Advertisement

Lab Conditions for Research on Explainable Automated Decisions

Conference paper
  • 77 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12641)

Abstract

Artificial neural networks are being proposed for automated decision making under uncertainty in many visionary contexts, including high-stake tasks such as navigating autonomous cars through dense traffic. Against this background, it is imperative that the decision making entities meet central societal desiderata regarding dependability, perspicuity, explainability, and robustness. Decision making problems under uncertainty are typically captured formally as variations of Markov decision processes (MDPs). This paper discusses a set of natural and easy-to-control abstractions, based on the Racetrack benchmarks and extensions thereof, that altogether connect the autonomous driving challenge to the modelling world of MDPs. This is then used to study the dependability and robustness of NN-based decision entities, which in turn are based on state-of-the-art NN learning techniques. We argue that this approach can be regarded as providing laboratory conditions for a systematic, structured and extensible comparative analysis of NN behavior, of NN learning performance, as well as of NN verification and analysis techniques.

References

  1. 1.
    Baier, C., Dubslaff, C., Hermanns, H., Klauck, M., Klüppelholz, S., Köhl, M.A.: Components in probabilistic systems: suitable by construction. In: Margaria, T., Steffen, B. (eds.) ISoLA 2020. LNCS, vol. 12476, pp. 240–261. Springer, Cham (2020).  https://doi.org/10.1007/978-3-030-61362-4_13CrossRefGoogle Scholar
  2. 2.
    Barnaghi, P., Ganz, F., Henson, C., Sheth, A.: Computing perception from sensor data. In: SENSORS, 2012 IEEE, pp. 1–4. IEEE (2012)Google Scholar
  3. 3.
    Barto, A.G., Bradtke, S.J., Singh, S.P.: Learning to act using real-time dynamic programming. Artif. Intell. 72(1–2), 81–138 (1995).  https://doi.org/10.1016/0004-3702(94)00011-OCrossRefGoogle Scholar
  4. 4.
    Berndt, H., Emmert, J., Dietmayer, K.: Continuous driver intention recognition with hidden Markov models. In: 11th International IEEE Conference on Intelligent Transportation Systems, ITSC 2008, Beijing, China, 12–15 October 2008, pp. 1189–1194. IEEE (2008).  https://doi.org/10.1109/ITSC.2008.4732630
  5. 5.
    Bonet, B., Geffner, H.: Labeled RTDP: improving the convergence of real-time dynamic programming. In: Giunchiglia, E., Muscettola, N., Nau, D.S. (eds.) Proceedings of the Thirteenth International Conference on Automated Planning and Scheduling (ICAPS 2003), Trento, Italy, 9–13 June 2003, pp. 12–21. AAAI (2003). http://www.aaai.org/Library/ICAPS/2003/icaps03-002.php
  6. 6.
    Budde, C.E., D’Argenio, P.R., Hartmanns, A., Sedwards, S.: A statistical model checker for nondeterminism and rare events. In: Beyer, D., Huisman, M. (eds.) TACAS 2018. LNCS, vol. 10806, pp. 340–358. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-89963-3_20CrossRefGoogle Scholar
  7. 7.
    Christakis, M., et al.: Automated Safety Verification of Programs Invoking Neural Networks (2020). Submitted for publicationGoogle Scholar
  8. 8.
    Dietmayer, K.: Predicting of machine perception for automated driving. In: Maurer, M., Gerdes, J.C., Lenz, B., Winner, H. (eds.) Autonomous Driving, pp. 407–424. Springer, Heidelberg (2016).  https://doi.org/10.1007/978-3-662-48847-8_20CrossRefGoogle Scholar
  9. 9.
    Faqeh, R., et al.: Towards dynamic dependable systems through evidence-based continuous certification. In: Margaria, T., Steffen, B. (eds.) ISoLA 2020. LNCS, vol. 12477, pp. 416–439. Springer, Cham (2020).  https://doi.org/10.1007/978-3-030-61470-6_25CrossRefGoogle Scholar
  10. 10.
    Gardner, M.: Mathematical games. Sci. Am. 229, 118–121 (1973)CrossRefGoogle Scholar
  11. 11.
