A Car-Following Model Driven by Combination of Theory and Data Considering Effects of Lane Change of Side Cars

doi:10.12141/j.issn.1000-565X.220448

Abstract

Abstract:

In order to analyze the following behavior of the target vehicle under the influence of lateral vehicle lane change, this study proposed a combination of theory-data driving following model by combining the multi-velocity difference theoretical following model and deep learning method. Firstly, it considered the following vehicle’s characteristics of maintaining a safe distance between forward and lateral vehicles and being affected by vehicle speed difference. And it proposed a two-lane multi-speed difference following(FS-MAVD) model, the parameters of which were calibrated by differential evolution algorithm. Secondly, it constructed a CNN-Bi-LSTM-Attention data-driven car following model. Convolutional neural network layer (CNN) was used to fully extract forward and lateral vehicle traffic features. Bidirectional long and short term memory networks layer (Bi-LSTM) took driver memory effect into account. The Attention mechanism layer was used to assign model weights. Drivers’ memory duration, model training batches and training rounds are trained based on data. Thirdly, considering the wide applicability of the theoretical model and the characteristics of the data-driven model close to the real value and smooth, the study used the optimal weighting method to combine the two models for prediction. Fourthly, the following behavior sample set was established by using the track data of expressway vehicles shot by UAV, and the model was trained and tested. Compared with the prediction effect of LSTM model, Bi-LSTM model, CNN-Bi-LSTM-Attention model and FS-MAVD theoretical model, the prediction accuracy and error of different models for different vehicles were respectively compared. The results show that the acceleration prediction accuracy of the combined model constructed in this paper reaches 97.64%. The root-mean-square error of prediction is as low as 0.027. Compared with other models, the proposed model can better predict acceleration and deceleration of vehicles affected by lane changing of side vehicles, and better analyze the following behavior of target vehicles.

Key words: traffic flow, car following, data-driven model, combination model, prediction, deep learning

CLC Number:

U491.1

ZHAO Jiandong, JIAO Lanxin, ZHAO Zhimin, et al. A Car-Following Model Driven by Combination of Theory and Data Considering Effects of Lane Change of Side Cars[J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 10-19.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Table 1

Table 2

Fig.4

Fig.5

Fig.6

Table 3

Evaluation of forecast results of vehicle 949"

模型	$E R M S$	$E M S$	$E M A$	$S E V$	$R 2$
LSTM	0.076 9	0.005 9	0.054 6	0.986 5	0.977 3
Bi-LSTM	0.063 6	0.004 0	0.048 0	0.990 8	0.984 5
CNN-Bi-LSTM-Attention	0.062 4	0.003 9	0.053 1	0.995 3	0.985 1
理论模型	0.232 7	0.054 1	0.167 3	0.801 8	0.792 4
组合模型	0.057 3	0.003 3	0.049 5	0.994 1	0.987 4

