Advertisement

Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning

  • Bernhard K. Aichernig
  • Roderick Bloem
  • Masoud Ebrahimi
  • Martin Horn
  • Franz Pernkopf
  • Wolfgang Roth
  • Astrid Rupp
  • Martin TapplerEmail author
  • Markus Tranninger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11812)

Abstract

Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as possible. However, the construction of models that comprise physical and digital behavior is challenging. Therefore, there is considerable interest in learning such hybrid behavior by means of machine learning which requires sufficient and representative training data covering the behavior of the physical system adequately. In this work, we exploit a combination of automata learning and model-based testing to generate sufficient training data fully automatically.

Experimental results on a platooning scenario show that recurrent neural networks learned with this data achieved significantly better results compared to models learned from randomly generated data. In particular, the classification error for crash detection is reduced by a factor of five and a similar F1-score is obtained with up to three orders of magnitude fewer training samples.

Keywords

Hybrid systems Behavior modeling Automata learning Model-Based Testing Machine learning Autonomous vehicle Platooning 

Notes

Acknowledgment

This work is supported by the TU Graz LEAD project “Dependable Internet of Things in Adverse Environments”. It is also partially supported by ECSEL Joint Undertaking under Grant No.: 692455.

References

  1. 1.
    Aarts, F., Heidarian, F., Kuppens, H., Olsen, P., Vaandrager, F.: Automata learning through counterexample guided abstraction refinement. In: Giannakopoulou, D., Méry, D. (eds.) FM 2012. LNCS, vol. 7436, pp. 10–27. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-32759-9_4CrossRefGoogle Scholar
  2. 2.
    Aichernig, B.K., et al.: Learning a behavior model of hybrid systems through combining model-based testing and machine learning (full version). CoRR abs/1907.04708 (2019). http://arxiv.org/abs/1907.04708
  3. 3.
    Aichernig, B.K., Mostowski, W., Mousavi, M.R., Tappler, M., Taromirad, M.: Model learning and model-based testing. In: Bennaceur et al. [6], pp. 74–100.  https://doi.org/10.1007/978-3-319-96562-8_3Google Scholar
  4. 4.
    Aichernig, B.K., Tappler, M.: Efficient active automata learning via mutation testing. J. Autom. Reason. (2018).  https://doi.org/10.1007/s10817-018-9486-0
  5. 5.
    Angluin, D.: Learning regular sets from queries and counterexamples. Inf. Comput. 75(2), 87–106 (1987)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Bennaceur, A., Hähnle, R., Meinke, K. (eds.): Machine Learning for Dynamic Software Analysis: Potentials and Limits. LNCS, vol. 11026. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-96562-8CrossRefGoogle Scholar
  7. 7.
    Chollet, F., et al.: Keras (2015). https://keras.io
  8. 8.
    Chow, T.S.: Testing software design modeled by finite-state machines. IEEE Trans. Softw. Eng. 4(3), 178–187 (1978).  https://doi.org/10.1109/TSE.1978.231496CrossRefzbMATHGoogle Scholar
  9. 9.
    Derler, P., Lee, E.A., Sangiovanni-Vincentelli, A.L.: Modeling cyber-physical systems. Proc. IEEE 100(1), 13–28 (2012).  https://doi.org/10.1109/JPROC.2011.2160929CrossRefGoogle Scholar
  10. 10.
    Dolk, V.S., Ploeg, J., Heemels, W.P.M.H.: Event-triggered control for string-stable vehicle platooning. IEEE Trans. Intell. Transp. Syst. 18(12), 3486–3500 (2017).  https://doi.org/10.1109/TITS.2017.2738446CrossRefGoogle Scholar
  11. 11.
    Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: Balcan, M., Weinberger, K.Q. (eds.) ICML 2016. JMLR Workshop and Conference Proceedings, vol. 48, pp. 1329–1338. JMLR.org (2016). http://jmlr.org/proceedings/papers/v48/duan16.html
  12. 12.
    Fermi, A., Mongelli, M., Muselli, M., Ferrari, E.: Identification of safety regions in vehicle platooning via machine learning. In: WFCS (2018)Google Scholar
  13. 13.
    Fujiwara, S., von Bochmann, G., Khendek, F., Amalou, M., Ghedamsi, A.: Test selection based on finite state models. IEEE Trans. Softw. Eng. 17(6), 591–603 (1991).  https://doi.org/10.1109/32.87284CrossRefGoogle Scholar
  14. 14.
    Henzinger, T.A.: The theory of hybrid automata. In: LICS (1996)Google Scholar
  15. 15.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  16. 16.
    Howar, F., Steffen, B.: Active automata learning in practice. In: Bennaceur, A., Hähnle, R., Meinke, K. (eds.) Machine Learning for Dynamic Software Analysis: Potentials and Limits. LNCS, vol. 11026, pp. 123–148. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-96562-8_5CrossRefGoogle Scholar
  17. 17.
    Howar, F., Steffen, B., Merten, M.: From ZULU to RERS. In: Margaria, T., Steffen, B. (eds.) ISoLA 2010. LNCS, vol. 6415, pp. 687–704. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-16558-0_55CrossRefGoogle Scholar
  18. 18.
