Papers
Topics
Authors
Recent
2000 character limit reached

Data-Driven Permissible Safe Control with Barrier Certificates (2405.00136v2)

Published 30 Apr 2024 in cs.LG, cs.RO, cs.SY, and eess.SY

Abstract: This paper introduces a method of identifying a maximal set of safe strategies from data for stochastic systems with unknown dynamics using barrier certificates. The first step is learning the dynamics of the system via Gaussian process (GP) regression and obtaining probabilistic errors for this estimate. Then, we develop an algorithm for constructing piecewise stochastic barrier functions to find a maximal permissible strategy set using the learned GP model, which is based on sequentially pruning the worst controls until a maximal set is identified. The permissible strategies are guaranteed to maintain probabilistic safety for the true system. This is especially important for learning-enabled systems, because a rich strategy space enables additional data collection and complex behaviors while remaining safe. Case studies on linear and nonlinear systems demonstrate that increasing the size of the dataset for learning the system grows the permissible strategy set.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (20)
  1. S. Shalev-Shwartz, S. Shammah, and A. Shashua, “On a Formal Model of Safe and Scalable Self-driving Cars,” arXiv preprint arXiv:1708.06374, 2017.
  2. J. Guiochet, M. Machin, and H. Waeselynck, “Safety-critical Advanced Robots: A survey,” Robotics and Autonomous Systems, vol. 94, pp. 43–52, 2017.
  3. C. Santoyo, M. Dutreix, and S. Coogan, “A barrier function approach to finite-time stochastic system verification and control,” Automatica, vol. 125, p. 109439, 2021.
  4. Y. Yu, T. Wu, B. Xia, J. Wang, and B. Xue, “Safe probabilistic invariance verification for stochastic discrete-time dynamical systems,” in 2023 62nd IEEE Conference on Decision and Control (CDC).   IEEE, 2023, pp. 5804–5811.
  5. F. Berkenkamp, M. Turchetta, A. Schoellig, and A. Krause, “Safe model-based reinforcement learning with stability guarantees,” Advances in neural information processing systems, vol. 30, 2017.
  6. S. R. Chowdhury and A. Gopalan, “On kernelized multi-armed bandits,” in International Conference on Machine Learning.   PMLR, 2017, pp. 844–853.
  7. J. Skovbekk, L. Laurenti, E. Frew, and M. Lahijanian, “Formal abstraction of general stochastic systems via noise partitioning,” IEEE Control Systems Letters, 2023.
  8. R. Mazouz, F. Baymler Mathiesen, L. Laurenti, and M. Lahijanian, “Piecewise Barrier Functions for Stochastic Systems,” arXiv preprint arXiv:2404.16986, 2024.
  9. Z. Wang and R. M. Jungers, “Data-driven computation of invariant sets of discrete time-invariant black-box systems,” arXiv preprint arXiv:1907.12075, 2019.
  10. Y. Gao, K. H. Johansson, and L. Xie, “Computing probabilistic controlled invariant sets,” IEEE Transactions on Automatic Control, vol. 66, no. 7, pp. 3138–3151, 2020.
  11. P. Griffioen, A. Devonport, and M. Arcak, “Probabilistic invariance for gaussian process state space models,” in Learning for Dynamics and Control Conference.   PMLR, 2023, pp. 458–468.
  12. A. Lederer and S. Hirche, “Local asymptotic stability analysis and region of attraction estimation with gaussian processes,” in 2019 IEEE 58th Conference on Decision and Control (CDC).   IEEE, 2019, pp. 1766–1771.
  13. J. Jackson, L. Laurenti, E. Frew, and M. Lahijanian, “Formal verification of unknown dynamical systems via gaussian process regression,” arXiv preprint arXiv:2201.00655, 2021.
  14. P. Jagtap, S. Soudjani, and M. Zamani, “Formal synthesis of stochastic systems via control barrier certificates,” IEEE Transactions on Automatic Control, vol. 66, no. 7, pp. 3097–3110, 2020.
  15. R. Wajid, A. U. Awan, and M. Zamani, “Formal synthesis of safety controllers for unknown stochastic control systems using gaussian process learning,” in Learning for Dynamics and Control Conference.   PMLR, 2022, pp. 624–636.
  16. R. Mazouz, K. Muvvala, A. Ratheesh, L. Laurenti, and M. Lahijanian, “Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions,” Advances in Neural Information Processing Systems, 2022.
  17. F. B. Mathiesen, S. C. Calvert, and L. Laurenti, “Safety Certification for Stochastic Systems via Neural Barrier Functions,” IEEE Control Systems Letters, vol. 7, pp. 973–978, 2022.
  18. 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 Transactions on Robotics, 2023.
  19. N. Srinivas, A. Krause, S. M. Kakade, and M. W. Seeger, “Information-theoretic regret bounds for gaussian process optimization in the bandit setting,” IEEE transactions on information theory, vol. 58, no. 5, pp. 3250–3265, 2012.
  20. I. Steinwart, “On the influence of the kernel on the consistency of support vector machines,” Journal of machine learning research, vol. 2, no. Nov, pp. 67–93, 2001.
Citations (1)

Summary

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

Whiteboard

Paper to Video (Beta)

Open Problems

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

Continue Learning

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

Collections

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

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.