Certainty Equivalent Perception-Based Control

Sarah Dean, Benjamin Recht
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:399-411, 2021.

Abstract

In order to certify performance and safety, feedback control requires precise characterization of sensor errors. In this paper, we provide guarantees on such feedback systems when sensors are characterized by solving a supervised learning problem. We show a uniform error bound on nonparametric kernel regression under a dynamically-achievable dense sampling scheme. This allows for a finite-time convergence rate on the sub-optimality of using the regressor in closed-loop for waypoint tracking. We demonstrate our results in simulation with simplified unmanned aerial vehicle and autonomous driving examples.

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-dean21a, title = {Certainty Equivalent Perception-Based Control}, author = {Dean, Sarah and Recht, Benjamin}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {399--411}, year = {2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and A. Parrilo, Pablo and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, volume = {144}, series = {Proceedings of Machine Learning Research}, month = {07 -- 08 June}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v144/dean21a/dean21a.pdf}, url = {https://proceedings.mlr.press/v144/dean21a.html}, abstract = {In order to certify performance and safety, feedback control requires precise characterization of sensor errors. In this paper, we provide guarantees on such feedback systems when sensors are characterized by solving a supervised learning problem. We show a uniform error bound on nonparametric kernel regression under a dynamically-achievable dense sampling scheme. This allows for a finite-time convergence rate on the sub-optimality of using the regressor in closed-loop for waypoint tracking. We demonstrate our results in simulation with simplified unmanned aerial vehicle and autonomous driving examples.} }
Endnote
%0 Conference Paper %T Certainty Equivalent Perception-Based Control %A Sarah Dean %A Benjamin Recht %B Proceedings of the 3rd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2021 %E Ali Jadbabaie %E John Lygeros %E George J. Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire J. Tomlin %E Melanie N. Zeilinger %F pmlr-v144-dean21a %I PMLR %P 399--411 %U https://proceedings.mlr.press/v144/dean21a.html %V 144 %X In order to certify performance and safety, feedback control requires precise characterization of sensor errors. In this paper, we provide guarantees on such feedback systems when sensors are characterized by solving a supervised learning problem. We show a uniform error bound on nonparametric kernel regression under a dynamically-achievable dense sampling scheme. This allows for a finite-time convergence rate on the sub-optimality of using the regressor in closed-loop for waypoint tracking. We demonstrate our results in simulation with simplified unmanned aerial vehicle and autonomous driving examples.
APA
Dean, S. & Recht, B.. (2021). Certainty Equivalent Perception-Based Control. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:399-411 Available from https://proceedings.mlr.press/v144/dean21a.html.

Related Material