Control of Unknown (Linear) Systems with Receding Horizon Learning

Christian Ebenbauer, Fabian Pfitz, Shuyou Yu
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:584-596, 2021.

Abstract

A receding horizon learning scheme is proposed to transfer the state of a discrete-time dynamical control system to zero without the need of a system model. Global state convergence to zero is proved for the class of stabilizable and detectable linear time-invariant systems, assuming that only input and output data is available and an upper bound of the state dimension is known. The proposed scheme consists of a receding horizon control scheme and a proximity-based estimation scheme to estimate and control the closed-loop trajectory

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-ebenbauer21a, title = {Control of Unknown (Linear) Systems with Receding Horizon Learning}, author = {Ebenbauer, Christian and Pfitz, Fabian and Yu, Shuyou}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {584--596}, 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/ebenbauer21a/ebenbauer21a.pdf}, url = {https://proceedings.mlr.press/v144/ebenbauer21a.html}, abstract = {A receding horizon learning scheme is proposed to transfer the state of a discrete-time dynamical control system to zero without the need of a system model. Global state convergence to zero is proved for the class of stabilizable and detectable linear time-invariant systems, assuming that only input and output data is available and an upper bound of the state dimension is known. The proposed scheme consists of a receding horizon control scheme and a proximity-based estimation scheme to estimate and control the closed-loop trajectory} }
Endnote
%0 Conference Paper %T Control of Unknown (Linear) Systems with Receding Horizon Learning %A Christian Ebenbauer %A Fabian Pfitz %A Shuyou Yu %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-ebenbauer21a %I PMLR %P 584--596 %U https://proceedings.mlr.press/v144/ebenbauer21a.html %V 144 %X A receding horizon learning scheme is proposed to transfer the state of a discrete-time dynamical control system to zero without the need of a system model. Global state convergence to zero is proved for the class of stabilizable and detectable linear time-invariant systems, assuming that only input and output data is available and an upper bound of the state dimension is known. The proposed scheme consists of a receding horizon control scheme and a proximity-based estimation scheme to estimate and control the closed-loop trajectory
APA
Ebenbauer, C., Pfitz, F. & Yu, S.. (2021). Control of Unknown (Linear) Systems with Receding Horizon Learning. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:584-596 Available from https://proceedings.mlr.press/v144/ebenbauer21a.html.

Related Material