Abstract
Safety, resilience and performance are crucial properties in intelligent hybrid systems, in particular if they are used in critical infrastructures or safety-critical systems. In this paper, we present a case study that illustrates how to construct provably safe and resilient systems that still achieve certain performance levels with a statistical guarantee in the industrially widely used modeling language Simulink. The key ideas of our paper are threefold: First, we show how to model failures and repairs in Simulink. Second, we use hybrid contracts to non-deterministically overapproximate the failure and repair model and to deductively verify safety properties in the presence of worst-case behavior. Third, we show how to learn optimal decisions using statistical model checking (SMC-based learning), which uses the results from deductive verification as a shield to ensure that only safe actions are chosen. We take component failures into account and learn a schedule that is optimized for performance and ensures resilience in a given Simulink model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Adelt, J., Brettschneider, D., Herber, P.: Reusable contracts for safe integration of reinforcement learning in hybrid systems. In: Automated Technology for Verification and Analysis: 20th International Symposium, ATVA 2022, Virtual Event, 25–28 October 2022, Proceedings, pp. 58–74. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-19992-9_4
Adelt, J., Herber, P., Niehage, M., Remke, A.: Towards safe and resilient hybrid systems in the presence of learning and uncertainty. In: Leveraging Applications of Formal Methods, Verification and Validation. Verification Principles: 11th International Symposium, ISoLA 2022, Rhodes, Greece, 22–30 October 2022, Proceedings, Part I, pp. 299–319. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-19849-6_18
Adelt, J., Liebrenz, T., Herber, P.: Formal verification of intelligent hybrid systems that are modeled with simulink and the reinforcement learning toolbox. In: Huisman, M., Păsăreanu, C., Zhan, N. (eds.) FM 2021. LNCS, vol. 13047, pp. 349–366. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-90870-6_19
Agresti, A., Coull, B.: Approximate is better than “exact’’ for interval estimation of binomial proportions. Am. Stat. 52, 119–126 (1998)
Alshiekh, M., Bloem, R., Ehlers, R., Könighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Alur, R.: Formal verification of hybrid systems. In: ACM International Conference on Embedded Software (EMSOFT), pp. 273–278 (2011)
Araiza-Illan, D., Eder, K., Richards, A.: Formal verification of control systems’ properties with theorem proving. In: UKACC International Conference on Control (CONTROL), pp. 244–249. IEEE (2014)
Boyer, B., Corre, K., Legay, A., Sedwards, S.: PLASMA-lab: a flexible, distributable statistical model checking library. In: Joshi, K., Siegle, M., Stoelinga, M., D’Argenio, P.R. (eds.) QEST 2013. LNCS, vol. 8054, pp. 160–164. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40196-1_12
Budde, C.E., D’Argenio, P.R., Hartmanns, A., Sedwards, S.: An efficient statistical model checker for nondeterminism and rare events. Int. J. Softw. Tools Technol. Transf. 22(6), 759–780 (2020)
Cai, M., Peng, H., Li, Z., Kan, Z.: Learning-based probabilistic LTL motion planning with environment and motion uncertainties. IEEE Trans. Autom. Control 66(5), 2386–2392 (2021)
Carr, S., Jansen, N., Junges, S., Topcu, U.: Safe reinforcement learning via shielding under partial observability. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 12, pp. 14748–14756 (2023)
Chen, M., et al.: MARS: a toolchain for modelling, analysis and verification of hybrid systems. In: Hinchey, M.G., Bowen, J.P., Olderog, E.-R. (eds.) Provably Correct Systems. NMSSE, pp. 39–58. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-48628-4_3
Chutinan, A., Krogh, B.H.: Computational techniques for hybrid system verification. IEEE Trans. Autom. Control 48(1), 64–75 (2003)
D’Argenio, P., Legay, A., Sedwards, S., Traonouez, L.M.: Smart sampling for lightweight verification of Markov decision processes. Int. J. Softw. Tools Technol. Transfer 17(4), 469–484 (2015)
D’Argenio, P.R., Hartmanns, A., Sedwards, S.: Lightweight statistical model checking in nondeterministic continuous time. In: Margaria, T., Steffen, B. (eds.) ISoLA 2018. LNCS, vol. 11245, pp. 336–353. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03421-4_22
Ellen, C., Gerwinn, S., Fränzle, M.: Statistical model checking for stochastic hybrid systems involving nondeterminism over continuous domains. Int. J. Softw. Tools Technol. Transfer 17(4), 485–504 (2015)
Filipovikj, P., et al.: Analyzing industrial simulink models by statistical model checking (2017)
Fulton, N., Mitsch, S., Quesel, J.-D., Völp, M., Platzer, A.: KeYmaera X: an axiomatic tactical theorem prover for hybrid systems. In: Felty, A.P., Middeldorp, A. (eds.) CADE 2015. LNCS (LNAI), vol. 9195, pp. 527–538. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21401-6_36
