Symbolic Regression for Precrash Accident Severity Prediction

  • Andreas Meier
  • Mark Gonter
  • Rudolf Kruse
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8480)


New advanced safety systems like accident-adaptive restraint systems have the potential to improve vehicle safety. However, these systems may require a function predicting the crash severity prior to a collision. This means that only with accident parameters gathered by precrash car sensors the severity of the upcoming collision has to be predicted. In this work, we present the first known approach based on symbolic regression that finds a solution for this challenging problem automatically. For that, we process crash simulation data and apply Prioritized Grammar Enumeration (PGE) for the first time in a real-world application. In the evaluation, we show that the found model is fast, compact and interpretable yet achieving a good prediction performance. We conclude this paper with a discussion and research questions, which may lead to an application of this approach for future, safer vehicles.


Safety System Velocity Curve Electronic Control Unit Symbolic Regression Good Prediction Performance 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abraham, A.: Special Issue: Hybrid Approaches for Approximate Reasoning. Journal of Intelligent and Fuzzy Systems 23(2), 41–42 (2012)MathSciNetGoogle Scholar
  2. 2.
    Angel, A., Hickman, M.: Analysis of the Factors Affecting the Severity of Two-Vehicle Crashes. Ingeniería y Desarollo 24, 176–194 (2008)Google Scholar
  3. 3.
    Cho, K., Choi, S.B., Shin, K., Yun, Y.: A Pre-Crash Discrimination System for an Airbag Deployment Algorithm. In: American Control Conference (ACC), 2010, pp. 6949–6954. IEEE (July 2010)Google Scholar
  4. 4.
    Corchado, E., Woniak, M., Abraham, A., De Carvalho, A.C., Snášel, V.: Editorial: Recent Trends in Intelligent Data Analysis. Neurocomputing 126, 1–2 (2014)CrossRefGoogle Scholar
  5. 5.
    Hansen, N., Ostermeier, A.: Adapting Arbitrary Normal Mutation Distributions in Evolution Strategies: The Covariance Matrix Adaptation. In: Proceedings of International Conference on Evolutionary Computation, pp. 312–317. IEEE (1996)Google Scholar
  6. 6.
    Harding, S., Miller, J.F., Banzhaf, W.: Developments in Cartesian Genetic Programming: self-modifying CGP. Genetic Programming and Evolvable Machines 11(3-4), 397–439 (2010)CrossRefGoogle Scholar
  7. 7.
    Kübler, L., Gargallo, S., Elsäßer, K.: Characterization and Evaluation of Frontal Crash Pulses with Respect to Occupant Safety. In: Airbag. 9th International Symposium and Exhibition on Sophisticated Car Occupant Safety Systems, ICT (2008)Google Scholar
  8. 8.
    Koza, J.R.: Genetic Programming: A Paradigm for Genetically Breeding Populations of Computer Programs to Solve Problems. Stanford University, Department of Computer Science (1990)Google Scholar
  9. 9.
    Kruse, R., Borgelt, C., Klawonn, F., Moewes, C., Steinbrecher, M., Held, P.: Computational Intelligence: A Methodological Introduction. Springer Publishing Company, Incorporated (2013)Google Scholar
  10. 10.
    Marsh IV, J.C., Campbell, K.L., Shah, U.: A Review and Investigation of Better Crash Severity Measures: An Annotated Bibliography. Tech. rep., Highway Safety Research Institute, The University of Michigan (1977)Google Scholar
  11. 11.
    Meier, A., Gonter, M., Kruse, R.: Accelerating Convergence in Cartesian Genetic Programming by Using a New Genetic Operator. In: Proceeding of the 15th Annual Conference on Genetic and Evolutionary Computation Conference, GECCO 2013, pp. 981–988. ACM (2013)Google Scholar
  12. 12.
