网联车对抗神经网络跟驰模型

doi:10.19562/j.chinasae.qcgc.2021.02.005

Abstract

Abstract:

In view of the poor real?time performance and safety as the responses of connected and autonomous vehicles （CAVs） to the speed change of leading vehicle and the low stability of CAV platoon under the current mixed traffic flow situation， a generative adversarial nets vehicle following model （GANVFM） composed of generation model and discrimination model is proposed for CAVs. The generation model extracts the vehicle flowing parameters such as the leading vehicle speed， the following vehicle speed and the vehicle spacing to calculate the generated acceleration， while the discrimination model calculates the similarity of the acceleration parameters generated by generation model and updates both the generation and discrimination models by updating function. Then the real?time performance and safety of CAVs and the stability of vehicle platoon are analyzed by using mean square deviation $σ$ for speed and acceleration， rear?end collision predicting factor $γ n$ and vehicle following state factor $φ n$ as corresponding indicators. The results show that the GANVFM has the smallest $γ n$ and $σ$ ， and the real?time performance and safety of GANVFM to the speed change of leading vehicle are high. With the increase of the permeability rate $δ$ of CAV_S， the $φ n$ reduces， the fleet length shortens， and the fleet stability improves.

Key words: mixed traffic flow, penetration rate of CAVs, generative adversarial network, vehicle following model

Jun Liang,Jun Wang,Yunqing Yang,long Chen,Chaofeng Pan,Guangquan Lu. A Connected and Autonomous Vehicle Following Model Based on Generative Adversarial Network[J].Automotive Engineering, 2021, 43(2): 189-195.

Figures/Tables 12

方法	评价参数	渗透率δ
方法	评价参数	50%	37.5%	25%
传统车辆	ξ	21.1%	18.4%	15%
	$σ α$	0.194 1	0.196 5	0.212 3
	$σ v$	0.081 6	0.095 4	0.145 7
	γ_n	0.517 6	0.591 7	0.645 1
	$φ n$	1.361 8	1.239 4	1.127 3
GANVFM- CAV	$σ α$	0.128 0	0.132 4	0.149 1
	$σ v$	0.019 6	0.028 7	0.036 9
	γ_n	0.100 9	0.105 1	0.109 4
	$φ n$	2.406 7	2.291 7	2.145 4

References 29

1	PARKINSON S， WARD P， WILSON K， et al. Cyber threats facing autonomous and connected vehicles：future challenges［J］. IEEE Transactions on Intelligent Transportation System， 2017， 18（11）：2898-2915.
2	QIN Y， WANG H. Analytical framework of string stability of connected and autonomous platoons with electronic throttle angle feedback［J］. Transportmetrica A：Transport Science， 2018.
3	QIN Y， WANG H， RAN B. Stability analysis of connected and automated vehicles to reduce fuel consumption and emissions［J］. Journal of Transportation Engineering， Part A：Systems， 2018， 144（11）：4001-4028.
4	柴琳果，蔡伯根，王化深，等. 车联网关键指标对车辆安全影响仿真测试方法［J］. 汽车工程， 2017， 39（11）：1316-1324.
	CHAI L G， CAI B G， WANG H S， et al. A simulation scheme for testing the effects of key indicators of the internet of vehicles on vehicle safety［J］. Automotive Engineering， 2017， 39（11）：1316-1324.
5	PAN D， ZHENG Y， QIU J，et al. Synchronous control of vehicle following behavior and distance under the safe and efficient steady⁃following state：two case studies of high⁃speed train following control［J］. IEEE Transactions on Intelligent Transportation Systems， 2018， 19（5）：1445-1456.
6	RO J W， ROOP J L， RANJITKAR P. A formal approach for modeling and simulation of human car⁃following behavior ［J］. IEEE Transactions on Intelligent Transportation Systems， 2018， 2（19）：639-648.
7	WANG F J， DAI M W， SUN L T. Mixed distribution model of vehicle headway based on multiclass car following［J］. Journal of Zhejiang University， 2015， 49（7）：1288-1294.
8	袁伟，付锐，马勇，等. 基于高速实车驾驶数据的驾驶人跟车模型研究［J］. 汽车工程， 2015， 37（6）：71-77.
	YUAN W， FU R， MA Y， et al. A study on driver’s vehicle⁃following model based on high speed real driving data［J］. Automotive Engineering， 2015， 37（6）：71-77.
9	YANG D， ZHU L， WU D， et al. A novel car⁃following control model combining machine learning and kinematics models for automated vehicles［J］. IEEE Transactions on Intelligent Transportation Systems， 2019， 20（6）：1991-2000.
10	KENDZIORRA A， WAGNER P， TOLEDO T. A stochastic car following model［J］. Transportation Research Procedia， 2016， 5（1）：198-207.
11	XIANG R Z， WANG J M. A stochastic driver pedal behavior model incorporating road information［J］. IEEE Transactions on Human-Machine Systems， 2017（99）：1-11.
12	QIAN Y S， ZENG J W， WANG N. A traffic flow model considering influence of car⁃following and its echo characteristics［J］. Nonlinear Dynamics， 2017（4）：1-11.
13	GUO H F， YUAN X L， XU D W. Selection of measures of performance on calibrating parameters in car following models［J］. China Journal of Highway and Transport， 2017， 30（1）：103-110.
14	张金辉，李克强，罗禹贡，等. 基于贝叶斯网络的联网环境中跟车工况下的前车运动状态预测［J］. 汽车工程， 2019， 41（3）：10-16，39.
	ZHANG J H， LI K Q， LUO Y G， et al. Prediction of preceding car motion under car⁃following scenario in the internet of vehicle based on Bayesian network［J］. Automotive Engineering， 2019， 41（3）：10-16，39.
15	郭艳君，鲁玉萍，张运虎. BP神经网络跟车模型优化［J］. 中国安全科学学报， 2016， 26（3）：107-112.
	GUO Y J， LU Y P， ZHANG Y H. Optimization of BP neural network based model for car following［J］. China Safety Science Journal， 2016， 26（3）：107-112.
16	DING D D， SUN L， CHEN S. A car⁃following model coupling machine learning and dynamic［J］. Journal of Transportation Systems Engineering & Information Technology， 2017， 17 （6）：33-39.
17	KUEFLER A， MORTON J， WHEELER T， et al. Imitating driver behavior with generative adversarial networks［C］. 2017： IEEE Intelligent Vehicles Symposium （IV）， 2017： 204-211.
18	ZHANG H， BENJAMIN S， HU S C. Synthesis of high-quality visible faces from polarimetric thermal faces using fenerative adversarial networks［J］. International Journal of Computer Vision， 2019（6）：845–862.
19	REED S， AKATA Z， YAN X， et al. Generative adversarial text to image synthesis［J］. Proceedings of the 33rd International Conference on Machine Learning， 2016， 48（10）：1060-1069.
20	WANG Y. 3D auto⁃context⁃based locality adaptive multi-modality GANs for PET synthesis［J］. IEEE Transactions on Medical Imaging， 2019， 38（6）：1328-1339.
21	WEN S， LIU W， YANG Y. Generating realistic videos from keyframes with concatenated GANs［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2019， 29（8）：2337-2348.
22	LIU J， QU F， HONG X， et al. A small⁃sample wind turbine fault detection method with synthetic fault data using generative adversarial nets［J］. IEEE Transactions on Industrial Informatics， 2019， 15（7）：3877-3888.
23	安树科，徐良杰，陈国俊. 基于车路协同技术的信号交叉口改进车辆跟驰模型［J］. 东南大学学报， 2020， 50（1）：169-174.
24	蒋阳升，胡蓉，姚志洪. 智能网联车环境下异质交通流稳定性及安全性分析［J］. 北京交通大学学报. 2020，44（1）：27-33.
25	MATEOS D M， RIVEAUD L E， LAMBERTI P W. Detecting dynamical changes in time series by using the Jensen Shannon Divergence［J］. Chaos， 2017， 27（8）：83-118.
26	LI J， SHANG P， ZHANG X. Time series irreversibility analysis using Jensen–Shannon divergence calculated by permutation pattern［J］. Nonlinear Dynamics， 2019， 96（4）：2637-2652.
27	ELFWING S， UCHIBE E， DOYA K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning［J］. Neural Network， 2018， 107（1）：3-11.
28	BRECHT B， THERRIAULT D， WEIMERSKIRCH A， et al. A security credential management system for V2X communications［J］. IEEE Transactions on Intelligent Transportation System， 2018， 67（6）：3850-3871.
29	KUMARI P， CHOI N， HEATH R W. IEEE 802.11ad-based radar：an approach to joint vehicular communication-radar system［J］. IEEE Transactions on Vehicle Technology， 2018， 67（4）：3012-3027.

[1]	WANG Dan, LIU Zhong-Chang, TIAN Jing, HAN Yong-Qiang, TAN Man-Zhi. [J]. , 2016, 38(12): 1415 -1419 .
[2]	KONG Xiang-Dong, ZHANG Zhen-Dong, XIE Nai-Liu, CHENG Qiang, YIN Cong-Bo. [J]. , 2016, 38(12): 1471 -1476 .
[3]	LI Ling, MA Li, MOU Yu, XU Chao, LI Wen-Ru, SHI Shu-Ming. [J]. , 2016, 38(12): 1508 -1514 .
[4]	GAO Ji-Dong, GAO Bo-Lin, XIE Shu-Gang. [J]. , 2016, 38(12): 1515 -1520 .
[5]	QIN Xiao-Hui, WANG Jian-Qiang, XIE Bo-Yuan, HU Man-Jiang, LI Ke-Qiang. [J]. , 2017, 39(1): 73 -78 .
[6]	SU Chang, FU Li-Ming, WEI Jun, CAO Yue, HUANG Lei, LI Shuo. [J]. , 2017, 39(1): 35 -40 .
[7]	ZHANG Jian, ZHOU Dao-Kui, TONG Rui, QI Hao-Chen. [J]. , 2017, 39(1): 47 -51 .
[8]	ZHENG Wei. [J]. , 2017, 39(1): 107 -112 .
[9]	SHAO Shi-Ping, HUANG Ju-Hua, CAO Ming. [J]. , 2017, 39(2): 200 -205 .
[10]	Chen-Xin, FENG Xiao, SHEN Chuan-Liang, WANG Shuo, HU Cui-Song, LI Yan-Yang, YANG Chang-Hai-　. [J]. , 2017, 39(2): 206 -213 .

项目	均方差σ_v	追尾预测因子γ_n
实验员操作	4.082 4	0.317 6
BP模型预测	0.286	0.135 5
LC-CF模型预测	0.106 3	0.117 6
GANVFM预测	0.036 9	0.109 4

序号	节点 a		节点 b		节点 c
序号	v_n+1/ (m·s^-1)	D/m	v_n+1/ (m·s^-1)	D/m	v_n+1/ (m·s^-1)	D/m
C₂	16.67	13.72	20.55	17.87	17.72	14.95
C₃	16.69	14.06	20.62	17.99	17.67	15.07
C₄	17.91	16.53	20.83	23.17	17.56	17.34
C₅	17.63	17.96	20.79	24.63	17.29	17.68
C₆	16.59	18.67	20.47	24.78	17.15	17.88
C₇	16.45	19.02	20.12	24.59	17.62	16.94
C₈	16.39	14.46	19.94	18.06	17.85	15.31
C₉	16.32	13.81	19.76	18.65	17.97	14.86

序号	节点 a		节点 b		节点 c
序号	v_n+1/ (m·s^-1)	D/m	v_n+1/ (m·s^-1)	D/m	v_n+1/ (m·s^-1)	D/m
C₂	15.46	15.26	20.28	24.97	17.08	18.61
C₃	15.4	13.19	20.31	17.61	17.36	15.36
C₄	15.03	13.29	20.42	18.05	17.36	15.49
C₅	14.89	15.67	20.49	23.76	16.98	18.94
C₆	14.7	15.76	20.92	23.67	17.16	17.68
C₇	14.63	16.09	20.73	24.64	17.35	17.59
C₈	14.59	13.57	20.64	17.96	17.44	15.31
C₉	14.56	15.17	20.55	20.31	17.54	17.83

序号	节点 a		节点 b		节点 c
序号	v_n+1/ (m·s^-1)	D/m	v_n+1/ (m·s^-1)	D/m	v_n+1/ (m·s^-1)	D/m
C₂	18.39	20.96	20.56	23.49	17.5	20.17
C₃	18.62	18.07	20.72	19.54	17.56	17.97
C₄	18.18	18.21	20.83	19.29	17.42	17.78
C₅	18.2	20.67	20.3	24.17	18.08	20.26
C₆	18.12	20.96	20.54	24.06	18.14	20.46
C₇	17.86	20.61	20.84	23.67	18.19	20.17
C₈	17.75	20.87	20.49	23.78	18.25	21.00
C₉	17.62	21.01	20.35	24.21	18.31	20.68

A Connected and Autonomous Vehicle Following Model Based on Generative Adversarial Network

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 29

Related Articles 1

Metrics

Comments

Recommended 10