A Mixture-of-Experts Model for Vehicle Prediction Using an Online Learning Approach

  • Florian MirusEmail author
  • Terrence C. Stewart
  • Chris Eliasmith
  • Jörg Conradt
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11729)


Predicting future motion of other vehicles or, more generally, the development of traffic situations, is an essential step towards secure, context-aware automated driving. On the one hand, human drivers are able to anticipate driving situations continuously based on the currently perceived behavior of other traffic participants while incorporating prior experience. On the other hand, the most successful data-driven prediction models are typically trained on large amounts of recorded data before deployment achieving remarkable results. In this paper, we present a mixture-of-experts online learning model encapsulating both ideas. Our system learns at run time to choose between several models, which have been previously trained offline, based on the current situational context. We show that our model is able to improve over the offline models already after a short ramp-up phase. We evaluate our system on real world driving data.


Vehicle prediction Online learning Long short-term memory Spiking neural networks 


  1. 1.
    Aeberhard, M., et al.: Experience, results and lessons learned from automated driving on Germany’s Highways, 7(1), 42–57. Scholar
  2. 2.
    Altche, F., de La Fortelle, A.: An LSTM network for highway trajectory prediction. In: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), pp. 353–359. IEEE (2017).
  3. 3.
    Bahram, M., Hubmann, C., Lawitzky, A., Aeberhard, M., Wollherr, D.: A combined model- and learning-based framework for interaction-aware maneuver prediction. IEEE Trans. Intell. Transp. Syst. 17(6), 1538–1550 (2016). Scholar
  4. 4.
    Bekolay, T., et al.: Nengo: a python tool for building large-scale functional brain models. Front. Neuroinform. 7(48) (2014).
  5. 5.
    Bonnin, S., Kummert, F., Schmüdderich, J.: A generic concept of a system for predicting driving behaviors. In: 2012 15th International IEEE Conference on Intelligent Transportation Systems, pp. 1803–1808 (2012).
  6. 6.
    Colyar, J., Halkias, J.: US Highway 101 Dataset (2017).
  7. 7.
    Deo, N., Trivedi, M.M.: Convolutional social pooling for vehicle trajectory prediction. CoRR abs/1805.06771 (2018).
  8. 8.
    Deo, N., Trivedi, M.M.: Multi-modal trajectory prediction of surrounding vehicles with maneuver based LSTMs. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 1179–1184. IEEE (2018).
  9. 9.
    DeWolf, T., Stewart, T.C., Slotine, J.J., Eliasmith, C.: A spiking neural model of adaptive arm control. Proc. R. Soc. B 283(48), 20162134 (2016). Scholar
  10. 10.
    Eliasmith, C.: How to Build a Brain: A Neural Architecture for Biological Cognition. Oxford University Press, Oxford (2013)CrossRefGoogle Scholar
  11. 11.
    Gomes, H.M., Barddal, J.P., Enembreck, F., Bifet, A.: A survey on ensemble learning for data stream classification. ACM Comput. Surv. 50(2), 1–36 (2017). Scholar
  12. 12.
    Graf, R., Deusch, H., Seeliger, F., Fritzsche, M., Dietmayer, K.: A learning concept for behavior prediction at intersections. In: 2014 IEEE Intelligent Vehicles Symposium Proceedings, pp. 939–945 (2014).
  13. 13.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). Scholar
  14. 14.
    Hoi, S.C.H., Sahoo, D., Lu, J., Zhao, P.: Online learning: A comprehensive survey abs/1802.02871.
  15. 15.
    Lefèvre, S., Vasquez, D., Laugier, C.: A survey on motion prediction and risk assessment for intelligent vehicles. ROBOMECH J. 1(1), 1 (2014). Scholar
  16. 16.
    Losing, V., Hammer, B., Wersing, H.: Incremental on-line learning: a review and comparison of state of the art algorithms. Neurocomputing 275, 1261–1274 (2018). Scholar
  17. 17.
    Losing, V., Hammer, B., Wersing, H.: Personalized maneuver prediction at intersections. In: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), pp. 1–6. IEEE (2017).
  18. 18.
    Maye, J., Triebel, R., Spinello, L., Siegwart, R.: Bayesian on-line learning of driving behaviors. In: Proceedings of The International Conference in Robotics and Automation (ICRA) (2011).
  19. 19.
    Mirus, F., Blouw, P., Stewart, T.C., Conradt, J.: Predicting vehicle behaviour using LSTMs and a vector power representation for spatial positions. In: 27th European Symposium on Artificial Neural Networks, ESANN 2019, Bruges, Belgium (2019)Google Scholar
  20. 20.
    Polychronopoulos, A., Tsogas, M., Amditis, A., Andreone, L.: Sensor fusion for predicting vehicles’ path for collision avoidance systems, 8(3), 549–562. Scholar
  21. 21.
    Taieb, S.B., Hyndman, R.: Boosting multi-step autoregressive forecasts. In: Xing, E.P., Jebara, T. (eds.) Proceedings of the 31st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 32, pp. 109–117. PMLR.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Research, New Technologies, InnovationsBMW GroupGarchingGermany
  2. 2.Department of Electrical and Computer EngineeringTechnical University of MunichMunichGermany
  3. 3.Applied Brain Research Inc.WaterlooCanada
  4. 4.Department of Computational Science and TechnologyKTH Royal Institute of TechnologyStockholmSweden

Personalised recommendations