Fulton, N., Platzer, A.: Safe reinforcement learning via formal methods: toward safe control through proof and learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Gomes, A., Mota, A., Sampaio, A., Ferri, F., Buzzi, J.: Systematic model-based safety assessment via probabilistic model checking. In: Margaria, T., Steffen, B. (eds.) ISoLA 2010. LNCS, vol. 6415, pp. 625–639. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-16558-0_50
Gomes, A., Mota, A., Sampaio, A., Ferri, F., Watanabe, E.: Constructive model-based analysis for safety assessment. Int. J. Softw. Tools Technol. Transfer 14, 673–702 (2012)
Gudemann, M., Ortmeier, F.: A framework for qualitative and quantitative formal model-based safety analysis. In: IEEE International Symposium on High Assurance Systems Engineering, pp. 132–141. IEEE (2010)
Hahn, E.M., Perez, M., Schewe, S., Somenzi, F., Trivedi, A., Wojtczak, D.: Faithful and effective reward schemes for model-free reinforcement learning of omega-regular objectives. In: Hung, D.V., Sokolsky, O. (eds.) ATVA 2020. LNCS, vol. 12302, pp. 108–124. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59152-6_6
Hartmanns, A., Hermanns, H.: The modest toolset: an integrated environment for quantitative modelling and verification. In: Ábrahám, E., Havelund, K. (eds.) TACAS 2014. LNCS, vol. 8413, pp. 593–598. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-642-54862-8_51
Hasanbeig, M., Kantaros, Y., Abate, A., Kroening, D., Pappas, G.J., Lee, I.: Reinforcement learning for temporal logic control synthesis with probabilistic satisfaction guarantees. In: IEEE Conference on Decision and Control (CDC), pp. 5338–5343. IEEE, Nice (2019)
Hasanbeig, M., Abate, A., Kroening, D.: Cautious reinforcement learning with logical constraints. In: AAMAS 2020, International Foundation for Autonomous Agents and Multiagent Systems, pp. 483–491 (2020)
Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th Innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2–7 February 2018, vol. 32, pp. 3207–3214. AAAI Press (2018)
Herber, P., Reicherdt, R., Bittner, P.: Bit-precise formal verification of discrete-time MATLAB/Simulink models using SMT solving. In: International Conference on Embedded Software (EMSOFT), pp. 1–10. IEEE (2013)
Kanwar, K., Vajpai, D.J.: Performance evaluation of different models of PV panel in matlab/simulink environment. Appl. Solar Energy 58(1), 86–94 (2022)
Knüppel, A., Thüm, T., Schaefer, I.: GUIDO: automated guidance for the configuration of deductive program verifiers. In: IEEE/ACM International Conference on Formal Methods in Software Engineering (FormaliSE), pp. 124–129. IEEE (2021)
Könighofer, B., Lorber, F., Jansen, N., Bloem, R.: Shield synthesis for reinforcement learning. In: Margaria, T., Steffen, B. (eds.) ISoLA 2020. LNCS, vol. 12476, pp. 290–306. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61362-4_16
Kwiatkowska, M., Norman, G., Parker, D.: PRISM: probabilistic symbolic model checker. In: Field, T., Harrison, P.G., Bradley, J., Harder, U. (eds.) TOOLS 2002. LNCS, vol. 2324, pp. 200–204. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-46029-2_13
Legay, A., Sedwards, S., Traonouez, L.-M.: Scalable verification of Markov decision processes. In: Canal, C., Idani, A. (eds.) SEFM 2014. LNCS, vol. 8938, pp. 350–362. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-15201-1_23
Legay, A., Traonouez, L.-M.: Statistical model checking of simulink models with plasma lab. In: Artho, C., Ölveczky, P.C. (eds.) FTSCS 2015. CCIS, vol. 596, pp. 259–264. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-29510-7_15
Liebrenz, T., Herber, P., Glesner, S.: Deductive verification of hybrid control systems modeled in simulink with KeYmaera X. In: Sun, J., Sun, M. (eds.) ICFEM 2018. LNCS, vol. 11232, pp. 89–105. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-02450-5_6
Liebrenz, T., Herber, P., Glesner, S.: A service-oriented approach for decomposing and verifying hybrid system models. In: Arbab, F., Jongmans, S.-S. (eds.) FACS 2019. LNCS, vol. 12018, pp. 127–146. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-40914-2_7
Liebrenz, T., Herber, P., Glesner, S.: Service-oriented decomposition and verification of hybrid system models using feature models and contracts. Sci. Comput. Program. 211, 102694 (2021)
Lygeros, J., Prandini, M.: Stochastic hybrid systems: a powerful framework for complex, large scale applications. Eur. J. Control. 16(6), 583–594 (2010)
Mahto, R.K., Kaur, J., Jain, P.: Performance analysis of robotic arm using simulink. In: 2022 IEEE World Conference on Applied Intelligence and Computing (AIC), pp. 508–512. IEEE (2022)
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
