The combination of machine learning with control offers many opportunities, in particular for robust control. However, due to strong safety and reliability requirements in many real-world applications, providing rigorous statistical and control-theoretic guarantees is of utmost importance, yet difficult to achieve for learning-based control schemes. We present a general framework for learning-enhanced robust control that allows for systematic integration of prior engineering knowledge, is fully compatible with modern robust control and still comes with rigorous and practically meaningful guarantees. Building on the established Linear Fractional Representation and Integral Quadratic Constraints framework, we integrate Gaussian Process Regression as a learning component and state-of-the-art robust controller synthesis. In a concrete robust control example, our approach is demonstrated to yield improved performance with more data, while guarantees are maintained throughout.
%0 Conference Paper
%1 FieSch21
%A Fiedler, Christian
%A Scherer, Carsten W.
%A Trimpe, Sebastian
%B 60th IEEE Conf. Decision and Control
%D 2021
%K from:carsten.scherer pn4 peerReviewed EXC2075 imng
%P 5122-5129
%T Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
%U https://arxiv.org/abs/2105.03397
%X The combination of machine learning with control offers many opportunities, in particular for robust control. However, due to strong safety and reliability requirements in many real-world applications, providing rigorous statistical and control-theoretic guarantees is of utmost importance, yet difficult to achieve for learning-based control schemes. We present a general framework for learning-enhanced robust control that allows for systematic integration of prior engineering knowledge, is fully compatible with modern robust control and still comes with rigorous and practically meaningful guarantees. Building on the established Linear Fractional Representation and Integral Quadratic Constraints framework, we integrate Gaussian Process Regression as a learning component and state-of-the-art robust controller synthesis. In a concrete robust control example, our approach is demonstrated to yield improved performance with more data, while guarantees are maintained throughout.
@inproceedings{FieSch21,
abstract = {The combination of machine learning with control offers many opportunities, in particular for robust control. However, due to strong safety and reliability requirements in many real-world applications, providing rigorous statistical and control-theoretic guarantees is of utmost importance, yet difficult to achieve for learning-based control schemes. We present a general framework for learning-enhanced robust control that allows for systematic integration of prior engineering knowledge, is fully compatible with modern robust control and still comes with rigorous and practically meaningful guarantees. Building on the established Linear Fractional Representation and Integral Quadratic Constraints framework, we integrate Gaussian Process Regression as a learning component and state-of-the-art robust controller synthesis. In a concrete robust control example, our approach is demonstrated to yield improved performance with more data, while guarantees are maintained throughout.},
added-at = {2023-02-24T09:02:34.000+0100},
archiveprefix = {arXiv},
author = {Fiedler, Christian and Scherer, Carsten W. and Trimpe, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2dadf7256d6d249ad407f613f73b02a09/mathematik},
booktitle = {60th IEEE Conf. Decision and Control},
eprint = {2105.03397},
file = {:FieSch21 - Learning Enhanced Robust Controller Synthesis with Rigorous Statistical and Control Theoretic Guarantees.pdf:PDF},
interhash = {43a93d9b959414f2bdfa6b14df1fd2dd},
intrahash = {dadf7256d6d249ad407f613f73b02a09},
keywords = {from:carsten.scherer pn4 peerReviewed EXC2075 imng},
pages = {5122-5129},
primaryclass = {eess.SY},
timestamp = {2024-03-12T10:23:43.000+0100},
title = {Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees},
url = {https://arxiv.org/abs/2105.03397},
year = 2021
}