Table 3

Fig.7

References 20

1	BANDO M， HASEBE K， NAKAYAMA A，et al ．Dynamical model of traffic congestion and numerical simulation ［J］．Physical Review.E.Statistical Physics，Plasmas，Fluids，and Related Interdisciplinary Topics，1995，51（2）：1035-1042.
2	HELBING D， TILCH B ．Generlized force model of taffic dynamics ［D］．Physical Review E，1998，58（1）：133-138
3	JIANG R， WU Q， ZHU Z ．Full velocity difference model for a car-following theory［J］．Physical Review E，2001，64（1）：017101/1-4.
4	王涛，高自友，赵小梅．多速度差模型及稳定性分析［J］．物理学报，2006，55（2）：634-640.
	WANG Tao， GAO Ziyou， ZHAO Xiaomei ．Multiple velocity difference model and its stability analysis［J］．Acta Physica Sinica，2006，55（2）：634-640.
5	孙棣华，李永福，田川．基于多前车位置及速度差信息的车辆跟驰模型［J］．系统工程理论与实践，2010，30（7）：1326-1332.
	SUN Dihua， LI Yongfu， TIAN Chuan ．Car-following model based on the information of multiple ahead & velocity difference ［J］．Systems Engineering-Theory & Practice，2010，30（7）：1326-1332.
6	KESTING A， TREIBER M， HELBING D ．General lane-changing model mobil for car-following models［J］．Transportation Research Record：Journal of the Transportation Research Board，1999（1）：86-94.
7	TANG T Q， HUANG H J， GAO Z Y ．Stability of the car-following model on two lanes［J］．Physical Review E Statistical Nonlinear & Soft Matter Physics，2005，72（6）：066124 /1-7.
8	陈漩，高自友，赵小梅，等．反馈控制双车道跟驰模型研究［J］．物理学报，2007，56（4）：2024-2029.
	CHEN Xuan， GAO Ziyou， ZHAO Xiaomei，et al ．Study on the two-lane feedback controled car-following model ［J］．Acta Physica Sinica，2007，56（4）：2024-2029.
9	王玄金．考虑前车换道过程的跟驰模型研究［D］．重庆：重庆大学，2017.
10	刘大为，史忠科．基于侧向车辆影响的跟驰模型建模及仿真［J］．交通信息与安全，2019，37（1）：35-41.
	LIU Dawei， SHI Zhongke ．Modeling and simulation of car-following model based on influences of lateral vehicles ［J］．Journal of Transport Information and Safety，2019，37（1）：35-41.
11	陶鹏飞．考虑侧向车影响的跟驰行为分析与建模［D］．长春：吉林大学，2009.
12	周立军，王殿海，李卫青．人工神经网络及粒子群优化算法在跟驰模型中的应用［J］．吉林大学学报（工学版），2009，39（4）：896-899.
	ZHOU Lijun， WANG Dianhai， LI Weiqing ．Application of artificial neural network and particle swarm optimization algorithm in car-following model［J］．Journal of Jilin University （Engineering and Technology Edition），2009，39（4）：896-899.
13	XIAO W， JIANG R， LI L，et al ．Capturing car-following behaviors by deep learning［J］．IEEE Transactions on Intelligent Transportation Systems，2017，19（3）：910-920.
14	HUANG X， SUN J， SUN J ．A car-following model considering asymmetric driving behavior based on long short-term memory neural networks ［J］．Transportation Research Part C：Emerging Technologies，2018，95：346-362.
15	王梦玉．基于LTE-V车车通信环境下的跟驰模型设计［D］．北京：北京交通大学，2020.
16	YANG X L， WANG P， ZHOU Y，et al ．Platoon trajectories generation：a unidirectional interconnected LSTM-based car-following model ［J］．IEEE Transactions on Intelligent Transportation Systems，2020，23（3）：2071-2081.
17	孙倩，郭忠印．基于长短期记忆神经网络方法的车辆跟驰模型［J］．吉林大学学报（工学版），2020，50（4）：1380-1386.
	SUN Qian， GUO Zhongyin ．Vehicle following model based on long and short-term memory neural network ［J］．Journal of Jilin University（Engineering and Technology Edition），2020，50（4）：1380-1386.
18	BAHDANAU D， CHO K， BENGIO Y ．Neural machine translation by jointly learning to align and translate ［C］∥ Proceedings of International Conference on Learning Representations 2015．San Diego：［s.n.］ 2014：1-15.
19	ROSE S， MARK J ．Simple optimal weighting of cases and controls in case-control studies ［J/OL］．International Journal of Bio-statistics．2008，4（1）：1-24.
20	王雪松，孙平，张晓春，等．基于自然驾驶数据的高速公路跟驰模型参数标定［J］．中国公路学报，2020，33（5）：132-142.
	WANG Xuesong， SUN Ping， ZHANG Xiaochun，et al ．Calibrating car-following models on freeway based on naturalistic driving data ［J］．China Journal of Highway and Transport，2020，33（5）：132-142.

字段名称	取值		取值
车辆号	1 041辆车	速度	0~103.04 m/s
时间	0~332 s，精度为0.04 s	加速度	-34.15~12.31 m/s²
车道号	1~10	横向距离	-3.7~4.8 m
纵向位置	0~381 m	车辆长度	41~151像素
速度	0~28.62 m/s	车辆宽度	20~45像素

车辆号	时间/s	车道号	纵向位置/m	速度/（m·s^-1）	加速度/（m·s^-2）	横向位置/m	前车号	前车纵向位置/m	前车速度/ （m·s^-1）	前车加速度/（m·s^-2）	跟驰间距/m	跟驰速度差/（m·s^-1）	侧方车辆号	侧方车辆速度/（m·s^-1）	侧方车辆加速度/（m·s^-2）	侧方车辆纵向位置/m
9	11.26	6	161.38	17.83	-0.46	0.23	3	201.61	17.95	0.77	40.23	0.12	6	16.92	0.35	180.08
9	11.30	6	162.13	17.83	-0.46	0.25	3	202.35	17.95	0.77	40.23	0.12	6	16.92	0.35	180.78
9	11.34	6	162.87	17.79	-0.46	0.27	3	203.10	18.02	0.84	40.23	0.23	6	16.95	0.50	181.49
9	11.38	6	163.62	17.79	-0.46	0.28	3	203.85	18.02	0.84	40.24	0.23	6	16.95	0.50	182.19

[1]	. Feature-domain Proximal High-Dimensional Gradient Descent Network for Image Compressed Sensing [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(3): 119-130.
[2]	ZHENG Juanyi, DONG Jiahao, ZHANG Qingjue, et al. Reconfigurable Intelligence Surface Channel Estimation Algorithm Based on RDN [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(3): 102-111.
[3]	. Research on Forest Fire Recognition Based on Improved EfficientNet-E Model Based on ECA Attention Mechanism [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 42-49.
[4]	. Dynamic Neighborhood Sampling for Social Recommendation [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 32-41.
[5]	HE Jiapeng, ZHANG Jinyu, CHEN Zhangxing, LIU Chao, WANG Zhongchang, ZHOU Guowei, LI Dayong. Mechanical Properties Degradation Under Fatigue Loading in Pultruded Unidirectional Glass Fiber Reinforced Polymer Composites [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(1): 62-71.
[6]	LI Fang, GUO Weisen, ZHANG Ping, et al.. Prediction Technique for Remaining Useful Life of Bearing Based on Spatial-Temporal Dual Cell State [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 69-81.
[7]	SU Jindian, YU Shanshan, HONG Xiaobin. A Self-Supervised Pre-Training Method for Chinese Spelling Correction [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 90-98.
[8]	LI Jiachun, LI Bowen, LIN Weiwei. AdfNet: An Adaptive Deep Forgery Detection Network Based on Diverse Features [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 82-89.
[9]	WEI Haibin, WEI Dongsheng, JIANG Boyu, et al. Prediction Analysis of Settlement of Existing Road Under Shield Tunneling Based on IPSO-SVR [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 62-71.
[10]	GUO Enqiang, FU Xinsha. Dropped Object Detection Method Based on Feature Similarity Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 30-41.
[11]	LIN Zhijian, DING Yongqiang, YANG Xiuzhi, et al. Parallel Pipeline Hardware Design of Intra Rate-Distortion Optimization Prediction Mode in HEVC [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 95-103.
[12]	YE Feng, CHEN Biao, LAI Yizong. Contrastive Knowledge Distillation Method Based on Feature Space Embedding [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 13-23.
[13]	WANG Yonggang, CHEN Junxian, ZHENG Shaoya, et al. Analysis and Prediction of Rear-End Conflicts on Road Sharp Curves [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(4): 80-87.
[14]	ZHOU Chuhao, LIN Peiqun, YAN Mingyue. Traffic Data Imputation Based on Self-Supervised Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(4): 101-114.
[15]	WANG Qingqing, LIU Zhanqiang, CHENG Yanhai, et al. Hardness Prediction of TC4 Machined Surface Based on the Evolution of Multi-scale Grain Refinement [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(2): 35-46.