Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Investigating Robustness in Cyber-Physical Systems: Specification-Centric Analysis in the face of System Deviations (2311.07462v2)

Published 13 Nov 2023 in eess.SY, cs.LO, cs.SE, and cs.SY

Abstract: The adoption of cyber-physical systems (CPS) is on the rise in complex physical environments, encompassing domains such as autonomous vehicles, the Internet of Things (IoT), and smart cities. A critical attribute of CPS is robustness, denoting its capacity to operate safely despite potential disruptions and uncertainties in the operating environment. This paper proposes a novel specification-based robustness, which characterizes the effectiveness of a controller in meeting a specified system requirement, articulated through Signal Temporal Logic (STL) while accounting for possible deviations in the system. This paper also proposes the robustness falsification problem based on the definition, which involves identifying minor deviations capable of violating the specified requirement. We present an innovative two-layer simulation-based analysis framework designed to identify subtle robustness violations. To assess our methodology, we devise a series of benchmark problems wherein system parameters can be adjusted to emulate various forms of uncertainties and disturbances. Initial evaluations indicate that our falsification approach proficiently identifies robustness violations, providing valuable insights for comparing robustness between conventional and reinforcement learning (RL)-based controllers

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. J. Moos, K. Hansel, H. Abdulsamad, S. Stark, D. Clever, and J. Peters, “Robust reinforcement learning: A review of foundations and recent advances,” Machine Learning and Knowledge Extraction, vol. 4, no. 1, pp. 276–315, 2022. [Online]. Available: https://www.mdpi.com/2504-4990/4/1/13
  2. M. Xu, Z. Liu, P. Huang, W. Ding, Z. Cen, B. Li, and D. Zhao, “Trustworthy reinforcement learning against intrinsic vulnerabilities: Robustness, safety, and generalizability,” 2022.
  3. G. Zames, “Input-output feedback stability and robustness, 1959-85,” IEEE Control Systems Magazine, vol. 16, no. 3, pp. 61–66, 1996.
  4. M. Rungger and P. Tabuada, “A notion of robustness for cyber-physical systems,” IEEE Transactions on Automatic Control, vol. 61, no. 8, pp. 2108–2123, 2016.
  5. A. Y. Ng, D. Harada, and S. J. Russell, “Policy invariance under reward transformations: Theory and application to reward shaping,” in Proceedings of the Sixteenth International Conference on Machine Learning, ser. ICML ’99.   San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1999, p. 278–287.
  6. S. Booth, W. B. Knox, J. Shah, S. Niekum, P. Stone, and A. Allievi, “The perils of trial-and-error reward design: Misdesign through overfitting and invalid task specifications,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 5, pp. 5920–5929, Jun. 2023. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/25733
  7. A. Donzé and O. Maler, “Robust satisfaction of temporal logic over real-valued signals,” in Formal Modeling and Analysis of Timed Systems, K. Chatterjee and T. A. Henzinger, Eds.   Berlin, Heidelberg: Springer Berlin Heidelberg, 2010, pp. 92–106.
  8. A. G. Barto, R. S. Sutton, and C. W. Anderson, “Neuronlike adaptive elements that can solve difficult learning control problems,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-13, no. 5, pp. 834–846, 1983.
  9. A. Corso, R. Moss, M. Koren, R. Lee, and M. Kochenderfer, “A survey of algorithms for black-box safety validation of cyber-physical systems,” Journal of Artificial Intelligence Research, vol. 72, pp. 377–428, 2021.
  10. N. Hansen and A. Ostermeier, “Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptation,” in Proceedings of IEEE International Conference on Evolutionary Computation, 1996, pp. 312–317.
  11. K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: Nsga-ii,” IEEE Transactions on Evolutionary Computation, vol. 6, no. 2, pp. 182–197, 2002.
  12. M. Schlüter, J. A. Egea, and J. R. Banga, “Extended ant colony optimization for non-convex mixed integer nonlinear programming,” Computers & Operations Research, vol. 36, no. 7, pp. 2217–2229, 2009. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0305054808001524
  13. A. Donzé, “Breach, a toolbox for verification and parameter synthesis of hybrid systems,” in Computer Aided Verification, T. Touili, B. Cook, and P. Jackson, Eds.   Berlin, Heidelberg: Springer Berlin Heidelberg, 2010, pp. 167–170.
  14. G. Brockman, V. Cheung, L. Pettersson, J. Schneider, J. Schulman, J. Tang, and W. Zaremba, “Openai gym,” 2016.