Manno, G., Chiacchio, F., Compagno, L., D’Urso, D., Trapani, N.: Matcarlore: an integrated FT and monte carlo simulink tool for the reliability assessment of dynamic fault tree. Expert Syst. Appl. 39(12), 10334–10342 (2012)
Minopoli, S., Frehse, G.: SL2SX translator: from Simulink to SpaceEx models. In: International Conference on Hybrid Systems: Computation and Control, pp. 93–98. ACM (2016)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Niehage, M., Hartmanns, A., Remke, A.: Learning optimal decisions for stochastic hybrid systems. In: ACM-IEEE International Conference on Formal Methods and Models for System Design (MEMOCODE), pp. 44–55. ACM (2021)
Niehage, M., Pilch, C., Remke, A.: Simulating hybrid petri nets with general transitions and non-linear differential equations. In: VALUETOOLS 2020: 13th EAI International Conference on Performance Evaluation Methodologies and Tools, Tsukuba, Japan, 18–20 May 2020, pp. 88–95. ACM (2020)
Niehage, M., Remke, A.: Learning that grid-convenience does not hurt resilience in the presence of uncertainty. In: Formal Modeling and Analysis of Timed Systems, vol. 13465, pp. 298–306. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-15839-1_17
Pilch, C., Edenfeld, F., Remke, A.: HYPEG: statistical model checking for hybrid petri nets: tool paper. In: EAI International Conference on Performance Evaluation Methodologies and Tools (VALUETOOLS), pp. 186–191. ACM Press (2017)
Pilch, C., Niehage, M., Remke, A.: HPnGs go Non-linear: statistical dependability evaluation of battery-powered systems. In: IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), pp. 157–169. IEEE (2018)
Pilch, C., Remke, A.: Statistical model checking for hybrid petri nets with multiple general transitions. In: Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), pp. 475–486. IEEE (2017)
Platzer, A.: Differential dynamic logic for hybrid systems. J. Autom. Reason. 41(2), 143–189 (2008)
Reicherdt, R., Glesner, S.: Formal verification of discrete-time MATLAB/simulink models using boogie. In: Giannakopoulou, D., Salaün, G. (eds.) SEFM 2014. LNCS, vol. 8702, pp. 190–204. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10431-7_14
Sadigh, D., Kim, E.S., Coogan, S., Sastry, S.S., Seshia, S.A.: A learning based approach to control synthesis of Markov decision processes for linear temporal logic specifications. In: IEEE Conference on Decision and Control, pp. 1091–1096. IEEE (2014)
Saraoğlu, M., Morozov, A., Söylemez, M.T., Janschek, K.: ErrorSim: a tool for error propagation analysis of simulink models. In: Tonetta, S., Schoitsch, E., Bitsch, F. (eds.) SAFECOMP 2017. LNCS, vol. 10488, pp. 245–254. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66266-4_16
Shmarov, F., Zuliani, P.: Probabilistic hybrid systems verification via SMT and monte carlo techniques. In: Bloem, R., Arbel, E. (eds.) HVC 2016. LNCS, vol. 10028, pp. 152–168. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49052-6_10
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, Cambridge (2018)
The MathWorks: Simulink. https://de.mathworks.com/products/simulink.html
The MathWorks: Reinforcement Learning Toolbox. https://www.mathworks.com/products/reinforcement-learning.html
The MathWorks: Simulink Design Verifier. https://de.mathworks.com/products/simulink-design-verifier.html
The MathWorks: Simulink Example: Water Distribution System Scheduling Using Reinforcement Learning. https://de.mathworks.com/help/reinforcement-learning/ug/water-distribution-scheduling-system.html
Tsoutsanis, E., Meskin, N., Benammar, M., Khorasani, K.: Dynamic performance simulation of an aeroderivative gas turbine using the matlab simulink environment. In: ASME International Mechanical Engineering Congress and Exposition, vol. 56246, p. V04AT04A050. American Society of Mechanical Engineers (2013)
Wilson, E.: Probable inference, the law of succession, and statistical inference. J. Am. Stat. Assoc. 22(158), 209–212 (1927)
Zou, L., Zhan, N., Wang, S., Fränzle, M.: Formal verification of simulink/stateflow diagrams. In: Finkbeiner, B., Pu, G., Zhang, L. (eds.) ATVA 2015. LNCS, vol. 9364, pp. 464–481. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24953-7_33
Zuliani, P., Platzer, A., Clarke, E.M.: Bayesian statistical model checking with application to stateflow/simulink verification. Formal Methods Syst. Des. 43, 338–367 (2013)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Adelt, J., Bruch, S., Herber, P., Niehage, M., Remke, A. (2024). Shielded Learning for Resilience and Performance Based on Statistical Model Checking in Simulink. In: Steffen, B. (eds) Bridging the Gap Between AI and Reality. AISoLA 2023. Lecture Notes in Computer Science, vol 14380. Springer, Cham. https://doi.org/10.1007/978-3-031-46002-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-46002-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46001-2
Online ISBN: 978-3-031-46002-9
eBook Packages: Computer ScienceComputer Science (R0)