2000 character limit reached
Forward Invariance in Neural Network Controlled Systems (2309.09043v2)
Published 16 Sep 2023 in eess.SY, cs.LG, cs.SY, and math.OC
Abstract: We present a framework based on interval analysis and monotone systems theory to certify and search for forward invariant sets in nonlinear systems with neural network controllers. The framework (i) constructs localized first-order inclusion functions for the closed-loop system using Jacobian bounds and existing neural network verification tools; (ii) builds a dynamical embedding system where its evaluation along a single trajectory directly corresponds with a nested family of hyper-rectangles provably converging to an attractive set of the original system; (iii) utilizes linear transformations to build families of nested paralleletopes with the same properties. The framework is automated in Python using our interval analysis toolbox $\texttt{npinterval}$, in conjunction with the symbolic arithmetic toolbox $\texttt{sympy}$, demonstrated on an $8$-dimensional leader-follower system.
- S. Chen, K. Saulnier, N. Atanasov, D. D. Lee, V. Kumar, G. J. Pappas, and M. Morari, “Approximating explicit model predictive control using constrained neural networks,” in 2018 Annual American Control Conference (ACC), 2018, pp. 1520–1527.
- U. Topcu, A. Packard, and P. Seiler, “Local stability analysis using simulations and sum-of-squares programming,” Automatica, vol. 44, no. 10, pp. 2669–2675, 2008.
- A. D. Ames, S. Coogan, M. Egerstedt, G. Notomista, K. Sreenath, and P. Tabuada, “Control barrier functions: Theory and applications,” in 18th European control conference (ECC). IEEE, 2019, pp. 3420–3431.
- F. Blanchini, “Set invariance in control,” Automatica, vol. 35, no. 11, pp. 1747–1767, 1999.
- C. Liu, T. Arnon, C. Lazarus, C. Strong, C. Barrett, M. J. Kochenderfer et al., “Algorithms for verifying deep neural networks,” Foundations and Trends® in Optimization, vol. 4, no. 3-4, pp. 244–404, 2021.
- C. Huang, J. Fan, X. Chen, W. Li, and Q. Zhu, “POLAR: A polynomial arithmetic framework for verifying neural-network controlled systems,” in Automated Technology for Verification and Analysis. Springer International Publishing, 2022, pp. 414–430.
- C. Schilling, M. Forets, and S. Guadalupe, “Verification of neural-network control systems by integrating Taylor models and zonotopes,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2022.
- S. Jafarpour, A. Harapanahalli, and S. Coogan, “Interval reachability of nonlinear dynamical systems with neural network controllers,” in Learning for Dynamics and Control Conference. PMLR, 2023.
- ——, “Efficient interaction-aware interval analysis of neural network feedback loops,” arXiv preprint arXiv:2307.14938, 2023.
- M. Everett, G. Habibi, C. Sun, and J. How, “Reachability analysis of neural feedback loops,” IEEE Access, vol. 9, pp. 163 938–163 953, 2021.
- H. Hu, M. Fazlyab, M. Morari, and G. J. Pappas, “Reach-SDP: Reachability analysis of closed-loop systems with neural network controllers via semidefinite programming,” in 59th IEEE Conference on Decision and Control (CDC), 2020, pp. 5929–5934.
- A. Saoud and R. G. Sanfelice, “Computation of controlled invariants for nonlinear systems: Application to safe neural networks approximation and control,” IFAC-PapersOnLine, vol. 54, no. 5, pp. 91–96, 2021, conference on Analysis and Design of Hybrid Systems (ADHS).
- H. Yin, P. Seiler, and M. Arcak, “Stability analysis using quadratic constraints for systems with neural network controllers,” IEEE Transactions on Automatic Control, vol. 67, no. 4, pp. 1980–1987, 2022.
- H. Dai, L. Landry, B.and Yang, M. Pavone, and R. Tedrake, “Lyapunov-stable neural-network control,” arXiv preprint arXiv:2109.14152, 2021.
- E. Bacci, M. Giacobbe, and D. Parker, “Verifying reinforcement learning up to infinity,” in Proceedings of the International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, 2021.
- A. Harapanahalli, S. Jafarpour, and S. Coogan, “A toolbox for fast interval arithmetic in numpy with an application to formal verification of neural network controlled system,” in 2nd ICML Workshop on Formal Verification of Machine Learning, 2023.
- H. Zhang, T.-W. Weng, P.-Y. Chen, C.-J. Hsieh, and L. Daniel, “Efficient neural network robustness certification with general activation functions,” in Advances in Neural Information Processing Systems, vol. 31, 2018, p. 4944–4953.
- V. Tjeng, K. Y. Xiao, and R. Tedrake, “Evaluating robustness of neural networks with mixed integer programming,” in International Conference on Learning Representations, 2019.
- K. Xu, Z. Shi, H. Zhang, Y. Wang, K.-W. Chang, M. Huang, B. Kailkhura, X. Lin, and C.-J. Hsieh, “Automatic perturbation analysis for scalable certified robustness and beyond,” Advances in Neural Information Processing Systems, vol. 33, pp. 1129–1141, 2020.
- D. Angeli and E. D. Sontag, “Monotone control systems,” IEEE Transactions on Automatic Control, vol. 48, no. 10, pp. 1684–1698, 2003.
- G. A. Enciso, H. L. Smith, and E. D. Sontag, “Nonmonotone systems decomposable into monotone systems with negative feedback,” Journal of Differential Equations, vol. 224, no. 1, pp. 205–227, 2006.
- M. Abate and S. Coogan, “Computing robustly forward invariant sets for mixed-monotone systems,” in 2020 59th IEEE Conference on Decision and Control (CDC), 2020, pp. 4553–4559.