  15. E. Coumans and Y. Bai, “Pybullet, a python module for physics simulation for games, robotics and machine learning,” http://pybullet.org, 2016.
  16. A. Avizienis, J.-C. Laprie, B. Randell, and C. Landwehr, “Basic concepts and taxonomy of dependable and secure computing,” IEEE Transactions on Dependable and Secure Computing, vol. 1, no. 1, pp. 11–33, 2004.
  17. I. Haghighi, N. Mehdipour, E. Bartocci, and C. Belta, “Control from signal temporal logic specifications with smooth cumulative quantitative semantics,” in 2019 IEEE 58th Conference on Decision and Control (CDC), 2019, pp. 4361–4366.
  18. N. Mehdipour, C.-I. Vasile, and C. Belta, “Arithmetic-geometric mean robustness for control from signal temporal logic specifications,” in 2019 American Control Conference (ACC), 2019, pp. 1690–1695.
  19. V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing atari with deep reinforcement learning,” 2013.
  20. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” 2017.
  21. S. Gronauer, “Bullet-safety-gym: A framework for constrained reinforcement learning,” mediaTUM, Tech. Rep., 2022.
  22. Z. Liu, Z. Guo, Z. Cen, H. Zhang, J. Tan, B. Li, and D. Zhao, “On the robustness of safe reinforcement learning under observational perturbations,” 2023.
  23. T. Haarnoja, A. Zhou, P. Abbeel, and S. Levine, “Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor,” 2018.
  24. J. Song, D. Lyu, Z. Zhang, Z. Wang, T. Zhang, and L. Ma, “When cyber-physical systems meet ai: A benchmark, an evaluation, and a way forward,” in Proceedings of the 44th International Conference on Software Engineering: Software Engineering in Practice, ser. ICSE-SEIP ’22.   New York, NY, USA: Association for Computing Machinery, 2022, p. 343–352. [Online]. Available: https://doi.org/10.1145/3510457.3513049
  25. X. Jin, J. V. Deshmukh, J. Kapinski, K. Ueda, and K. Butts, “Powertrain control verification benchmark,” in Proceedings of the 17th International Conference on Hybrid Systems: Computation and Control, ser. HSCC ’14.   New York, NY, USA: Association for Computing Machinery, 2014, p. 253–262. [Online]. Available: https://doi.org/10.1145/2562059.2562140
  26. T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra, “Continuous control with deep reinforcement learning,” 2019.
  27. S. Fujimoto, H. van Hoof, and D. Meger, “Addressing function approximation error in actor-critic methods,” in Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, J. Dy and A. Krause, Eds., vol. 80.   PMLR, 10–15 Jul 2018, pp. 1587–1596. [Online]. Available: https://proceedings.mlr.press/v80/fujimoto18a.html
  28. I. Goodfellow, P. McDaniel, and N. Papernot, “Making machine learning robust against adversarial inputs,” Commun. ACM, vol. 61, no. 7, p. 56–66, jun 2018. [Online]. Available: https://doi.org/10.1145/3134599
  29. Q. Thibeault, J. Anderson, A. Chandratre, G. Pedrielli, and G. Fainekos, “Psy-taliro: A python toolbox for search-based test generation for cyber-physical systems,” 2021.
  30. T. Dreossi, D. J. Fremont, S. Ghosh, E. Kim, H. Ravanbakhsh, M. Vazquez-Chanlatte, and S. A. Seshia, “Verifai: A toolkit for the formal design and analysis of artificial intelligence-based systems,” in Computer Aided Verification, I. Dillig and S. Tasiran, Eds.   Cham: Springer International Publishing, 2019, pp. 432–442.
  31. T. Dreossi, A. Donzé, and S. A. Seshia, “Compositional falsification of cyber-physical systems with machine learning components,” Journal of Automated Reasoning, vol. 63, pp. 1031–1053, 2019.
  32. X. B. Peng, M. Andrychowicz, W. Zaremba, and P. Abbeel, “Sim-to-real transfer of robotic control with dynamics randomization,” in 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018, pp. 3803–3810.
  33. F. Sadeghi and S. Levine, “Cad2rl: Real single-image flight without a single real image,” 2017.
  34. J. Tobin, R. Fong, A. Ray, J. Schneider, W. Zaremba, and P. Abbeel, “Domain randomization for transferring deep neural networks from simulation to the real world,” 2017.
  35. E. Lecarpentier and E. Rachelson, “Non-stationary markov decision processes, a worst-case approach using model-based reinforcement learning,” in Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, Eds., vol. 32.   Curran Associates, Inc., 2019.
  36. M. A. Abdullah, H. Ren, H. B. Ammar, V. Milenkovic, R. Luo, M. Zhang, and J. Wang, “Wasserstein robust reinforcement learning,” 2019.
  37. I. Yang, “A convex optimization approach to distributionally robust markov decision processes with wasserstein distance,” IEEE Control Systems Letters, vol. 1, no. 1, pp. 164–169, 2017.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets