Neural network model for recognition of driving strategies and interaction of drivers in traffic conditions

The paper presents a neural network model for recognizing driving strategies based on the interaction of drivers in traffic flow conditions. The architecture of the model, based on self-organizing map (SOM), consisting of various neural networks based on RBF (Radial Basis Function). The purpose of this work is to describe the architecture and structure of the neural network model, which allows to recognize the strategic features of driving. Our neural network is able to identify the interaction strategies of cars (drivers) in traffic flow conditions, as well as to identify such behavioral patterns of movement that can be correlated with different types of dangerous driving. From the results of the study, it follows that neural networks of the SOM RBF type are able to recognize and classify the types of interactions in traffic conditions based on modeling the analysis of the trajectories of cars. This neural network showed a high percentage of recognition and clear clustering of similar driving strategies.

 

1. Avtomaticheskoe porozhdenie gipotez v intellektual’nykh sistemakh [Automatic generation of hypotheses in intelligent systems.] Sost. E.S. Pankratova, V.K. Finn. Moscow: Librokom, 2009. 526 p.
2. Velikhov E.P., Chernavskii A.V. Intellektual’nye protsessy i modelirovanie [Intellectual processes and modeling]. Moscow: Nauka, 1987. 396 p.
3. Efremov S.B. The model of recognition of driving styles and classification of traffic interaction strategies. Sotsial’naia psikhologiia i obshchestvo [Social Psychology and Society], 2017. Vol. 8, no. 4, pp. 123—133. doi:10.17759/sps.2017080409. (In Russ., аbstr. in Engl.)
4. Efremov S.B. Type of communication between driver and car, based on the augmented reality: “new trend” in building intelligent transportation systems [Elektronnyi resurs]. Sovremennaia zarubezhnaia psikhologiia [Journal of Modern Foreign Psychology], 2017. Vol. 6, no. 1, pp. 6—14. doi:10.17759/jmfp.2017060101. (In Russ., аbstr. in Engl.)
5. Efremov S.B., Kochetova T.V. K voprosu issledovaniya stilisticheskikh i strategicheskikh osobennostei upravleniya transportnym sredstvom [To the question of the study of stylistic and strategic features of driving a vehicle]. Sotsial’naya psikhologiya: voprosy teorii i praktiki. Materialy III Ezhegodnoi nauchno-prakticheskoi konferentsii pamyati M.Yu. Kondrat’eva (Moskva, 10—11 maya 2018 g.) [Social Psychology: Theory and Practice Questions. Materials of the III Annual Scientific and Practical Conference in Memory of M.Yu. Kondratiev.]. Moscow State University of Psychology and Educatioon, Faculty of Social Psychology. 2018, pp. 265—267.
6. Klebel’sberg D. Transportnaya psikhologiya [Transport Psychology]. Moscow: Transport, 1989. 367 p.
7. Klimov E.A. Individual’nyi stil’ deyatel’nosti. Psikhologiya individual’nykh razlichii. Teksty [Individual style of activity. Psychology of individual differences. Texts]. In Yu.B. Gippenreiter, V.Ya. Romanova (eds.). Moscow: Publ. MGU, 1982, pp. 74—77.
8. Kondrat’ev M.Yu., Kochetova T.V. «Traffic psychology»: ot prikladnykh issledovanii k metodologii kompleksnogo izucheniya sovremennoi dorozhno-transportnoi sredy [Traffic psychology: from applied researches to the methodology of integrated study of the modern transport environment]. Sbornik materialov mezhdunarodnoi nauchno-prakticheskoi konferentsii “Chelovek i transport (Psikhologiya. Ekonomika. Tekhnika)” (Sankt-Peterburg, 28—30 iyunya 2012 g.). [ The sourcebook of the international scientifically-practical conference “People and Transport (Psychology. Economics. Technique)”]. Saint-Petersburg: PGUPS, 2012, pp. 119—122.
9. Lobanova Yu.I. Stil’ vozhdeniya: opredelyayushchie faktory, kharakteristiki, napravleniya optimizatsii [Driving style: determining factors, characteristics, directions of optimization]. Rossiiskii gumanitarnyi zhurnal. [Russian Journal of Humanities], 2015. Vol. 4, no. 1, pp. 76—84.
10. Mararitsa L.V., Kazantseva T.V., Pochebut L.G., Sventsitskiy A.L. The contribution of the individual to the group’s social capital: the structure of altruistic investment. Sotsial’naia psikhologiia i obshchestvo [Social Psychology and Society], 2018. Vol. 9, no. 1, pp. 43—66. doi:10.17759/sps.2018090104. (In Russ., аbstr. in Engl.)
11. Osipov G.S. Lektsii po iskusstvennomu intellektu [Lectures on artificial intelligence]. Moscow: Krasand, 2009. 272 p.
12. Petrov V.E. Psikhologicheskii analiz problemy opasnogo stilya upravleniya transportnym sredstvom [Elektronnyi resurs] [Psychological analysis of the problem of dangerous driving style]. Sovremennye nauchnye issledovaniya i innovatsii [Modern scientific research and innovation, 2016, no. 8. URL: http://web.snauka.ru/issues/2016/08/70377 (Accessed: 30.08.2018).
13. Polikarpova M.S. The problem of correlation between the concepts of “violent” and “dangerous driving” in modern national and foreign psychology [Elektronnyi resurs]. Sovremennaia zarubezhnaia psikhologiia [Journal of Modern Foreign Psychology], 2017. Vol. 6, no. 1, pp. 44—52. doi:10.17759/jmfp.2017060106. (In Russ., аbstr. in Engl.)
14. Yadov V.A. Samoregulyatsiya i prognozirovanie sotsial’nogo povedeniya lichnosti: Dispozitsionnaya kontseptsiya [Self-regulation and prediction of social behavior of an individual: Dispositional concept]. M.: TsSPiM, 2013. 376 p.
15. Fujita I. The inferior temporal cortex: architecture, computation, and representation. Journal of Neurocytology, 2002. Vol. 31, Is. 3—5, pp. 359—371.
16. Efremova N., Asakura N., Inui T., Abdikeev N. Inferotemporal network model for 3d object recognition. The proceedings of the International Conference on Complex Medical Engineering IEEE/ICME. 2011, pp. 555—560.
17. Kohonen T. Self-organizing maps. Berlin: Springer-Verlag. 2001. 502 p.
18. Logothetis N., Pauls J. Psychophysical and physiological evidence for viewer-centered object representations in the primate. Cerebral Cortex, 1995. Vol. 5, no. 3, pp. 270—288.
19. Riesenhuber M., Poggio T. Hierarchical models of object recognition in cortex. Nature Neuroscience, 1999. Vol. 2, pp. 1019—1025.
20. Riesenhuber M., Poggio T. Modeling Invariances in Inferotemporal Cell Tuning. Technical Report. MIT. 1998. 6 p.
21. Riesenhuber M., Poggio T. Models of object recognition. Nature Neuroscience. 2000. Vol. 3, pp. 1199–1204.
22. Tokunaga K., Furukawa T. Modular network SOM. Neural Networks. 2009. Vol. 22, pp. 82–90.