Influence of Lateral Collision Risk on Merging Behavior of
Weaving Area

doi:10.16097/j.cnki.1009-6744.2021.04.025

Abstract

Abstract: In order to study the merging behavior of vehicles in the interweaving area of ramps of the expressway, an acceleration model of vehicle merging was constructed based on the gradient boosting decision tree (Gradient Boosting Decision Tree, GBDT). Traffic parameters such as distance difference, speed difference and acceleration, which were extracted from the NGSIM vehicle trajectory data of the United States are used as candidate variables. The combined acceleration after 1s is used as the predictor variable. Five-fold cross-training and testing are performed on the model to obtain the best parameter combination of the model. The lateral distance collision time TC is introduced to analyze the merging process and the impact of the mid-to- side collision risk on the confluence acceleration. The study indicates that: the model has higher prediction accuracy compared to the perspective- based stimulus- response model (VASR); the introduction of the variable TC performs better in the three indicators of mean square error (MSE), mean absolute deviation (MAD) and R2 than the original model; among the various influencing variables, the speed difference ΔVPL between the converging vehicle and the leading vehicle in the target lane and the lateral distance collision time TC have the greatest impact on the confluence acceleration, with the relative impact reaching 20.2% and 12.1%, respectively. The study found that the GBDT model can accurately predict the confluence acceleration of vehicles, and deeply explore the nonlinear relationship between the variables and the confluence acceleration. The introduction of the variable TC can effectively improve the accuracy of the model.

Key words: highway transportation, GBDT, merging behavior, merging acceleration, side collision risk

摘要： 为研究高速公路交织区匝道车辆的汇合行为，基于梯度提升决策树(Gradient Boosting Decision Tree, GBDT)构建了交织区汇合加速度模型，利用美国 Next Generation Simulation (NGSIM)车辆轨迹数据提取汇合车辆与周围车辆之间的横纵向距离差、速度差及加速度等交通参数作为候选变量，将1 s后的汇合加速度作为预测变量，对模型进行五重交叉训练和测试，获取模型最佳参数组合，引入横向距离碰撞时间 TC 分析汇合过程中侧向碰撞风险对汇合加速度的影响。研究发现：与基于视角的刺激-反应模型(VASR)相比，本文模型的预测精度更高；引入变量 TC 在均方误差(MSE)、平均绝对偏差(MAD)和R2这3个指标上均优于原模型；在各影响变量之中，汇合车辆与目标车道领车的速度差 ΔVPL 和横向距离碰撞时间 TC 对汇合加速度的影响最大，相对影响程度分别达到20.2%和12.1%。研究发现，GBDT模型能够准确预测车辆汇合加速度，深入挖掘变量和汇合加速度之间的非线性关系，引入变量 TC 能够有效提高模型精度。

关键词: 公路运输, 梯度提升决策树, 汇合行为, 汇合加速度, 侧向碰撞风险

CLC Number:

U491.2

LI Gen, ZHAI Wei, ZHU Xing-bei, YANG Sheng, WU Lan. Influence of Lateral Collision Risk on Merging Behavior of Weaving Area[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(4): 204-210.

李根, 翟伟, 朱兴贝, 杨晟, 邬岚. 侧向碰撞风险对交织区汇合行为的影响[J]. 交通运输系统工程与信息, 2021, 21(4): 204-210.

Add to citation manager EndNote|Ris|BibTeX

URL: http://www.tseit.org.cn/EN/10.16097/j.cnki.1009-6744.2021.04.025

http://www.tseit.org.cn/EN/Y2021/V21/I4/204

References

[1] GIPPS P G. A model for the structure of lane-changing decisions[J]. Pergamon, 1986, 20(5): 403-414.

[2] 张兰芳, 陈程, 张佳妍, 等. 基于自然驾驶数据的高速公路出口换道决策模型[J]. 同济大学学报(自然科学版), 2018, 46(3): 318-325, 333. [ZHANG L F, CHEN C, ZHANG J Y, et al. A highway exit lane changing decision model based on natural driving data[J]. Journal of Tongji University (Natural Science Edition), 2018, 46 (3): 318-325, 333.]

[3] 彭博, 王玉婷, 谢济铭, 等. 城市干线短交织区元胞自动机多级换道决策模型[J]. 交通运输系统工程与信息, 2020, 20(4): 41-48, 70. [PENG B, WANG Y T, XIE J M, et al. Cellular automata multi-level lane changing decision model for urban trunk line short interweaving area[J]. Transportation Systems Engineering and Information, 2020, 20(4): 41-48, 70.]

[4] ZHANG Q, FILEV D, TSENG H E, et al. Addressing mandatory lane change problem with game theoretic model predictive control and fuzzy markov chain[J]. In 2018 Annual American Control Conference (ACC), IEEE, 2018: 4764-4771.

[5] BALAL E, CHEU R L, SARKODIE-GYAN T. A binary decision model for discretionary lane changing move based on fuzzy inference system[J]. Transportation Research Part C, 2016, 67(67): 47-61.

[6] XIE D F, FANG Z Z, JIA B, et al. A data- driven lanechanging model based on deep learning[J]. Transportation Research Part C, 2019, 106(106): 41-60.

[7] 杨达, 苏刚, 吴丹红, 等. 基于社会力的驾驶员换道决策行为建模[J]. 西南交通大学学报, 2018, 53(4): 791- 797. [YANG D, SU G, WU D H, et al. Modeling ofdriver's lane changing decision behavior based on social forces[J]. Journal of Southwest Jiaotong University, 2018, 53(4): 791-797.]

