Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
ESAIM: Control, Optimisation and Calculus of Variations · 2021 · 27 · 16
DOI: 10.1051/cocv/2021009 ↗Kurz gefasst
Fachartikel in der Zeitschrift ESAIM: Control, Optimisation and Calculus of Variations, online erschienen am 22.03.2021. Verfasst von Karl Kunisch und 1 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Horizon 2020.
Abstract (Originalsprache)
A learning approach for optimal feedback gains for nonlinear continuous time control systems is proposed and analysed. The goal is to establish a rigorous framework for computing approximating optimal feedback gains using neural networks. The approach rests on two main ingredients. First, an optimal control formulation involving an ensemble of trajectories with ‘control’ variables given by the feedback gain functions. Second, an approximation to the feedback functions via realizations of neural networks. Based on universal approximation properties we prove the existence and convergence of optimal stabilizing neural network feedback controllers.
Förderung
- Horizon 2020
Zitieren
APA
Kunisch, K., & Walter, D. (2021). Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation. ESAIM: Control, Optimisation and Calculus of Variations, 27, 16. https://doi.org/10.1051/cocv/2021009
Vancouver
Kunisch K, Walter D. Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation. ESAIM: Control, Optimisation and Calculus of Variations. 2021;27:16. doi:10.1051/cocv/2021009
BibTeX
@article{Kunisch2021,
author = {Kunisch, Karl and Walter, Daniel},
title = {Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation},
journal = {ESAIM: Control, Optimisation and Calculus of Variations},
year = {2021},
volume = {27},
pages = {16},
doi = {10.1051/cocv/2021009}
}
EUVIMED