Datum
2022-11-21Metadata
Zur Langanzeige
Aufsatz
Receding-Horizon Control of Constrained Switched Systems with Neural Networks as Parametric Function Approximators
Zusammenfassung
This work studies receding-horizon control of discrete-time switched linear systems subject to polytopic constraints for the continuous states and inputs. The objective is to approximate the optimal receding-horizon control strategy for cases in which the online computation is intractable due to the necessity of solving mixed-integer quadratic programs in each discrete time instant. The proposed approach builds upon an approximated optimal finite-horizon control law in closed-loop form with guaranteed constraint satisfaction. The paper derives the properties of recursive feasibility and asymptotic stability for the proposed approach. A numerical example is provided for illustration and evaluation of the approach.
Zitierform
In: SN Computer Science Volume 4 / issue 1 (2022-11-21) eissn:2661-8907Förderhinweis
Gefördert im Rahmen des Projekts DEALZitieren
@article{doi:10.17170/kobra-202301047295,
author={Markolf, Lukas and Stursberg, Olaf},
title={Receding-Horizon Control of Constrained Switched Systems with Neural Networks as Parametric Function Approximators},
journal={SN Computer Science},
year={2022}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2022$n2022 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/14328 3000 Markolf, Lukas 3010 Stursberg, Olaf 4000 Receding-Horizon Control of Constrained Switched Systems with Neural Networks as Parametric Function Approximators / Markolf, Lukas 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/14328=x R 4204 \$dAufsatz 4170 5550 {{Modellprädiktive Regelung}} 5550 {{Neuronales Netz}} 5550 {{Optimierung}} 5550 {{Approximation}} 5550 {{Modell}} 7136 ##0##http://hdl.handle.net/123456789/14328
2023-01-04T10:42:56Z 2023-01-04T10:42:56Z 2022-11-21 doi:10.17170/kobra-202301047295 http://hdl.handle.net/123456789/14328 Gefördert im Rahmen des Projekts DEAL eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ Model approximation Neural networks Optimization Online control Reinforcement learning Stability 600 Receding-Horizon Control of Constrained Switched Systems with Neural Networks as Parametric Function Approximators Aufsatz This work studies receding-horizon control of discrete-time switched linear systems subject to polytopic constraints for the continuous states and inputs. The objective is to approximate the optimal receding-horizon control strategy for cases in which the online computation is intractable due to the necessity of solving mixed-integer quadratic programs in each discrete time instant. The proposed approach builds upon an approximated optimal finite-horizon control law in closed-loop form with guaranteed constraint satisfaction. The paper derives the properties of recursive feasibility and asymptotic stability for the proposed approach. A numerical example is provided for illustration and evaluation of the approach. open access Markolf, Lukas Stursberg, Olaf 16 Seiten doi:10.1007/s42979-022-01442-0 Modellprädiktive Regelung Neuronales Netz Optimierung Approximation Modell publishedVersion eissn:2661-8907 issue 1 SN Computer Science Volume 4 false 62
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: