Car-Following Model Based on Deep Learning and Markov Theory
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 146, Issue 9
Abstract
A car-following (CF) model can reproduce various micro traffic phenomena and plays a crucial role in traffic theory. In this study, we combine Markov theory and a gated recurrent unit (GRU) neural network (NN) to propose a new CF model. Next-generation simulation (NGSIM) data were used to generate the Markov chain and train the GRU-NN. Considering the memory effects, we predicted each vehicle’s state at the next time step by the headways and speeds in the last several time steps. Simulations were used to test the merits of the proposed CF model under some given scenarios. The results indicate that the proposed CF model has high accuracy and can enhance the stability of trajectory prediction in simulation, which provides a new approach for micro traffic simulation.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are available in a repository or online in accordance with funder data retention policies.
NGSIM (2006) Next-generation simulation (http://ngsim.fhwa.dot.gov).
Some or all data, models, or codes that support the findings of this study are available from the corresponding author upon reasonable request.
Code of data processing, training model, and simulation.
Acknowledgments
This work was supported by the National Natural Science Foundation of China (71890971 and 71890970).
References
Aghabayk, K., M. Sarvi, N. Forouzideh, and W. Young. 2014. “Modelling heavy vehicle car-following behaviour in congested traffic conditions.” J. Adv. Transp. 48 (8): 1017–1029. https://doi.org/10.1002/atr.1242.
Ardakani, M. K., and J. Yang. 2016. “Generalized Gipps-type vehicle-following models.” J. Transp. Eng. Part A 143 (3): 04016011. https://doi.org/10.1061/JTEPBS.0000022.
Chen, C., L. Li, J. Hu, and C. Geng. 2010. “Calibration of MITSIM and IDM car-following model based on NGSIM trajectory datasets.” In Proc., 2010 IEEE Int. Conf. on Vehicular Electronics and Safety, 48–53. New York: IEEE. https://doi.org/10.1109/ICVES.2010.5550943.
Chong, L., M. M. Abbas, A. M. Flintsch, and B. Higgs. 2013. “A rule-based neural network approach to model driver naturalistic behavior in traffic.” Transp. Res. Part C 32 (Jul): 207–223. https://doi.org/10.1016/j.trc.2012.09.011.
Colombaroni, C., and G. Fusco. 2014. “Artificial neural network models for car following: Experimental analysis and calibration issues.” J. Intell. Transp. Syst. 18 (1): 5–16. https://doi.org/10.1080/15472450.2013.801717.
Cui, Z., K. Henrickson, S. A. Biancardo, Z. Pu, and Y. Wang. 2020. “Establishing multisource data-integration framework for transportation data analytics.” J. Transp. Eng. Part A 146 (5): 04020024. https://doi.org/10.1061/JTEPBS.0000331.
Dhahir, B., and Y. Hassan. 2019. “Modeling speed and comfort threshold on horizontal curves of rural two-lane highways using naturalistic driving data.” J. Transp. Eng. Part A 145 (6): 04019025. https://doi.org/10.1061/JTEPBS.0000246.
Gazis, D. C., R. Herman, and R. W. Rothery. 1961. “Nonlinear follow-the-leader models of traffic flow.” Oper. Res. 9 (4): 545–567. https://doi.org/10.1287/opre.9.4.545.
He, J., Z. He, B. Fan, and Y. Chen. 2020. “Optimal location of lane-changing warning point in a two-lane road considering different traffic flows.” Physica A 540 (Feb): 123000. https://doi.org/10.1016/j.physa.2019.123000.
He, Z., L. Zheng, and W. Guan. 2015. “A simple nonparametric car-following model driven by field data.” Transp. Res. Part B 80 (Oct): 185–201. https://doi.org/10.1016/j.trb.2015.07.010.
He, Z., L. Zheng, L. Song, and N. Zhu. 2017. “A jam-absorption driving strategy for mitigating traffic oscillations.” IEEE Trans. Intell. Transp. Syst. 18 (4): 802–813. https://doi.org/10.1109/TITS.2016.2587699.
Huang, X., J. Sun, and J. Sun. 2018. “A car-following model considering asymmetric driving behavior based on long short-term memory neural networks.” Transp. Res. Part C 95 (Oct): 346–362. https://doi.org/10.1016/j.trc.2018.07.022.
Jiang, R., Q. Wu, and Z. Zhu. 2001. “Full velocity difference model for a car-following theory.” Phys. Rev. E 64 (1): 017101. https://doi.org/10.1103/PhysRevE.64.017101.
Jiang, Z. Y., S. P. Yu, M. D. Zhou, Y. Q. Chen, and Y. Liu. 2017. “Model study for intelligent transportation system with big data.” Procedia Comput. Sci. 107 (Apr): 157–163. https://doi.org/10.1016/j.procs.2017.03.072.
Kesting, A., and M. Treiber. 2008. “Calibrating car-following models by using trajectory data: Methodological study.” Transp. Res. Rec. 2088 (1): 148–156. https://doi.org/10.3141/2088-16.
Li, C., X. Jiang, W. Wang, Q. Cheng, and Y. Shen. 2016. “A simplified car-following model based on the artificial potential field.” Procedia Eng. 137 (Feb): 13–20. https://doi.org/10.1016/j.proeng.2016.01.229.
Li, L., R. Jiang, Z. He, X. M. Chen, and X. Zhou. 2020. “Trajectory data-based traffic flow studies: A revisit.” Transp. Res. Part C 114 (May): 225–240. https://doi.org/10.1016/j.trc.2020.02.016.
NGSIM (Next Generation Simulation). 2006. “Next generation simulation.” Accessed May 18, 2020. http://ngsim.fhwa.dot.gov.
