Online Robust Control of Nonlinear Systems with Large Uncertainty

Dimitar Ho, Hoang Le, John Doyle, Yisong Yue
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:3475-3483, 2021.

Abstract

Robust control is a core approach for controlling systems with performance guarantees that are robust to modeling error, and is widely used in real-world systems. However, current robust control approaches can only handle small system uncertainty, and thus require significant effort in system identification prior to controller design. We present an online approach that robustly controls a nonlinear system under large model uncertainty. Our approach is based on decomposing the problem into two sub-problems, “robust control design” (which assumes small model uncertainty) and “chasing consistent models”, which can be solved using existing tools from control theory and online learning, respectively. We provide a learning convergence analysis that yields a finite mistake bound on the number of times performance requirements are not met and can provide strong safety guarantees, by bounding the worst-case state deviation. To the best of our knowledge, this is the first approach for online robust control of nonlinear systems with such learning theoretic and safety guarantees. We also show how to instantiate this framework for general robotic systems, demonstrating the practicality of our approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-ho21a, title = { Online Robust Control of Nonlinear Systems with Large Uncertainty }, author = {Ho, Dimitar and Le, Hoang and Doyle, John and Yue, Yisong}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {3475--3483}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/ho21a/ho21a.pdf}, url = {https://proceedings.mlr.press/v130/ho21a.html}, abstract = { Robust control is a core approach for controlling systems with performance guarantees that are robust to modeling error, and is widely used in real-world systems. However, current robust control approaches can only handle small system uncertainty, and thus require significant effort in system identification prior to controller design. We present an online approach that robustly controls a nonlinear system under large model uncertainty. Our approach is based on decomposing the problem into two sub-problems, “robust control design” (which assumes small model uncertainty) and “chasing consistent models”, which can be solved using existing tools from control theory and online learning, respectively. We provide a learning convergence analysis that yields a finite mistake bound on the number of times performance requirements are not met and can provide strong safety guarantees, by bounding the worst-case state deviation. To the best of our knowledge, this is the first approach for online robust control of nonlinear systems with such learning theoretic and safety guarantees. We also show how to instantiate this framework for general robotic systems, demonstrating the practicality of our approach. } }
Endnote
%0 Conference Paper %T Online Robust Control of Nonlinear Systems with Large Uncertainty %A Dimitar Ho %A Hoang Le %A John Doyle %A Yisong Yue %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-ho21a %I PMLR %P 3475--3483 %U https://proceedings.mlr.press/v130/ho21a.html %V 130 %X Robust control is a core approach for controlling systems with performance guarantees that are robust to modeling error, and is widely used in real-world systems. However, current robust control approaches can only handle small system uncertainty, and thus require significant effort in system identification prior to controller design. We present an online approach that robustly controls a nonlinear system under large model uncertainty. Our approach is based on decomposing the problem into two sub-problems, “robust control design” (which assumes small model uncertainty) and “chasing consistent models”, which can be solved using existing tools from control theory and online learning, respectively. We provide a learning convergence analysis that yields a finite mistake bound on the number of times performance requirements are not met and can provide strong safety guarantees, by bounding the worst-case state deviation. To the best of our knowledge, this is the first approach for online robust control of nonlinear systems with such learning theoretic and safety guarantees. We also show how to instantiate this framework for general robotic systems, demonstrating the practicality of our approach.
APA
Ho, D., Le, H., Doyle, J. & Yue, Y.. (2021). Online Robust Control of Nonlinear Systems with Large Uncertainty . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:3475-3483 Available from https://proceedings.mlr.press/v130/ho21a.html.

Related Material