    Isberner, M., Howar, F., Steffen, B.: The open-source LearnLib. In: Kroening, D., Păsăreanu, C.S. (eds.) CAV 2015. LNCS, vol. 9206, pp. 487–495. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-21690-4_32CrossRefGoogle Scholar
  19. 19.
    Kearns, M.J., Vazirani, U.V.: An Introduction to Computational Learning Theory. MIT Press, Cambridge, (1994)CrossRefGoogle Scholar
  20. 20.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015). arXiv:1412.6980
  21. 21.
    Ljung, L.: System Identification: Theory for the User. PTR Prentice Hall Information and System Sciences Series. Prentice Hall, New Jersey (1999)zbMATHGoogle Scholar
  22. 22.
    Lv, C., Liu, Y., Hu, X., Guo, H., Cao, D., Wang, F.: Simultaneous observation of hybrid states for cyber-physical systems: a case study of electric vehicle powertrain. IEEE Trans. Cybern. 48(8), 2357–2367 (2018).  https://doi.org/10.1109/TCYB.2017.2738003CrossRefGoogle Scholar
  23. 23.
    Manna, Z., Pnueli, A.: Verifying hybrid systems. In: Hybrid Systems (1992)Google Scholar
  24. 24.
    Meinke, K.: Learning-based testing of cyber-physical systems-of-systems: a platooning study. In: Reinecke, P., Di Marco, A. (eds.) EPEW 2017. LNCS, vol. 10497, pp. 135–151. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66583-2_9CrossRefGoogle Scholar
  25. 25.
    Meinke, K.: Learning-based testing: recent progress and future prospects. In: Bennaceur et al. [6], pp. 53–73.  https://doi.org/10.1007/978-3-319-96562-8_2Google Scholar
  26. 26.
    O’Shea, T.J., Hoydis, J.: An introduction to deep learning for the physical layer. IEEE Trans. Cogn. Commun. Netw. 3(4), 563–575 (2017).  https://doi.org/10.1109/TCCN.2017.2758370CrossRefGoogle Scholar
  27. 27.
    Peled, D.A., Vardi, M.Y., Yannakakis, M.: Black box checking. J. Autom. Lang. Comb. 7(2), 225–246 (2002).  https://doi.org/10.25596/jalc-2002-225MathSciNetCrossRefzbMATHGoogle Scholar
  28. 28.
    Ploeg, J., Shukla, D.P., van de Wouw, N., Nijmeijer, H.: Controller synthesis for string stability of vehicle platoons. IEEE Trans. Intell. Transp. Syst. 15(2), 854–865 (2014).  https://doi.org/10.1109/TITS.2013.2291493CrossRefGoogle Scholar
  29. 29.
    Punjani, A., Abbeel, P.: Deep learning helicopter dynamics models. In: IEEE International Conference on Robotics and Automation, ICRA 2015, Seattle, WA, USA, 26–30 May 2015, pp. 3223–3230. IEEE (2015).  https://doi.org/10.1109/ICRA.2015.7139643
  30. 30.
    Rashid, A., Siddique, U., Hasan, O.: Formal verification of platoon control strategies. In: Johnsen, E.B., Schaefer, I. (eds.) SEFM 2018. LNCS, vol. 10886, pp. 223–238. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-92970-5_14CrossRefGoogle Scholar
  31. 31.
    Rupp, A., Steinberger, M., Horn, M.: Sliding mode based platooning with non-zero initial spacing errors. IEEE Control Syst. Lett. 1(2), 274–279 (2017).  https://doi.org/10.1109/LCSYS.2017.2714978CrossRefGoogle Scholar
  32. 32.
    Shahbaz, M., Groz, R.: Inferring Mealy machines. In: Cavalcanti, A., Dams, D.R. (eds.) FM 2009. LNCS, vol. 5850, pp. 207–222. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-05089-3_14CrossRefGoogle Scholar
  33. 33.
    Simpson, T., Booker, A., Ghosh, D., Giunta, A., Koch, P., Yang, R.J.: Approximation methods in multidisciplinary analysis and optimization: a panel discussion. Struct. Multidiscip. Optim. 27(5), 302–313 (2004).  https://doi.org/10.1007/s00158-004-0389-9CrossRefGoogle Scholar
  34. 34.
    Smeenk, W., Moerman, J., Vaandrager, F., Jansen, D.N.: Applying automata learning to embedded control software. In: Butler, M., Conchon, S., Zaïdi, F. (eds.) ICFEM 2015. LNCS, vol. 9407, pp. 67–83. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-25423-4_5CrossRefGoogle Scholar
  35. 35.
    Spielberg, S., Gopaluni, R.B., Loewen, P.D.: Deep reinforcement learning approaches for process control. In: 2017 6th International Symposium on Advanced Control of Industrial Processes (AdCONIP), pp. 201–206 (2017)Google Scholar
  36. 36.
    Tanwani, A., Shim, H., Liberzon, D.: Observability for switched linear systems: characterization and observer design. IEEE Trans. Autom. Control 58(4), 891–904 (2013).  https://doi.org/10.1109/tac.2012.2224257MathSciNetCrossRefzbMATHGoogle Scholar
  37. 37.
    Vaandrager, F.W.: Model learning. Commun. ACM 60(2), 86–95 (2017)CrossRefGoogle Scholar
  38. 38.
    Vasilevskii, M.P.: Failure diagnosis of automata. Cybernetics 9(4), 653–665 (1973).  https://doi.org/10.1007/BF01068590CrossRefGoogle Scholar
  39. 39.
    Vidal, R., Ma, Y., Sastry, S.S.: Hybrid system identification. Generalized Principal Component Analysis. IAM, vol. 40, pp. 431–451. Springer, New York (2016).  https://doi.org/10.1007/978-0-387-87811-9_12CrossRefzbMATHGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2019

Authors and Affiliations

  • Bernhard K. Aichernig
    • 1
  • Roderick Bloem
    • 1
  • Masoud Ebrahimi
    • 1
  • Martin Horn
    • 1
  • Franz Pernkopf
    • 1
  • Wolfgang Roth
    • 1
  • Astrid Rupp
    • 1
  • Martin Tappler
    • 1
    Email author
  • Markus Tranninger
    • 1
  1. 1.Graz University of TechnologyGrazAustria

Personalised recommendations