    Gros, T.P., Groß, D., Gumhold, S., Hoffmann, J., Klauck, M., Steinmetz, M.: TraceVis: towards visualization for deep statistical model checking. In: Proceedings of the 9th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation. From Verification to Explanation (2020)Google Scholar
  12. 12.
    Gros, T.P., Hermanns, H., Hoffmann, J., Klauck, M., Steinmetz, M.: Deep statistical model checking. In: Gotsman, A., Sokolova, A. (eds.) FORTE 2020. LNCS, vol. 12136, pp. 96–114. Springer, Cham (2020).  https://doi.org/10.1007/978-3-030-50086-3_6CrossRefGoogle Scholar
  13. 13.
    Gumhold, S.: The computer graphics and visualization framework. https://github.com/sgumhold/cgv. Accessed 18 May 2020
  14. 14.
    McMahan, H.B., Gordon, G.J.: Fast exact planning in Markov decision processes. In: Biundo, S., Myers, K.L., Rajan, K. (eds.) Proceedings of the Fifteenth International Conference on Automated Planning and Scheduling (ICAPS 2005), 5–10 June 2005, Monterey, California, USA, pp. 151–160. AAAI (2005). http://www.aaai.org/Library/ICAPS/2005/icaps05-016.php
  15. 15.
    Meresht, V.B., De, A., Singla, A., Gomez-Rodriguez, M.: Learning to switch between machines and humans. CoRR abs/2002.04258 (2020). https://arxiv.org/abs/2002.04258
  16. 16.
    Pineda, L.E., Lu, Y., Zilberstein, S., Goldman, C.V.: Fault-tolerant planning under uncertainty. In: Rossi, F. (ed.) IJCAI 2013, Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China, 3–9 August 2013, pp. 2350–2356. IJCAI/AAAI (2013). http://www.aaai.org/ocs/index.php/IJCAI/IJCAI13/paper/view/6819
  17. 17.
    Pineda, L.E., Zilberstein, S.: Planning under uncertainty using reduced models: revisiting determinization. In: Chien, S.A., Do, M.B., Fern, A., Ruml, W. (eds.) Proceedings of the Twenty-Fourth International Conference on Automated Planning and Scheduling, ICAPS 2014, Portsmouth, New Hampshire, USA, 21–26 June 2014. AAAI (2014). http://www.aaai.org/ocs/index.php/ICAPS/ICAPS14/paper/view/7920
  18. 18.
    Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming. In: Wiley Series in Probability and Statistics. Wiley (1994).  https://doi.org/10.1002/9780470316887
  19. 19.
    Sadri, F.: Logic-based approaches to intention recognition. In: Handbook of Research on Ambient Intelligence and Smart Environments: Trends and Perspectives, pp. 346–375. IGI Global (2011)Google Scholar
  20. 20.
    Strickland, M., Fainekos, G.E., Amor, H.B.: Deep predictive models for collision risk assessment in autonomous driving. In: 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 21–25 May 2018, pp. 1–8. IEEE (2018).  https://doi.org/10.1109/ICRA.2018.8461160
  21. 21.
    Tahboub, K.A.: Intelligent human-machine interaction based on dynamic Bayesian networks probabilistic intention recognition. J. Intell. Robotic Syst. 45(1), 31–52 (2006).  https://doi.org/10.1007/s10846-005-9018-0CrossRefGoogle Scholar
  22. 22.
    Wissenschaftsrat: Perspektiven der Informatik in Deutschland, October 2020. https://www.wissenschaftsrat.de/download/2020/8675-20.pdf
  23. 23.
    Younes, H.L.S., Simmons, R.G.: Probabilistic verification of discrete event systems using acceptance sampling. In: Brinksma, E., Larsen, K.G. (eds.) CAV 2002. LNCS, vol. 2404, pp. 223–235. Springer, Heidelberg (2002).  https://doi.org/10.1007/3-540-45657-0_17CrossRefzbMATHGoogle Scholar
  24. 24.
    Yu, M., Vasudevan, R., Johnson-Roberson, M.: Risk assessment and planning with bidirectional reachability for autonomous driving. In: 2020 IEEE International Conference on Robotics and Automation, ICRA 2020, Paris, France, 31 May–31 August 2020, pp. 5363–5369. IEEE (2020).  https://doi.org/10.1109/ICRA40945.2020.9197491

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.Technische Universität DresdenDresdenGermany
  2. 2.Saarland UniversitySaarbrückenGermany
  3. 3.Max Planck Institute for Software SystemsKaiserslautern and SaarbrückenGermany
  4. 4.Institute of Intelligent SoftwareGuangzhouChina

Personalised recommendations