Deviant Behavior Simulation in the Vehicles Traffic Flow

Abstract

The paper proposes a simulation computer model of heterogeneous traffic flow based on the cellular automata approach. The model includes three types of the road user agents: human-controlled vehicles, unmanned vehicles, and the deviant vehicles. The traffic dynamics are based on the behavior rules formulated in the improved S-NFS model. Three rules of a deviant agent behavior are proposed and analyzed. Two of them are related to the lane changes and one to the intentional speed reduction. The paper shows that the deviant transport vehicles are primarily influencing the traffic flow at the medium vehicle densities. It considers the problem of detecting deviant behavior in the traffic flows using the neural networks. The study applies a learning sample created using the developed simulation model. Sample observation included data on the tracked vehicle velocity, relative positions and velocities of the adjacent vehicles, as well as information on the lane alterations. These data are organized in the form of matrices making it possible to be efficiently implement them in the neural network architecture. The results obtained demonstrate that neural networks, even with a relatively simple architecture, are classifying efficiently the vehicles in a flow, and are able to identify the deviant behavior, which emphasizes their potential in introducing in the intelligent transport systems

The work was financially supported by the Russian Science Foundation (grant no. 24-21-00306)

Please cite this article in English as:

Bykov N.V., Kostrov M.A., Tovarnov M.S. Deviant behavior simulation in the vehicles traffic flow. Herald of the Bauman Moscow State Technical University, Series Instrument Engineering, 2025, no. 3 (152), pp. 64--87 (in Russ.). EDN: RUPHAG

References

[1] Pan Y., Wu Y., Xu L., et al. The impacts of connected autonomous vehicles on mixed traffic flow: a comprehensive review. Phys. A: Stat. Mech. Appl., 2024, vol. 635, art. 129454. DOI: https://doi.org/10.1016/j.physa.2023.129454

[2] Guo X.-Y., Zhang G., Jia A.-F. Study on mixed traffic of autonomous vehicles and human-driven vehicles with different cyber interaction approaches. Veh. Commun., 2023, vol. 39, art. 100550. DOI: https://doi.org/10.1016/j.vehcom.2022.100550

[3] Abdeen M.A.R., Yasar A., Benaida M., et al. Evaluating the impacts of autonomous vehicles’ market penetration on a complex urban freeway during autonomous vehicles’ transition period. Sustainability, 2022, vol. 14, no. 16, art. 10094. DOI: https://doi.org/10.3390/su141610094

[4] Muhammad T., Kashmiri F.A., Naeem H., et al. Simulation study of autonomous vehicles’ effect on traffic flow characteristics including autonomous buses. J. Adv. Transp., 2020, vol. 2020, no. 1, art. 4318652. DOI: https://doi.org/10.1155/2020/4318652

[5] Baek S.K., Minnhagen P., Bernhardsson S., et al. Flow improvement caused by agents who ignore traffic rules. arXiv preprint arXiv:0901.3513. DOI: https://doi.org/10.48550/arXiv.0901.3513

[6] Devyatkov V.V., Alfimtsev A.N. Selective covariance-based human localization, classification and tracking in video streams from multiple cameras. BIOSTEC 2018-- BIOINFORMATICS, 2018, vol. 3, pp. 81--88. DOI: http://dx.doi.org/10.5220/0006538100810088

[7] Chowdhury M.F., Biplob M.R.A., Uddin J. Real time traffic density measurement using computer vision and dynamic traffic control. ICIEV and icIVPR, 2018, pp. 353--356. DOI: https://doi.org/10.1109/ICIEV.2018.8641039

[8] Buch N., Velastin S.A., Orwell J. A review of computer vision techniques for the analysis of urban traffic. IEEE Trans. Intell. Transp. Syst., 2011, vol. 12, no. 3, pp. 920--939. DOI: https://doi.org/10.1109/TITS.2011.2119372

[9] Popov A.Y., Ibragimov S.V., Malyshev S.A. Multiple objects association system for the smart city. ElConRus, 2021, pp. 2211--2216. DOI: https://doi.org/10.1109/ElConRus51938.2021.9396415

[10] Baulin F.B., Buryi E.V. Feature extraction techniques for LIDAR range profile based object recognition. Comput. Opt., 2021, vol. 45, no. 6, pp. 934--941. DOI: https://doi.org/10.18287/2412-6179-CO-891

[11] Fitasov E.S., Legovtsova E.V., Pal’guev D.A. Experimental estimation of the projection method of the Doppler filtering of radar signals when detecting air objects with low radial velocities. Radiophys. Quantum El., 2021, vol. 64, no. 4, pp. 300--308. DOI: https://doi.org/10.1007/s11141-021-10132-5

[12] Saprykin Y., Ryazntsev V., Smirnov A. Application of neural networks to the analysis of time series data in the recognition of driver fatigue. ITNT, 2021. DOI: https://doi.org/10.1109/ITNT52450.2021.9649427

[13] Hochreiter S., Schmidhuber J. Long short-term memory. Neural Comput., 1997, vol. 9, no. 8, pp. 1735--1780. DOI: https://doi.org/10.1162/neco.1997.9.8.1735

[14] Suyatinov S.I., Buldakova T.I., Vishnevskaya J.A. Identification of situations based on synergetic model. SUMMA, 2021, pp. 509--514. DOI: https://doi.org/10.1109/SUMMA53307.2021.9632207

[15] Sakulin S., Alfimtsev A., Kvitchenko K., et al. Network anomalies detection approach based on weighted voting. IJISP, 2022, vol. 16, no. 1. DOI: https://doi.org/10.4018/IJISP.2022010105

[16] Nagel K., Schreckenberg M. A cellular automaton model for freeway traffic. J. Phys. I France, 1992, vol. 2, no. 12, pp. 2221--2229. DOI: https://doi.org/10.1051/jp1:1992277

[17] Kerner B.S., Klenov S.L. A microscopic model for phase transitions in traffic flow. J. Phys. A: Math. Gen., 2002, vol. 35, no. 3, pp. L31--L43. DOI: https://doi.org/10.1088/0305-4470/35/3/102

[18] Kokubo S., Tanimoto J., Hagishima A. A new cellular automata model including a decelerating damping effect to reproduce Kerner’s three-phase theory. Phys. A: Stat. Mech. Appl., 2011, vol. 390, no. 4, pp. 561--568. DOI: https://doi.org/10.1016/j.physa.2010.10.027

[19] Tanimoto J., Futamata M., Tanaka M. Automated vehicle control systems need to solve social dilemmas to be disseminated. Chaos Solitons Fractals, 2020, vol. 138, art. 109861. DOI: https://doi.org/10.1016/j.chaos.2020.109861

[20] Kukida S., Tanimoto J., Hagishima A. Analysis of the influence of lane changing on traffic-flow dynamics based on the cellular automaton model. Int. J. Mod. Phys. C, 2011, vol. 22, no. 3, pp. 271--281. DOI: https://doi.org/10.1142/S012918311101621X