, 54(1): 124-135.
[15]	岳昊,张琦悦,杨子玉,任孟杰,张旭. 拥堵空间排队的静态交通流分配迭代加权算法[J]. 吉林大学学报(工学版), 2024, 54(1): 136-145.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	类型一：小、中型货车	类型二：大型货车	类型三：特大型货车
样本个数/个	3 676	2 411	8 683
上边界/m	4.55	10.81	15.36
下边界/m	10.71	15.31	23.24
聚类中心/m	8.44	13.07	17.59

车辆类型	车长/m
中型货车	6~12
大型货车	12~18
特大型货车	18~24

	序号	变量符号	描述性信息
换道车辆信息	1	xVelocity	沿车道线速度
	2	yVelocity	垂直车道线速度（向左为正，向右为负）
	3	xAcceleration	沿车道线方向加速度
	4	yAcceleration	垂直车道线方向加速度
	5	length	车辆长度
周围车辆信息	6	F1_vd	f₁与换道车的速度差
	7	B1_vd	b₁与换道车的速度差
	8	F2_vd	f₂与换道车的速度差
	9	B2_vd	b₂与换道车的速度差
	10	F1_distance	f₁与换道车的间距
	11	B1_distance	b₁与换道车的间距
	12	F2_distance	f₂与换道车的间距
	13	B2_distance	b₂与换道车的间距
	14	F1_type	f₁车辆类型（1小型客车；2大型客车；3中型货车；4大型货车；5特大型货车）
	15	B1_type	b₁的车辆类型
	16	F2_type	f₂的车辆类型
	17	B2_type	b₂的车辆类型
交通流信息	18	volume	路段每分钟交通量
交通流信息	19	Percentage of truck	交通流中货车的占比

模型参数	数值
n_estimators	50
eta	0.3
max_depth	3
min_child_weight	3
gamma	0.4
subsample	1
colsample_bytree	1
scale_pos_weight	1.3

车辆类型	TTC最小值/s
车辆类型	f₁	b₁	f₂	b₂
中型货车	6.10	4.18	8.11	6.86
大型货车	4.04	6.09	14.96	4.37
特大型货车	10.25	13.84	21.07	7.77