[8] 谷新平, 韩云鹏, 于俊甫. 基于决策机理与支持向量机的车辆换道决策模型[J]. 哈尔滨工业大学学报, 2020, 52(7): 111- 121. [GU X P, HAN Y P, YU J P. Vehicle lane changing decision model based on decision mechanism and support vector machine[J]. Journal of Harbin Institute of Technology, 2020, 52(7): 111-121.]

[9] CHOUDHURY C F, RAMANUJAM V, BEN-AKIVA M E. Modeling acceleration decisions for freeway merges[J]. Transportation Research Record, 2009, 2124(1): 45-57.

[10] ZHENG Z, AHN S, CHEN D, et al. The effects of lanechanging on the immediate follower: Anticipation, relaxation, and change in driver characteristics[J]. Transportation Research Part C, 2013, 26(26): 367-379.

[11] 孙剑, 蒋舜, 欧阳吉祥. 城市快速路驶入匝道瓶颈车辆汇入行为[J]. 同济大学学报(自然科学版), 2015, 43(4): 549-554. [SUN J, JIANG S, OUYANG J X. The behavior of bottleneck vehicles merging into urban expressway on ramp[J]. Journal of Tongji University (Natural Science Edition), 2015, 43(4): 549-554.]

[12] 邓建华, 冯焕焕. 车道分隔方式对驾驶换道行为的影响[J]. 交通运输系统工程与信息, 2019, 19(2): 153- 159. [DENG J H, FENG H H. Influence of lane separation on lane changing behavior[J]. Transportation System Engineering and Information, 2019, 19 (2): 153- 159.]

[13] 徐兵, 刘潇, 汪子扬, 等. 采用梯度提升决策树的车辆换道融合决策模型[J]. 浙江大学学报(工学版), 2019, 53(6): 1171- 1181. [XU B, LIU X, WANG Z Y, et al. Vehicle lane changing fusion decision model using gradient boosting decision tree[J]. Journal of Zhejiang University (Engineering Science Edition), 2019, 53(6): 1171-1181.]

[14] HE Z B, ZHENG L, GUAN W. A simple nonparametric car -following model driven by field data[J]. Transportation Research Part B, 2015, 80(2015): 185- 201

[15] LI G, FANG S, MA J X, et al. odeling merging acceleration and deceleration behavior based on gradientboosting decision tree[J]. Journal of Transportation Engineering, Part A: Systems, 2020, 146(7): 05020005.

[16] WAN X, JIN P J, YANG F, et al. Modeling vehicle interactions during freeway ramp merging in congested weaving section[J]. Transportation Research Record: Journal of the Transportation Research Board, 2014, 2421(1): 82-92.

Influence of Lateral Collision Risk on Merging Behavior of Weaving Area

侧向碰撞风险对交织区汇合行为的影响

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	WANG Ning, ZHANG Jia-rui, ZHAO Jiao. Vehicle Routing Problem of Intercity Transportation Platform for Less-than-truck-load Cargo [J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(2): 163-177.
[2]	TAN Er-long , LI Hong-hai , ZHONG Hou-yue , HUO En-ze , MA Xiao-lei . Estimating Truck Spontaneous Platoon Fuel-saving Potential Based on Trajectory Data [J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(1): 74-84.
[3]	JIA Shu-yan , SONG Yu-tong, YANG Zi-du. Process of Peak Carbon Emissions of Trucks During Operating Activities Based on Growth Curve Function [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 310-318.
[4]	GAN Mi, QING San-dong, LIU Xiao-bo, LI Dan-dan. Review on Application of Truck Trajectory Data in Highway Freight System [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(5): 91-101.
[5]	LI Tao-ying,WANG Ting, ZHANG Yu-qi. Highway Traffic Flow Prediction Model with Multi-features [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(3): 101-111.
[6]	YUAN Fang, YANG Zhen, ZHOU Xiong-feng. Impact of Curve Radius and Spiral Length on Steering Behavior on Two-lane Highway [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(1): 116-123.
[7]	HU Li-wei, HE Yue-ren, LI Yao-ping, MENG Ling, YIN Xiu-fen. Commercial Truck Driving Risk Evaluation Based on Artificial Immune Mechanism [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(1): 149-155.
[8]	JI Xiao-feng, WU Ya-xin, HAO Jing-jing, FANG Rui, HU Cheng-yu. Severity Factors Analysis Model of Traffic Accident on Combined Horizontal and Vertical Alignments [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(6): 197-204.
[9]	. Evaluation of Eco-driving Behavior and Fuel-saving Potential of Large Freight Vehicles [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(6): 253-258.
[10]	DUAN Li-zhen, LUAN Qing-xiong, ZHAO Xin. Improved Statistical Method Measuring Freight Traffic Volume in Regional Road Network [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(4): 28-33.
[11]	LIU Yu, WU Zhi-xin, LI Meng-liang, YU Han-zheng-nan,. Development of China Light-duty Passenger Car Test Cycle [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(3): 233-240.
[12]	HE Yong-ming, PEI Yu-long, RAN Bin. Superhighway Virtual Track System Based on Intelligent Road Button [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(2): 55-60.
[13]	WANG Hai-xing,WANG Xiang-yu,WANG Zhao-xian, LI Xue-dong. Dangerous Driving Behavior Clustering Analysis for Hazardous Materials Transportation Based on Data Mining [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(1): 183-189.
[14]	YANG Tao,WANG Peng, ZHU Ji-ping, ZHAO Jian-dong. Optimization of Lane Number of Highway Toll Station Based on Multiple Payments [J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(5): 212-218.
[15]	LUO Xiao-ling, JIANG Yang-sheng. Vehicle Trajectory Optimization Model for Ramp Based on Connect Automatically Vehicles [J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(4): 94-100.