NHTSA (National Highway Traffic Safety Administration). 2009. “Traffic safety facts vehicle safety research, DOT HS 811 128.” Accessed May 18, 2009. http://www.nhtsa.gov.
Qi, H., and X. Hu. 2020. “Real-time headway state identification and saturation flow rate estimation: A hidden Markov chain model.” Transportmetrica A: Transp. Sci. 16 (3): 840–864. https://doi.org/10.1080/23249935.2020.1722285.
Tang, T. Q., J. G. Li, H. J. Huang, and X. B. Yang. 2014. “A car-following model with real-time road conditions and numerical tests.” Measurement 48 (Feb): 63–76. https://doi.org/10.1016/j.measurement.2013.10.035.
Tang, X., Y. Dai, T. Wang, and Y. Chen. 2019. “Short-term power load forecasting based on multi-layer bidirectional recurrent neural network.” IET Gener. Transm. Distrib. 13 (17): 3847–3854. https://doi.org/10.1049/iet-gtd.2018.6687.
Thiemann, C., M. Treiber, and A. Kesting. 2008. “Estimating acceleration and lane-changing dynamics from next generation simulation trajectory data.” Transp. Res. Rec. 2088 (1): 90–101. https://doi.org/10.3141/2088-10.
Treiber, M., A. Hennecke, and D. Helbing. 2000. “Congested traffic states in empirical observations and microscopic simulations.” Phys. Rev. E 62 (2): 1805. https://doi.org/10.1103/PhysRevE.62.1805.
Wan, N. F., C. Zhang, and A. Vahidi. 2019. “Probabilistic anticipation and control in autonomous car following.” IEEE Trans. Control Syst. Technol. 27 (1): 30–38. https://doi.org/10.1109/TCST.2017.2762288.
Wang, X., R. Jiang, L. Li, Y. Lin, X. Zheng, and F. Y. Wang. 2017. “Capturing car-following behaviors by deep learning.” IEEE Trans. Intell. Transp. Syst. 19 (3): 910–920. https://doi.org/10.1109/TITS.2017.2706963.
Wang, X., R. Jiang, L. Li, Y. L. Lin, and F. Y. Wang. 2019. “Long memory is important: A test study on deep-learning based car-following model.” Physica A 514 (Mar): 786–795. https://doi.org/10.1016/j.physa.2018.09.136.
Wu, Y., H. Tan, X. Chen, and B. Ran. 2019. “Memory, attention and prediction: A deep learning architecture for car-following.” Transportmetrica B: Transp. Dyn. 7 (1): 1553–1571. https://doi.org/10.1080/21680566.2019.1650674.
Xie, D. F., Z. Z. Fang, B. Jia, and Z. He. 2019a. “A data-driven lane-changing model based on deep learning.” Transp. Res. Part C 106 (Sep): 41–60. https://doi.org/10.1016/j.trc.2019.07.002.
Xie, D. F., X. M. Zhao, and Z. He. 2019b. “Heterogeneous traffic mixing regular and connected vehicles: Modeling and stabilization.” IEEE Trans. Intell. Transp. Syst. 20 (6): 2060–2071. https://doi.org/10.1109/TITS.2018.2857465.
Xu, Z., K. X. Yang, H. X. Zhao, and J. L. Li. 2012. “Differences in driving characteristics between normal and emergency situations and model of car-following behavior.” J. Transp. Eng. 138 (11): 1303–1313. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000434.
Xue, Q., K. Wang, J. J. Lu, and Y. Liu. 2019. “Rapid driving style recognition in car-following using machine learning and vehicle trajectory data.” J. Adv. Transp. 2019 (Jan): 9085238. https://doi.org/10.1155/2019/9085238.
Yu, Y., R. Jiang, and X. Qu. 2019. “A modified full velocity difference model with acceleration and deceleration confinement: Calibrations, validations, and scenario analyses.” IEEE Intell. Transp. Syst. Mag. 2 (Apr): 2–16. https://doi.org/10.1109/MITS.2019.2898965.
Zaky, A., W. Gomaa, and A. E. Khamis. 2015. “Car following Markov regime classification and calibration.” In Proc., IEEE 14th Int. Conf. on Machine Learning and Applications, 1013–1018. New York: IEEE. https://doi.org/10.1109/ICMLA.2015.126.
Zhang, X. 2014. “Empirical analysis of a generalized linear multi anticipative car-following model in congested traffic conditions.” J. Transp. Eng. 140 (6): 04014018. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000667.
Zhang, Y. D., C. Pan, J. Sun, and C. Tang. 2018. “Multiple sclerosis identification by convolutional neural network with dropout and parametric ReLU.” J. Comput. Sci. 28 (Sep): 1–10. https://doi.org/10.1016/j.jocs.2018.07.003.
Zhou, G. B., J. Wu, C. L. Zhang, and Z. H. Zhou. 2016. “Minimal gated unit for recurrent neural networks.” Int. J. Autom. Comput. 13 (3): 226–234. https://doi.org/10.1007/s11633-016-1006-2.
Zhou, M. F., X. B. Qu, and X. P. Li. 2017. “A recurrent neural network based microscopic car following model to predict traffic oscillation.” Transp. Res. Part C 84 (Nov): 245–264. https://doi.org/10.1016/j.trc.2017.08.027.
Information & Authors
Information
Published In
Copyright
© 2020 American Society of Civil Engineers.
History
Received: Jan 14, 2020
Accepted: May 14, 2020
Published online: Jul 11, 2020
Published in print: Sep 1, 2020
Discussion open until: Dec 11, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.