Papers
Topics
Authors
Recent
Search
2000 character limit reached

Learning deep Koopman operators with convex stability constraints

Published 24 Apr 2024 in eess.SY and cs.SY | (2404.15978v1)

Abstract: In this paper, we present a novel sufficient condition for the stability of discrete-time linear systems that can be represented as a set of piecewise linear constraints, which make them suitable for quadratic programming optimization problems. More specifically, we tackle the problem of imposing asymptotic stability to a Koopman matrix learned from data during iterative gradient descent optimization processes. We show that this sufficient condition can be decoupled by rows of the system matrix, and propose a control barrier function-based projected gradient descent to enforce gradual evolution towards the stability set by running an optimization-in-the-loop during the iterative learning process. We compare the performance of our algorithm with other two recent approaches in the literature, and show that we get close to state-of-the-art performance while providing the added flexibility of allowing the optimization problem to be further customized for specific applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. A. Mauroy and J. Goncalves, “Linear identification of nonlinear systems: A lifting technique based on the koopman operator,” in 2016 IEEE 55th Conference on Decision and Control (CDC).   IEEE, 2016, pp. 6500–6505.
  2. D. Bruder, C. D. Remy, and R. Vasudevan, “Nonlinear system identification of soft robot dynamics using koopman operator theory,” in 2019 International Conference on Robotics and Automation (ICRA).   IEEE, 2019, pp. 6244–6250.
  3. M. Korda and I. Mezić, “Linear predictors for nonlinear dynamical systems: Koopman operator meets Model Predictive Control,” Automatica, vol. 93, pp. 149–160, 2018.
  4. P. J. Schmid, “Dynamic mode decomposition of numerical and experimental data,” Journal of fluid mechanics, vol. 656, pp. 5–28, 2010.
  5. C. W. Rowley, I. Mezić, S. Bagheri, P. Schlatter, and D. S. Henningson, “Spectral analysis of nonlinear flows,” Journal of fluid mechanics, vol. 641, pp. 115–127, 2009.
  6. M. O. Williams, I. G. Kevrekidis, and C. W. Rowley, “A data–driven approximation of the koopman operator: Extending dynamic mode decomposition,” Journal of Nonlinear Science, vol. 25, no. 6, pp. 1307–1346, 2015.
  7. J. L. Proctor, S. L. Brunton, and J. N. Kutz, “Dynamic mode decomposition with control,” SIAM Journal on Applied Dynamical Systems, vol. 15, no. 1, pp. 142–161, 2016.
  8. M. Korda and I. Mezić, “On convergence of extended dynamic mode decomposition to the koopman operator,” Journal of Nonlinear Science, vol. 28, no. 2, pp. 687–710, 2018.
  9. Q. Li, F. Dietrich, E. M. Bollt, and I. G. Kevrekidis, “Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the koopman operator,” Chaos: An Interdisciplinary Journal of Nonlinear Science, vol. 27, no. 10, p. 103111, 2017.
  10. B. Lusch, J. N. Kutz, and S. L. Brunton, “Deep learning for universal linear embeddings of nonlinear dynamics,” Nature communications, vol. 9, no. 1, p. 4950, 2018.
  11. O. Azencot, N. B. Erichson, V. Lin, and M. Mahoney, “Forecasting sequential data using consistent koopman autoencoders,” in International Conference on Machine Learning.   PMLR, 2020, pp. 475–485.
  12. E. Yeung, S. Kundu, and N. Hodas, “Learning deep neural network representations for koopman operators of nonlinear dynamical systems,” in 2019 American Control Conference (ACC).   IEEE, 2019, pp. 4832–4839.
  13. M. O. Williams, M. S. Hemati, S. T. Dawson, I. G. Kevrekidis, and C. W. Rowley, “Extending data-driven koopman analysis to actuated systems,” IFAC-PapersOnLine, vol. 49, no. 18, pp. 704–709, 2016.
  14. J. L. Proctor, S. L. Brunton, and J. N. Kutz, “Generalizing koopman theory to allow for inputs and control,” SIAM Journal on Applied Dynamical Systems, vol. 17, no. 1, pp. 909–930, 2018.
  15. Y. Li, H. He, J. Wu, D. Katabi, and A. Torralba, “Learning compositional koopman operators for model-based control,” in International Conference on Learning Representations, 2019.
  16. I. Abraham and T. D. Murphey, “Active learning of dynamics for data-driven control using koopman operators,” IEEE Transactions on Robotics and Automation, vol. 35, no. 5, pp. 1071–1083, 2019.
  17. E. Kaiser, J. N. Kutz, and S. Brunton, “Data-driven discovery of koopman eigenfunctions for control,” Machine Learning: Science and Technology, 2021.
  18. E. Kaiser, J. N. Kutz, and S. L. Brunton, “Sparse identification of nonlinear dynamics for model predictive control in the low-data limit,” Proceedings of the Royal Society A, vol. 474, no. 2219, p. 20180335, 2018.
  19. G. Mamakoukas, I. Abraham, and T. D. Murphey, “Learning stable models for prediction and control,” IEEE Transactions on Robotics and Automation, 2023.
  20. B. Yi and I. R. Manchester, “On the equivalence of contraction and koopman approaches for nonlinear stability and control,” IEEE Transactions on Automatic Control, 2023.
  21. F. Fan, B. Yi, D. Rye, G. Shi, and I. R. Manchester, “Learning stable Koopman embeddings,” in IEEE American Control Conference.   IEEE, 2022, pp. 2742–2747.
  22. P. Bevanda, M. Beier, S. Kerz, A. Lederer, S. Sosnowski, and S. Hirche, “Diffeomorphically Learning Stable Koopman Operators,” vol. 6, pp. 3427–3432, 2022, conference Name: IEEE Control Systems Letters.
  23. C. Li and Y. Lan, “Koopman analysis of nonlinear systems with a neural network representation,” Communications in Theoretical Physics, vol. 74, no. 9, p. 095604, 2022.
  24. A. Agrawal and K. Sreenath, “Discrete control barrier functions for safety-critical control of discrete systems with application to bipedal robot navigation.” in Robotics: Science and Systems, vol. 13.   Cambridge, MA, USA, 2017, pp. 1–10.
  25. A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer, “Automatic differentiation in pytorch,” 2017.
  26. S. M. Khansari-Zadeh and A. Billard, “Learning stable nonlinear dynamical systems with gaussian mixture models,” IEEE Transactions on Robotics, vol. 27, no. 5, pp. 943–957, 2011.
  27. Gurobi Optimization, LLC, “Gurobi Optimizer Reference Manual,” 2023. [Online]. Available: https://www.gurobi.com
  28. G. Mamakoukas, I. Abraham, and T. D. Murphey, “Learning stable models for prediction and control,” arXiv preprint arXiv:2005.04291, 2020.

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

Collections

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

Sign Up