Safe Control with Minimal Regret

Andrea Martin, Luca Furieri, Florian Dörfler, John Lygeros, Giancarlo Ferrari-Trecate
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:726-738, 2022.

Abstract

As we move towards safety-critical cyber-physical systems that operate in non-stationary and uncertain environments, it becomes crucial to close the gap between classical optimal control algorithms and adaptive learning-based methods. In this paper, we present an efficient optimization-based approach for computing a finite-horizon robustly safe control policy that minimizes dynamic regret, in the sense of the loss relative to the optimal sequence of control actions selected in hindsight by a clairvoyant controller. By leveraging the system level synthesis framework (SLS), our method extends recent results on regret minimization for the linear quadratic regulator to optimal control subject to hard safety constraints, and allows competing against a safety-aware clairvoyant policy with minor modifications. Numerical experiments confirm superior performance with respect to finite-horizon constrained H2 and H-infinity control laws when the disturbance realizations poorly fit classical assumptions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v168-martin22a, title = {Safe Control with Minimal Regret}, author = {Martin, Andrea and Furieri, Luca and D\"orfler, Florian and Lygeros, John and Ferrari-Trecate, Giancarlo}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {726--738}, year = {2022}, editor = {Firoozi, Roya and Mehr, Negar and Yel, Esen and Antonova, Rika and Bohg, Jeannette and Schwager, Mac and Kochenderfer, Mykel}, volume = {168}, series = {Proceedings of Machine Learning Research}, month = {23--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v168/martin22a/martin22a.pdf}, url = {https://proceedings.mlr.press/v168/martin22a.html}, abstract = {As we move towards safety-critical cyber-physical systems that operate in non-stationary and uncertain environments, it becomes crucial to close the gap between classical optimal control algorithms and adaptive learning-based methods. In this paper, we present an efficient optimization-based approach for computing a finite-horizon robustly safe control policy that minimizes dynamic regret, in the sense of the loss relative to the optimal sequence of control actions selected in hindsight by a clairvoyant controller. By leveraging the system level synthesis framework (SLS), our method extends recent results on regret minimization for the linear quadratic regulator to optimal control subject to hard safety constraints, and allows competing against a safety-aware clairvoyant policy with minor modifications. Numerical experiments confirm superior performance with respect to finite-horizon constrained H2 and H-infinity control laws when the disturbance realizations poorly fit classical assumptions.} }
Endnote
%0 Conference Paper %T Safe Control with Minimal Regret %A Andrea Martin %A Luca Furieri %A Florian Dörfler %A John Lygeros %A Giancarlo Ferrari-Trecate %B Proceedings of The 4th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2022 %E Roya Firoozi %E Negar Mehr %E Esen Yel %E Rika Antonova %E Jeannette Bohg %E Mac Schwager %E Mykel Kochenderfer %F pmlr-v168-martin22a %I PMLR %P 726--738 %U https://proceedings.mlr.press/v168/martin22a.html %V 168 %X As we move towards safety-critical cyber-physical systems that operate in non-stationary and uncertain environments, it becomes crucial to close the gap between classical optimal control algorithms and adaptive learning-based methods. In this paper, we present an efficient optimization-based approach for computing a finite-horizon robustly safe control policy that minimizes dynamic regret, in the sense of the loss relative to the optimal sequence of control actions selected in hindsight by a clairvoyant controller. By leveraging the system level synthesis framework (SLS), our method extends recent results on regret minimization for the linear quadratic regulator to optimal control subject to hard safety constraints, and allows competing against a safety-aware clairvoyant policy with minor modifications. Numerical experiments confirm superior performance with respect to finite-horizon constrained H2 and H-infinity control laws when the disturbance realizations poorly fit classical assumptions.
APA
Martin, A., Furieri, L., Dörfler, F., Lygeros, J. & Ferrari-Trecate, G.. (2022). Safe Control with Minimal Regret. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:726-738 Available from https://proceedings.mlr.press/v168/martin22a.html.

Related Material