Advertisement

More Adaptive Does not Imply Less Safe (with Formal Verification)

  • Luca PulinaEmail author
  • Armando Tacchella
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10629)

Abstract

In this paper we provide a concise survey of our work devoted to applying formal methods to check the safety of adaptive cyber-physical systems.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lee, E.A.: Cyber physical systems: design challenges. In: 11th IEEE International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC 2008), May 5–7, 2008, Orlando, Florida, USA, pp. 363–369 (2008)Google Scholar
  2. 2.
    Pulina, L., Tacchella, A.: Challenging SMT solvers to verify neural networks. AI Commun. 25(2), 117–135 (2012)zbMATHMathSciNetGoogle Scholar
  3. 3.
    Pulina, L., Tacchella, A.: NeVer: a tool for artificial neural networks verification. Ann. Math. Artif. Intell. 62(3–4), 403–425 (2011)CrossRefzbMATHGoogle Scholar
  4. 4.
    Pulina, L., Tacchella, A.: An abstraction-refinement approach to verification of artificial neural networks. In: Touili, T., Cook, B., Jackson, P. (eds.) CAV 2010. LNCS, vol. 6174, pp. 243–257. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-14295-6_24 CrossRefGoogle Scholar
  5. 5.
    Leofante, F., Tacchella, A.: Learning in physical domains: mating safety requirements and costly sampling. In: Adorni, G., Cagnoni, S., Gori, M., Maratea, M. (eds.) AI*IA 2016. LNCS (LNAI), vol. 10037, pp. 539–552. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-49130-1_39 CrossRefGoogle Scholar
  6. 6.
    Metta, G., Natale, L., Pathak, S., Pulina, L., Tacchella, A.: Safe and effective learning: a case study. In: IEEE International Conference on Robotics and Automation, ICRA 2010, May 3–7, 2010, Anchorage, Alaska, USA, pp. 4809–4814 (2010)Google Scholar
  7. 7.
    Pathak, S., Pulina, L., Tacchella, A.: Evaluating probabilistic model checking tools for verification of robot control policies. AI Commun. 29(2), 287–299 (2016)CrossRefMathSciNetzbMATHGoogle Scholar
  8. 8.
    Leofante, F., Vuotto, S., Ábrahám, E., Tacchella, A., Jansen, N.: Combining static and runtime methods to achieve safe standing-up for humanoid robots. In: Margaria, T., Steffen, B. (eds.) ISoLA 2016. LNCS, vol. 9952, pp. 496–514. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-47166-2_34 CrossRefGoogle Scholar
  9. 9.
    Pathak, S., Pulina, L., Metta, G., Tacchella, A.: Ensuring safety of policies learned by reinforcement: reaching objects in the presence of obstacles with the iCub. In: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, November 3–7, 2013, Tokyo, Japan, pp. 170–175 (2013)Google Scholar
  10. 10.
    Pathak, S., Pulina, L., Tacchella, A.: Verification and Repair of Control Policies for Safe Reinforcement Learning. Applied Intelligence (2017, to appear)Google Scholar
  11. 11.
    Huang, X., Kwiatkowska, M., Wang, S., Wu, M.: Safety verification of deep neural networks. arXiv preprint arXiv:1610.06940 (2016). To appear as invited paper at CAV 2017
  12. 12.
    Katz, G., Barrett, C., Dill, D., Julian, K., Kochenderfer, M.: Reluplex: An efficient smt solver for verifying deep neural networks. arXiv preprint arXiv:1702.01135 (2017). To appear in the proc. of CAV 2017
  13. 13.
    Fränzle, M., Herde, C.: Hysat: An efficient proof engine for bounded model checking of hybrid systems. Formal Methods in System Design 30(3), 179–198 (2007)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.POLCOMINGUniversità degli Studi di SassariSassariItaly
  2. 2.DIBRISUniversità degli Studi di GenovaGenovaItaly

Personalised recommendations