Abstract
Autonomous systems are increasingly deployed in safety-critical applications and rely more on high-performance components based on artificial intelligence (AI) and machine learning (ML). Runtime monitors play an important role in raising the level of assurance in AI/ML-based autonomous systems by ensuring that the autonomous system stays safe within its operating environment. In this tutorial, we present VerifAI, an open-source toolkit for the formal design and analysis of systems that include AI/ML components. VerifAI provides features supporting a variety of use cases including formal modeling of the autonomous system and its environment, automatic falsification of system-level specifications as well as other simulation-based verification and testing methods, automated diagnosis of errors, and automatic specification-driven parameter and component synthesis. In particular, we describe the use of VerifAI for generating runtime monitors that capture the safe operational environment of systems with AI/ML components. We illustrate the advantages and applicability of VerifAI in real-life applications using a case study from the domain of autonomous aviation.
This work is partially supported by NSF grants 1545126 (VeHICaL), 1646208 and 1837132, by the DARPA contracts FA8750-18-C-0101 (AA) and FA8750-20-C-0156 (SDCPS), by Berkeley Deep Drive, by the Toyota Research Institute, and by Toyota under the iCyPhy center.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aarts, F., Jonsson, B., Uijen, J., Vaandrager, F.: Generating models of infinite-state communication protocols using regular inference with abstraction. Formal Methods Syst. Des. 46(1), 1–41 (2014). https://doi.org/10.1007/s10703-014-0216-x
Aceto, L., Cassar, I., Francalanza, A., Ingólfsdóttir, A.: On runtime enforcement via suppressions. In: CONCUR. LIPIcs, vol. 118, pp. 34:1–34:17 (2018)
Azad, A.S., et al.: Scenic4RL: programmatic modeling and generation of reinforcement learning environments. CoRR, abs/2106.10365 (2021)
Baumeister, J., Finkbeiner, B., Schwenger, M., Torfah, H.: FPGA stream-monitoring of real-time properties. ACM Trans. Embed. Comput. Syst. 18(5s), 88:1–88:24 (2019)
Bortolussi, L., Cairoli, F., Paoletti, N., Smolka, S.A., Stoller, S.D.: Neural predictive monitoring. In: Finkbeiner, B., Mariani, L. (eds.) RV 2019. LNCS, vol. 11757, pp. 129–147. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32079-9_8
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Wadsworth (1984)
Cairoli, F., Bortolussi, L., Paoletti, N.: Neural predictive monitoring under partial observability. CoRR, abs/2108.07134 (2021)
Chou, Y., Yoon, H., Sankaranarayanan, S.: Predictive runtime monitoring of vehicle models using Bayesian estimation and reachability analysis. In: IROS, pp. 2111–2118. IEEE (2020)
Desai, A., Ghosh, S., Seshia, S.A., Shankar, N., Tiwari, A.: SOTER: a runtime assurance framework for programming safe robotics systems. In: IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) (2019)
Deshmukh, J.V., Donzé, A., Ghosh, S., Jin, X., Juniwal, G., Seshia, S.A.: Robust online monitoring of signal temporal logic. Formal Methods Syst. Des. 51(1), 5–30 (2017). https://doi.org/10.1007/s10703-017-0286-7
Dreossi, T., et al.: VerifAI: a toolkit for the formal design and analysis of artificial intelligence-based systems. In: Dillig, I., Tasiran, S. (eds.) CAV 2019. LNCS, vol. 11561, pp. 432–442. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-25540-4_25
Dreossi, T., Jha, S., Seshia, S.A.: Semantic adversarial deep learning. In: Chockler, H., Weissenbacher, G. (eds.) CAV 2018. LNCS, vol. 10981, pp. 3–26. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-96145-3_1
Falcone, Y., Mounier, L., Fernandez, J.-C., Richier, J.-L.: Runtime enforcement monitors: composition, synthesis, and enforcement abilities. Formal Methods Syst. Des. 38(3), 223–262 (2011)
Faymonville, P., et al.: StreamLAB: stream-based monitoring of cyber-physical systems. In: Dillig, I., Tasiran, S. (eds.) CAV 2019. LNCS, vol. 11561, pp. 421–431. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-25540-4_24
Finkbeiner, B., Sipma, H.: Checking finite traces using alternating automata. Form. Methods Syst. Des. 24(2), 101–127 (2004)
Fremont, D.J., Chiu, J., Margineantu, D.D., Osipychev, D., Seshia, S.A.: Formal analysis and redesign of a neural network-based aircraft taxiing system with VerifAI. In: Lahiri, S.K., Wang, C. (eds.) CAV 2020. LNCS, vol. 12224, pp. 122–134. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-53288-8_6
Fremont, D.J., Dreossi, T., Ghosh, S., Yue, X., Sangiovanni-Vincentelli, A.L., Seshia, S.A.: Scenic: a language for scenario specification and scene generation. In: PLDI (2019)
Fremont, D.J., et al.: Scenic: a language for scenario specification and data generation (2020)
Fremont, D.J., et al.: Formal scenario-based testing of autonomous vehicles: from simulation to the real world. In: ITSC (2020)
Ghosh, S., Pant, Y.V., Ravanbakhsh, H., Seshia, S.A.: Counterexample-guided synthesis of perception models and control. In: American Control Conference (ACC), pp. 3447–3454. IEEE (2021)
Havelund, K., Roşu, G.: Synthesizing monitors for safety properties. In: Katoen, J.-P., Stevens, P. (eds.) TACAS 2002. LNCS, vol. 2280, pp. 342–356. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-46002-0_24
Henzinger, T.A., Ho, P.-H., Wong-Toi, H.: Algorithmic analysis of nonlinear hybrid systems. IEEE Trans. Autom. Control 43(4), 540–554 (1998)
Isberner, M., Steffen, B., Howar, F.: LearnLib tutorial - an open-source Java library for active automata learning. In: Bartocci, E., Majumdar, R. (eds.) RV 2015. LNCS, vol. 9333, pp. 358–377. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23820-3_25
Jha, S., Gulwani, S., Seshia, S.A., Tiwari, A.: Oracle-guided component-based program synthesis. In: ICSE (1), pp. 215–224. ACM (2010)
Jha, S., Seshia, S.A.: A theory of formal synthesis via inductive learning. Acta Informatica 54(7), 693–726 (2017). https://doi.org/10.1007/s00236-017-0294-5
Junges, S., Torfah, H., Seshia, S.A.: Runtime Monitors for Markov Decision Processes. In: Silva, A., Leino, K.R.M. (eds.) CAV 2021. LNCS, vol. 12760, pp. 553–576. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-81688-9_26
Koymans, R.: Specifying real-time properties with metric temporal logic. Real-Time Syst. 2(4), 255–299 (1990)
Leucker, M., Sánchez, C., Scheffel, T., Schmitz, M., Schramm, A.: Tessla: runtime verification of non-synchronized real-time streams. In: SAC, pp. 1925–1933. ACM (2018)
Maler, O., Nickovic, D.: Monitoring temporal properties of continuous signals. In: Lakhnech, Y., Yovine, S. (eds.) FORMATS/FTRTFT -2004. LNCS, vol. 3253, pp. 152–166. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30206-3_12
Mens, I.-E., Maler, O.: Learning regular languages over large ordered alphabets. Log. Methods Comput. Sci. 11(3) (2015)
Phan, D., Yang, J., Grosu, R., Smolka, S.A., Stoller, S.D.: Collision avoidance for mobile robots with limited sensing and limited information about moving obstacles. Formal Methods Syst. Des. 51(1), 62–86 (2017). https://doi.org/10.1007/s10703-016-0265-4
Pike, L., Goodloe, A., Morisset, R., Niller, S.: Copilot: a hard real-time runtime monitor. In: Barringer, H., et al. (eds.) RV 2010. LNCS, vol. 6418, pp. 345–359. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-16612-9_26
Pitt, L., Warmuth, M.K.: The minimum consistent DFA problem cannot be approximated within any polynomial. J. ACM 40(1), 95–142 (1993)
Ross Quinlan, J.: Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986)
Laminar Research. X-Plane 11 (2019). https://www.x-plane.com/
Rivest, R.L.: Learning decision lists. Mach. Learn. 2(3), 229–246 (1987)
Sánchez, C., et al.: A survey of challenges for runtime verification from advanced application domains (beyond software). Formal Methods Syst. Des. 54(3), 279–335 (2019)
Schneider, F.B.: Enforceable security policies. ACM Trans. Inf. Syst. Secur. 3(1), 30–50 (2000)
Seshia, S.A.: Introspective environment modeling. In: Finkbeiner, B., Mariani, L. (eds.) RV 2019. LNCS, vol. 11757, pp. 15–26. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32079-9_2
Seshia, S.A., Sadigh, D., Shankar Sastry, S.: Towards Verified Artificial Intelligence. arXiv e-prints (2016)
Seto, D., Ferriera, E., Marz, T.: Case study: development of a baseline controller for automatic landing of an F-16 aircraft using linear matrix inequalities (LMIs). Technical report CMU/SEI-99-TR-020, Software Engineering Institute, Carnegie Mellon University, Pittsburgh, PA (2000)
Sha, L.: Using simplicity to control complexity. IEEE Softw. 18(4), 20–28 (2001)
Shivakumar, S., Torfah, H., Desai, A., Seshia, S.A.: SOTER on ROS: a run-time assurance framework on the robot operating system. In: Deshmukh, J., Ničković, D. (eds.) RV 2020. LNCS, vol. 12399, pp. 184–194. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60508-7_10
Stoller, S.D., et al.: Runtime verification with state estimation. In: Khurshid, S., Sen, K. (eds.) RV 2011. LNCS, vol. 7186, pp. 193–207. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29860-8_15
Teubert, C., Watkins, J.: The X-Plane Connect Toolbox (2019). https://github.com/nasa/ XPlaneConnect
Torfah, H.: Stream-based monitors for real-time properties. In: Finkbeiner, B., Mariani, L. (eds.) RV 2019. LNCS, vol. 11757, pp. 91–110. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32079-9_6
Torfah, H., Shah, S., Chakraborty, S., Akshay, S., Seshia, S.A.: Synthesizing pareto-optimal interpretations for black-box models. In: FMCAD. IEEE (2021)
Vaandrager, F.W.: Model learning. Commun. ACM 60(2), 86–95 (2017)
Valiant, L.G.: A theory of the learnable. Commun. ACM 27(11), 1134–1142 (1984)
Acknowledgments
The authors are grateful to Johnathan Chiu, Tommaso Dreossi, Shromona Ghosh, Francis Indaheng, Edward Kim, Hadi Ravanbakhsh, Marcell Vazquez-Chanlatte, and Kesav Viswanadha for their valuable contributions to the VerifAI project. We also thank the team at Boeing helping to define the TaxiNet challenge problem including especially Dragos D. Margineantu and Denis Osipychev.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Torfah, H., Junges, S., Fremont, D.J., Seshia, S.A. (2021). Formal Analysis of AI-Based Autonomy: From Modeling to Runtime Assurance. In: Feng, L., Fisman, D. (eds) Runtime Verification. RV 2021. Lecture Notes in Computer Science(), vol 12974. Springer, Cham. https://doi.org/10.1007/978-3-030-88494-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-88494-9_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88493-2
Online ISBN: 978-3-030-88494-9
eBook Packages: Computer ScienceComputer Science (R0)