Driver Maneuvers Inference Through Machine Learning

  • Mauro Maria BaldiEmail author
  • Guido Perboli
  • Roberto Tadei
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10122)


Inferring driver maneuvers is a fundamental issue in Advanced Driver Assistance Systems (ADAS), which can significantly increase security and reduce the risk of road accidents. This is not an easy task due to a number of factors such as driver distraction, unpredictable events on the road, and irregularity of the maneuvers. In this complex setting, Machine Learning techniques can play a fundamental and leading role to improve driving security. In this paper, we present preliminary results obtained within the Development Platform for Safe and Efficient Drive (DESERVE) European project. We trained a number of classifiers over a preliminary dataset to infer driver maneuvers of Lane Keeping and Lane Change. These preliminary results are very satisfactory and motivate us to proceed with the application of Machine Learning techniques over the whole dataset.


Machine learning Driving security Advanced Driver Assistance Systems 



This research was developed under the European Research Project DESERVE, Development Platform for Safe and Efficient Drive, Project reference: 295364, Funded under: FP7-JTI. The authors are grateful to Fabio Tango, Sandro Cumani and Kenneth Morton for the support provided during the project.


  1. 1.
    Mandalia, H.M.: Pattern recognition techniques to infer driver intentions. Technical report DU-CS-04-08, Drexel University (2004).
  2. 2.
    Dogan, U., Edelbrunner, H., Iossifidis, I.: Towards a driver model: preliminary study of lane change behavior. In: Proceedings of the XI International IEEE Conference on Intelligent Transportation Systems, pp. 931–937 (2008)Google Scholar
  3. 3.
    Burzio, G., Guidotti, L., Montanari, R., Perboli, G., Tadei, R.: A subjective field test on lane departure warning function - euroFOT. In: Proceedings of TRA-Transport Research Arena - Europe 2010 (2010)Google Scholar
  4. 4.
  5. 5.
    Calefato, C., Kutila, M., Ferrarini, C., Landini, E., Baldi, M.M., Tadei, R.: Development of cost efficient ADAS tool platform for automotive industry. In: The 22nd ITS World Congress in Bordeaux (France), 5–9 October 2015 (2015)Google Scholar
  6. 6.
    Centro Ricerche Fiat, Orbassano (TO), Italy.
  7. 7.
  8. 8.
    INTEMPORA, Issy-Les-Moulineaux, France.
  9. 9.
    Mandalia, H.M., Salvucci, D.D.: Using support vector machines for lane change detection. In: Proceedings of the Human Factors and Ergonomics Society Annual Meeting, pp. 1965–1969. SAGE Publications (2005)Google Scholar
  10. 10.
    Butz, T., von Stryk, O.: Optimal control based modeling of vehicle driver properties. SAE Technical Paper 2005–01-0420 (2005). doi: 10.4271/2005-01-0420
  11. 11.
    Hayashi, K., Kojima, Y., Abe, K., Oguri, K.: Prediction of stopping maneuver considering driver’s state. In: Proceedings of the IEEE Intelligent Transportation Systems Conference, pp. 1191–1196 (2006)Google Scholar
  12. 12.
    McCall, J., Wipf, D., Trivedi, M., Rao, B.: Lane change intent analysis using robust operators and sparse bayesian learning. IEEE Trans. Intell. Transp. Syst. 8(3), 431–440 (2007)CrossRefGoogle Scholar
  13. 13.
    Salvucci, D.D., Mandalia, H.M., Kuge, N., Yamamura, T.: Lane-change detection using a computational driver model. Hum. Factors 49(3), 532–542 (2007)CrossRefGoogle Scholar
  14. 14.
    Huang, H., Gao, S.: Optimal paths in dynamic networks with dependent random link travel times. Transp. Res. B 46, 579–598 (2012)CrossRefGoogle Scholar
  15. 15.
    Deng, W.: A study on lane-change recognition using support vector machine. Ph.D. thesis, University of South Florida (2013)Google Scholar
  16. 16.
    Ly, M.V., Martin, S., Trivedi, M.M.: Driver classification and driving style recognition using inertial sensors. In: 2013 IEEE Intelligent Vehicles Symposium (IV), pp. 1040–1045 (2013)Google Scholar
  17. 17.
    Lin, N., Zong, C., Tomizuka, M., Song, P., Zhang, Z., Li, G.: An overview on study of identification of driver behavior characteristics for automotive control. Math. Probl. Eng. 2014, 15. Article ID 569109 (2014). doi: 10.1155/2014/569109 Google Scholar
  18. 18.
    Liu, W., Tao, D.: Multiview hessian regularization for image annotation. IEEE Trans. Image Process. 22(7), 2676–2687 (2013)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Ohn-Bar, E., Tawari, A., Martin, S., Trivedi, M.M.: Predicting driver maneuvers by learning holistic features. In: 2014 IEEE Intelligent Vehicles Symposium Proceedings, pp. 719–724 (2014)Google Scholar
  20. 20.
    Jain, A., Koppula, H.S., Raghavan, B., Soh, S., Saxena, A.: Car that knows before you do: anticipating maneuvers via learning temporal driving models (2015).
  21. 21.
    Tipping, M.E.: Sparse Bayesian learning and the relevance vector machine. J. Mach. Learn. Res. 1, 211–244 (2001)MathSciNetzbMATHGoogle Scholar
  22. 22.
    Jang, J.S.R.: Anfis: adaptive-network-based fuzzy inference systems. IEEE Trans. Syst. Man Cybern. 23(3), 665–685 (1993)CrossRefGoogle Scholar
  23. 23.
  24. 24.
    Rabiner, L.R., Juang, B.H.: An introduction to hidden Markov models. IEEE ASSP Mag. 3, 4–16 (1986)CrossRefGoogle Scholar
  25. 25.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  26. 26.
    Tagaki, T., Sugeno, M.: Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Syst. Man Cybern. 15(1), 116–132 (1985)CrossRefzbMATHGoogle Scholar
  27. 27.
    Hsu, C.-W., Chang, C.-C., Lin, C.J.: A practical guide to support vector classification (2010).

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Mauro Maria Baldi
    • 1
    Email author
  • Guido Perboli
    • 1
    • 2
  • Roberto Tadei
    • 1
  1. 1.Politecnico di TorinoTurinItaly
  2. 2.Centre interuniversitaire de recherche sur les reseaux d’entreprise, la logistique et le transport (CIRRELT)MontréalCanada

Personalised recommendations