Papers
Topics
Authors
Recent
Search
2000 character limit reached

Robust Stability of Neural Network Control Systems with Interval Matrix Uncertainties

Published 25 Nov 2023 in math.OC, cs.SY, and eess.SY | (2311.15109v2)

Abstract: Neural networks have become increasingly popular in controller design due to their versatility and efficiency. However, their integration into feedback systems can pose stability challenges, particularly in the presence of uncertainties. This work addresses the problem of certifying robust stability in neural network control systems with interval matrix uncertainties. Leveraging classical robust stability techniques and the quadratic constraint-based method to characterize the input-output behavior of neural networks, we derive novel robust stability certificates formulated as linear matrix inequalities. To reduce computational complexity, we introduce three relaxed sufficient conditions and establish their equivalence in terms of feasibility. Additionally, we explore their connections to existing robust stability results. The effectiveness of the proposed approach is demonstrated through inverted pendulum and mass-spring-damper examples.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural Netw., vol. 2, no. 5, pp. 359–366, 1989.
  2. M. Fazlyab, M. Morari, and G. J. Pappas, “Safety verification and robustness analysis of neural networks via quadratic constraints and semidefinite programming,” IEEE Trans. Autom. Control, vol. 67, no. 1, pp. 1–15, 2020.
  3. A. Nikolakopoulou, M. S. Hong, and R. D. Braatz, “Dynamic state feedback controller and observer design for dynamic artificial neural network models,” Automatica, vol. 146, p. 110622, 2022.
  4. R. Schwan, C. N. Jones, and D. Kuhn, “Stability verification of neural network controllers using mixed-integer programming,” IEEE Trans. Autom. Control, 2023.
  5. Y. Zhang, H. Zhang, and X. Xu, “Backward reachability analysis of neural feedback systems using hybrid zonotopes,” IEEE Control Syst. Lett., vol. 7, pp. 2779–2784, 2023.
  6. I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” in Int. Conf. Learn. Rep., 2015.
  7. B. Karg and S. Lucia, “Stability and feasibility of neural network-based controllers via output range analysis,” in IEEE 59th Conf. Decis. Control, 2020, pp. 4947–4954.
  8. F. Fabiani and P. J. Goulart, “Reliably-stabilizing piecewise-affine neural network controllers,” IEEE Trans. Autom. Control, vol. 68, no. 9, pp. 5201 – 5215, 2022.
  9. M. Newton and A. Papachristodoulou, “Sparse polynomial optimisation for neural network verification,” Automatica, vol. 157, p. 111233, 2023.
  10. C. Dawson, S. Gao, and C. Fan, “Safe control with learned certificates: A survey of neural Lyapunov, barrier, and contraction methods for robotics and control,” IEEE Trans. Robot., vol. 39, no. 3, pp. 1749 – 1767, 2023.
  11. 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 IEEE 59th Conf. Decis. Control, 2020, pp. 5929–5934.
  12. M. Jin and J. Lavaei, “Stability-certified reinforcement learning: A control-theoretic perspective,” IEEE Access, vol. 8, pp. 229 086–229 100, 2020.
  13. P. Pauli, D. Gramlich, J. Berberich, and F. Allgöwer, “Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multipliers,” in IEEE 60th Conf. Decis. Control, 2021, pp. 3611–3618.
  14. H. Yin, P. Seiler, and M. Arcak, “Stability analysis using quadratic constraints for systems with neural network controllers,” IEEE Trans. Autom. Control, vol. 67, no. 4, pp. 1980–1987, 2021.
  15. H. Yin, P. Seiler, M. Jin, and M. Arcak, “Imitation learning with stability and safety guarantees,” IEEE Control Syst. Lett., vol. 6, pp. 409–414, 2021.
  16. C. de Souza, A. Girard, and S. Tarbouriech, “Event-triggered neural network control using quadratic constraints for perturbed systems,” Automatica, vol. 157, p. 111237, 2023.
  17. I. R. Petersen and C. V. Hollot, “A Riccati equation approach to the stabilization of uncertain linear systems,” Automatica, vol. 22, no. 4, pp. 397–411, 1986.
  18. I. R. Petersen, “A stabilization algorithm for a class of uncertain linear systems,” Syst. Control Lett., vol. 8, no. 4, pp. 351–357, 1987.
  19. I. R. Petersen and R. Tempo, “Robust control of uncertain systems: Classical results and recent developments,” Automatica, vol. 50, no. 5, pp. 1315–1335, 2014.
  20. A. Ben-Tal and A. Nemirovski, “On tractable approximations of uncertain linear matrix inequalities affected by interval uncertainty,” SIAM J. Optim., vol. 12, no. 3, pp. 811–833, 2002.
  21. W.-J. Mao and J. Chu, “Quadratic stability and stabilization of dynamic interval systems,” IEEE Trans. Autom. Control, vol. 48, no. 6, pp. 1007–1012, 2003.
  22. T. Alamo, R. Tempo, D. R. Ramírez, and E. F. Camacho, “A new vertex result for robustness problems with interval matrix uncertainty,” Syst. Control Lett., vol. 57, no. 6, pp. 474–481, 2008.
  23. K.-K. K. Kim, E. R. Patrón, and R. D. Braatz, “Standard representation and unified stability analysis for dynamic artificial neural network models,” Neural Netw., vol. 98, pp. 251–262, 2018.
  24. A. Megretski and A. Rantzer, “System analysis via integral quadratic constraints,” IEEE Trans. Autom. Control, vol. 42, no. 6, pp. 819–830, 1997.
  25. X. Xu, B. Açıkmeşe, and M. J. Corless, “Observer-based controllers for incrementally quadratic nonlinear systems with disturbances,” IEEE Trans. Autom. Control, vol. 66, no. 3, pp. 1129–1143, 2020.
  26. S. Gowal, K. D. Dvijotham, R. Stanforth, R. Bunel, C. Qin, J. Uesato, R. Arandjelovic, T. Mann, and P. Kohli, “Scalable verified training for provably robust image classification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis., 2019, pp. 4842–4851.
  27. A. Nemirovskii, “Several NP-hard problems arising in robust stability analysis,” Math. Control Sign. Syst., vol. 6, pp. 99–105, 1993.
  28. G. Calafiore and F. Dabbene, “Reduced vertex set result for interval semidefinite optimization problems,” J. Optim. Theory Appl., vol. 139, pp. 17–33, 2008.
  29. C. Meyer Jr and M. Stadelmaier, “Singular M-matrices and inverse positivity,” Linear Algebra Appl., vol. 22, pp. 139–156, 1978.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Authors (2)

  1. Yuhao Zhang 
  2. Xiangru Xu 

Collections

Sign up for free to add this paper to one or more collections.

Sign Up