    Meier, A., Gonter, M., Kruse, R.: Approximation Methods for Velocity Curves Caused by Collisions (Original title: Approximationsverfahren für kollisionsbedingte Geschwindigkeitskurven). In: Proceedings of 23rd Workshop on Computational Intelligence. KIT Scientific Publishing (2013)Google Scholar
  13. 13.
    Miller, J.F., Thomson, P.: Cartesian Genetic Programming. In: Poli, R., Banzhaf, W., Langdon, W.B., Miller, J., Nordin, P., Fogarty, T.C. (eds.) EuroGP 2000. LNCS, vol. 1802, pp. 121–132. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  14. 14.
    Niederer, P.F., Walz, F., Muser, M.H., Zollinger, U.: What is a Severe, What is a Minor Traffic Accident (Original title: Was ist ein “schwerer”, was ist ein “leichter” Verkehrsunfall?). Schweizerische Ärztezeitung 82(28), 1535–1539 (2001)Google Scholar
  15. 15.
    Otte, C.: Safe and interpretable machine learning: A methodological review. In: Moewes, C., Nürnberger, A. (eds.) Computational Intelligence in Intelligent Data Analysis. SCI, vol. 445, pp. 111–122. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  16. 16.
    Pawlus, W., Robbersmyr, K.G., Karimi, H.R.: Performance Evaluation of Feedforward Neural Networks for Modeling a Vehicle to Pole Central Collision. In: Proceedings of the 4th International Conference on Energy and Development - Environment - Biomedicine, pp. 467–472. WSEAS (2011)Google Scholar
  17. 17.
    van Ratingen, M., Williams, A., Castaing, P., Lie, A., Frost, B., Sandner, V., Sferco, R., Segers, E., Weimer, C.: Beyond NCAP: Promoting New Advancements in Safety. In: Proceedings of the 22nd International Technical Conference on the Enhanced Safety of Vehicles (2011)Google Scholar
  18. 18.
    Sala, D.M., Wang, J.T.: Continuously Predicting Crash Severity. In: Proceedings of 18th International Technical Conference on the Enhanced Safety of Vehicles (2003)Google Scholar
  19. 19.
    Schmidt, M., Lipson, H.: Distilling Free-Form Natural Laws from Experimental Data. Science 324(5923), 81–85 (2009)CrossRefGoogle Scholar
  20. 20.
    Schramm, C., Fürst, F., van den Hove, M., Gonter, M.: Adaptive restraint systems - the restraint systems of the future. In: Proceedings of 8th International Symposium Airbag 2006 (2006)Google Scholar
  21. 21.
    Seiffert, U.W., Gonter, M.: Integrated Automotive Safety Handbook. SAE International (2013)Google Scholar
  22. 22.
    Sohnke, T., Sangorrin, J.S., Hötzel, J.: Adaptable Approach of Precrash Functions. In: 5th European Congress on ITS (2005)Google Scholar
  23. 23.
    Teller, A.: Turing Completeness in the Language of Genetic Programming With Indexed Memory. In: Proceedings of the First Conference on Evolutionary Computation. World Congress on Computational Intelligence, pp. 136–141. IEEE (1994)Google Scholar
  24. 24.
    Tingvall, C., Haworth, N.: Vision Zero: an Ethical Approach to Safety and Mobility. In: 6th ITE International Conference Road Safety & Traffic Enforcement: Beyond 2000, pp. 6–7 (1999)Google Scholar
  25. 25.
    Wallner, D., Eichberger, A., Hirschberg, W.: A Novel Control Algorithm for Integration of Active and Passive Vehicle Safety Systems in Frontal Collisions. Journal of Systemics, Cybernetics and Informatics 8(5), 6–11 (2010)Google Scholar
  26. 26.
    Worm, T., Chiu, K.: Prioritized grammar enumeration: Symbolic regression by dynamic programming. In: Proceeding of the 15th Annual Conference on Genetic and Evolutionary Computation Conference, pp. 1021–1028. ACM (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Andreas Meier
    • 1
  • Mark Gonter
    • 2
  • Rudolf Kruse
    • 3
  1. 1.Volkswagen AG, Group ResearchGermany
  2. 2.Volkswagen AGGermany
  3. 3.Faculty of Computer ScienceUniversity of MagdeburgGermany

Personalised recommendations