A Caltech Library Service

Online Robust Control of Nonlinear Systems with Large Uncertainty

Ho, Dimitar and Le, Hoang M. and Doyle, John and Yue, Yisong (2021) Online Robust Control of Nonlinear Systems with Large Uncertainty. Proceedings of Machine Learning Research, 130 . pp. 3475-3483. ISSN 1938-7228.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.

[img] PDF - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Doyle, John0000-0002-1828-2486
Yue, Yisong0000-0001-9127-1989
Additional Information:© 2021 by the author(s).
Record Number:CaltechAUTHORS:20210510-094452379
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:109028
Deposited By: Tony Diaz
Deposited On:10 May 2021 17:36
Last Modified:14 May 2021 17:30

Repository Staff Only: item control page