Real-Time Computation of Strategies of Differential Games with Applications to Collision Avoidance

  • Rainer Lachner
  • Michael H. Breitner
  • Hans J. Pesch
Part of the International Series of Numerical Mathematics book series (ISNM, volume 124)


Contemporary developments of on-board systems for automatic or semiautomatic driving include car collision avoidance. For this purpose a worst case approach based on pursuit-evasion differential games is investigated. On a freeway a correct driver (evader) is faced with a wrong driver (pursuer) ahead. The correct driver tries to avoid collision against all possible maneuvers of the wrong driver and additionally tries to stay on the freeway. The representation of an optimal collision avoidance strategy along a lot of optimal paths is used to synthesize implementations with neural networks. Examples of simulations which proved satisfactory performance of the on-board collision avoidance system against various typical maneuvers of wrong drivers are presented.


Optimal Path Collision Avoidance Differential Game Multilayer Feedforward Network Collision Avoidance System 
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]
    Anderson, J. A.: An Introduction to Neural Networks. MIT Press, Cambridge, Massachusetts, 1995.zbMATHGoogle Scholar
  2. [2]
    Annema, A. J.: Feedforward Neural Networks: Vector Decomposition Analysis, Modelling and Analog Implementation. Kluwer, Boston, Massachusetts, 1995.Google Scholar
  3. [3]
    Başar, T.; Olsder, G. J.: Dynamic Noncooperative Game Theory. Academic Press, London 1982and 1995 (2. edition).zbMATHGoogle Scholar
  4. [4]
    Blum, E. K.; Li, L. K.: Approximation Theory and Feedforward Networks, Neural Networks 4 (1990).Google Scholar
  5. [5]
    Boulter, J.; Maher, D.; Aburdene, M. F.: Collision Avoidance Using Ultrasonic Waves. Report, Bucknell University, Department of Electrical Engineering, Lewisburg, Pennsylvania 17837, 1994.Google Scholar
  6. [6]
    Breitner, M. H.: Robust optimale Rückkopplungssteuerungen gegen unvorhersehbare Einflüsse: Differentialspielansatz, numerische Berechnung und Echtzeitapproximation. Ph. D. thesis, Technische Universität Clausthal, Institut für Mathematik, Nr. 596, VDI-Verlag, VDI Fortschritt-Bericht, Reihe 8 “Meß-, Steuerungs-und Regelungstechnik”, Düsseldorf 1996.Google Scholar
  7. [7]
    Breitner, M. H.; Pesch, H. J.: Reentry Trajectory Optimization under Atmospheric Uncertainty as a Differential Game. Annals of the International Society of Dynamic Games 1 (1994). URL:
  8. [8]
    Breitner, M. H.; Pesch, H. J.; Grimm, W.: Complex Differential Games of Pursuit-Evasion Type with State Constraints, Necessary Conditions for Optimal Open-Loop Strategies (Part 1) and Numerical Computation of Optimal Open-Loop Strategies (Part 2). Journal of Optimization Theory and Applications 78 (1993).Google Scholar
  9. [9]
    Chachich, A. C.: Collision Avoidance and Automated Traffic Management Sensors. Proceedings 2592 of a Conference in Philadelphia, October 22th — 26th, 1995. International Society for Optical Engineering (SPIE), P. 0. B. 10, Bellingham, Washington 98227-0010. URL: Scholar
  10. [10]
    Chini, C.: Numerische Berechnung optimaler Ausweichmanöver mit einem Differentialspielansatz und Neuronalen Netzen. Diploma thesis, Technische Universität München, Mathematisches Institut, München 1994.Google Scholar
  11. [11]
    Gallant, S. I.: Neural Network Learning and Expert Systems. MIT Press, Cambridge, Massachusetts, 1993.zbMATHGoogle Scholar
  12. [12]
    Galperin, E. A.: The Cubic Algorithm for Global Games with Application to Pursuit-evasion Games. Computers and Mathematics with Applications 26 (1993).Google Scholar
  13. [13]
    Harris, C. J.; An, P. E.; Matthews, N. D.; Roberts, J. M.: Intelligent Collision Avoidance, Control and Guidance. Report, Prometheus (Programme for European traffic flow with highest efficiency and unprecedented safety), University of Southampton, Department of Electronics and Computer Sciences, Southampton SO17 1BJ, 1995. To appear in IMechE Autotech ′95.Google Scholar
  14. [14]
    Hautzinger, H.; Heidemann, D.; Krämer, B.: Fahrleistungserhebung 1990 — Inlandsfahrleistung und Kfz-Unfallrisiko in der Bundesrepublik Deutschland (alte Bundesländer). Bericht der Bundesanstalt für Straßenwesen M20, Wirtschaftsverlag NW/Verlag für neue Wissenschaft, Bremerhaven 1993.Google Scholar
  15. [15]
    Hautzinger, H.; Tassaux-Becker, B.; Hamacher, R.: Verkehrsunfallrisiko in Deutschland. Bericht der Bundesanstalt für Straßenwesen M58, Wirtschaftsverlag NW/Verlag für neue Wissenschaft, Bremerhaven 1996.Google Scholar
  16. [16]
    Hornik, K.: Approximation Capabilities of Multilayer Feedforward Networks. Neural Networks 4 (1991).Google Scholar
  17. [17]
    Hornik, K.; Stinchcombe, M.; White, H.: Multi-Layer Feedforward Networks are Universal Approximators. Neural Networks 2 (1989).Google Scholar
  18. [18]
    Isaacs, R. P.: Differential Games — A Mathematical Theory with Applications to Warfare and Pursuit, Control and Optimization. John Wiley & Sons, New York 1965. Robert E. Krieger, Huntington, New York, 1975 (3. edition).zbMATHGoogle Scholar
  19. [19]
    Isaacs, R. P.: Differential Games I: Introduction. Differential Games II: The Definition and Formulation. Differential Games III: The Basic Principles of the Solution Process. Differential Games IV: Mainly Examples. Memoranda RM-1391, RM-1399,RM-1411 and RM-1486. The RAND Corporation, P. O. B. 2138, Santa Monica, California 90407-2138, 1954/55. URL:
  20. [20]
    Isaacs, R. P.: Games of Pursuit. Paper P-257. The RAND Corporation, Santa Monica 1951.Google Scholar
  21. [21]
    Kühnen, M. A.; Brühning, E.; Schepers, A.: Unfallgeschehen auf Autobahnen — Strukturuntersuchung. Bericht der Bundesanstalt für Straßenwesen M50, Wirtschaftsverlag NW/Verlag für neue Wissenschaft, Bremerhaven 1995.Google Scholar
  22. [22]
    Lachner, R.; Breitner, M. H.; Pesch, H. J.: Three-Dimensional Air Combat Analysis — An Example for the Numerical Solution of Complex Differential Games. Annals of the International Society of Dynamic Games 3 (1996).Google Scholar
  23. [23]
    Lachner, R.; Breitner, M. H.; Pesch, H. J.: Optimal Strategies of a Complex Pursuit-Evasion Game. Journal of Computing and Information 4 (1994).Google Scholar
  24. [24]
    Leshno, M.; Lin, V. Y.; Pinkus, A.; Schocken, S.: Multilayer Feedforward Networks with a Nonpolynomial Activation Function Can Approximate Any Function. Neural Networks 6 (1993).Google Scholar
  25. [25]
    Miesbach, S.; Breitner, M. H.; Chini, C.; Pesch, H. J.: Neuronale Kennfeldsteuerung zur Kollisionsvermeidung von entgegenkommenden Fahrzeugen. German patent application 95 P 8066 DE, Europäisches Patentamt, Erhardtstrasse 27, D-80331 München, 1995. URL: Scholar
  26. [26]
    Miloh, T.: The Game of Two Elliptical Ships. Optimal Control Applications & Methods 4 (1983).Google Scholar
  27. [27]
    Miloh, T.; Pachter, M.: Ship Collision Avoidance and Pursuit-evasion Differential Games with Speed-loss in a Turn. Computers and Mathematics with Applications 18 (1989).Google Scholar
  28. [28]
    Miloh, T.: Sharma, S. D.: Maritime Collision Avoidance as a Differential Game. Schiffstechnik 24 (1977).Google Scholar
  29. [29]
    Neural Information Processing Systems Foundation (San Diego), Proceedings of NIPSF Conferences NIPS1 — NIPS9 (1988–1996). MIT Press, Cambridge, Massachusetts. URL: Scholar
  30. [30]
    Pesch, H. J.; Gabler, I.; Miesbach, S.; Breitner, M. H.: Synthesis of Optimal Strategies for Differential Games by Neural Networks. Annals of the International Society of Dynamic Games 3 (1996).Google Scholar
  31. [31]
    Petrosjan, L. A.: Differential Games of Pursuit. World Scientific, River Edge, New York, 1993.CrossRefGoogle Scholar
  32. [32]
    Rigoll, G.: Neuronale Netze — Eine Einführung für Ingenieure, Informatiker und Naturwissenschaftler. Expert Verlag, Renningen-Malmsheim 1994.Google Scholar
  33. [33]
    Scherer, A.: Neuronale Netze — Grundlagen und Anwendungen. Vieweg, Wiesbaden 1996.Google Scholar
  34. [34]
    Shinar, J.; Tabak, R.: New Results in Optimal Missile Avoidance Analysis. Journal of Guidance, Control & Dynamics 17 (1994).Google Scholar
  35. [35]
    Vincent, T. L.: Collision Avoidance at Sea. In: Hagedorn, P.; Knobloch, H. W.; Olsder, G. J. (editors): Differential Games and Applications, Lecture Notes in Control and Information Sciences 3, Springer, Berlin 1977.Google Scholar
  36. [36]
    Vincent, T. L.; Cliff, E. M.; Grantham, W. J.; Peng, W. Y.: Some Aspects of Collision Avoidance. AIAA Journal 12 (1974).Google Scholar
  37. [37]
    White, H.; Gallant, A. R.; Hornik, K.; Stinchcombe, M.; Wooldridge, J.: Artificial Neural Networks — Approximation and Learning Theory. Blackwell, Oxford 1992.Google Scholar
  38. [38]
    White, D. A.; Sofge, D. A.: Handbook of Intelligent Control — Neural, Fuzzy and Adaptive Approaches. Van Nostrand Reinhold, New York 1992.Google Scholar
  39. [39]
    Zell, A.: Simulation Neuronaler Netze. Addison-Wesley, Bonn 1996.Google Scholar
  40. [40]
    Zell, A. et al.: SNNS — Stuttgart Neural Network Simulator (Version 4.0): User Manual. Universität Stuttgart, Institut für paralleles und verteiltes Hochleistungsrechnen, Breitwiesenstraße 20–22, D-70565 Stuttgart, 1995. URL: Scholar

Copyright information

© Springer Basel AG 1998

Authors and Affiliations

  • Rainer Lachner
    • 1
  • Michael H. Breitner
    • 1
  • Hans J. Pesch
    • 1
  1. 1.Institut für MathematikTechnische Universität ClausthalClausthal-ZellerfeldGermany

Personalised recommendations