Certainty Equivalent Perception-Based Control
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
Text
Dean and Recht. "Certainty Equivalent Perception-Based Control." Proceedings of the 3rd Conference on Learning for Dynamics and Control, 2021.Markdown
[Dean and Recht. "Certainty Equivalent Perception-Based Control." Proceedings of the 3rd Conference on Learning for Dynamics and Control, 2021.](https://mlanthology.org/l4dc/2021/dean2021l4dc-certainty/)BibTeX
@inproceedings{dean2021l4dc-certainty,
title = {{Certainty Equivalent Perception-Based Control}},
author = {Dean, Sarah and Recht, Benjamin},
booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control},
year = {2021},
pages = {399-411},
volume = {144},
url = {https://mlanthology.org/l4dc/2021/dean2021l4dc-certainty/}
}