Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

Externe Organisationen

  • Technische Universität Berlin
  • Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU Erlangen-Nürnberg)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des Sammelwerks2023 62nd IEEE Conference on Decision and Control, CDC 2023
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten2358-2365
Seitenumfang8
ISBN (elektronisch)9798350301243
PublikationsstatusVeröffentlicht - 2023
Extern publiziertJa
Veranstaltung62nd IEEE Conference on Decision and Control, CDC 2023 - Singapore, Singapur
Dauer: 13 Dez. 202315 Dez. 2023

Publikationsreihe

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0743-1546
ISSN (elektronisch)2576-2370

Abstract

Learning input signals that make a dynamic system respond with a desired output is often data intensive and time consuming. It is therefore natural to ask whether, in a heterogeneous multi-agent scenario, an input signal learned by one agent can be suitably adapted and transferred to make the other agents respond with the same desired output, despite exhibiting different dynamics. In this paper, we propose a novel method to achieve this by employing a dynamic input transfer map. The method does not require any a-priori knowledge of the individual agents' dynamics. Instead, a small amount of experimental data from the source and target systems are used to estimate the transfer map. We evaluate the proposed method and compare it to existing approaches using static input transfer maps by investigating two example scenarios: (i) a simulation scenario for muscle dynamics, (ii) an experimental setting with a group of two-wheeled inverted pendulum robots and a sim-to-real motion learning problem.

ASJC Scopus Sachgebiete

Zitieren

Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics. / Lehmann, Dustin; Drebinger, Philipp; Seel, Thomas et al.
2023 62nd IEEE Conference on Decision and Control, CDC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. S. 2358-2365 (Proceedings of the IEEE Conference on Decision and Control).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Lehmann, D, Drebinger, P, Seel, T & Raisch, J 2023, Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics. in 2023 62nd IEEE Conference on Decision and Control, CDC 2023. Proceedings of the IEEE Conference on Decision and Control, Institute of Electrical and Electronics Engineers Inc., S. 2358-2365, 62nd IEEE Conference on Decision and Control, CDC 2023, Singapore, Singapur, 13 Dez. 2023. https://doi.org/10.1109/cdc49753.2023.10383433
Lehmann, D., Drebinger, P., Seel, T., & Raisch, J. (2023). Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics. In 2023 62nd IEEE Conference on Decision and Control, CDC 2023 (S. 2358-2365). (Proceedings of the IEEE Conference on Decision and Control). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/cdc49753.2023.10383433
Lehmann D, Drebinger P, Seel T, Raisch J. Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics. in 2023 62nd IEEE Conference on Decision and Control, CDC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. S. 2358-2365. (Proceedings of the IEEE Conference on Decision and Control). doi: 10.1109/cdc49753.2023.10383433
Lehmann, Dustin ; Drebinger, Philipp ; Seel, Thomas et al. / Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics. 2023 62nd IEEE Conference on Decision and Control, CDC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. S. 2358-2365 (Proceedings of the IEEE Conference on Decision and Control).
Download
@inproceedings{40e87e6be4764fe4a990564862362fa2,
title = "Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics",
abstract = "Learning input signals that make a dynamic system respond with a desired output is often data intensive and time consuming. It is therefore natural to ask whether, in a heterogeneous multi-agent scenario, an input signal learned by one agent can be suitably adapted and transferred to make the other agents respond with the same desired output, despite exhibiting different dynamics. In this paper, we propose a novel method to achieve this by employing a dynamic input transfer map. The method does not require any a-priori knowledge of the individual agents' dynamics. Instead, a small amount of experimental data from the source and target systems are used to estimate the transfer map. We evaluate the proposed method and compare it to existing approaches using static input transfer maps by investigating two example scenarios: (i) a simulation scenario for muscle dynamics, (ii) an experimental setting with a group of two-wheeled inverted pendulum robots and a sim-to-real motion learning problem.",
author = "Dustin Lehmann and Philipp Drebinger and Thomas Seel and J{\"o}rg Raisch",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 62nd IEEE Conference on Decision and Control, CDC 2023 ; Conference date: 13-12-2023 Through 15-12-2023",
year = "2023",
doi = "10.1109/cdc49753.2023.10383433",
language = "English",
series = "Proceedings of the IEEE Conference on Decision and Control",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2358--2365",
booktitle = "2023 62nd IEEE Conference on Decision and Control, CDC 2023",
address = "United States",

}

Download

TY - GEN

T1 - Data-Driven Dynamic Input Transfer for Learning Control in Multi-Agent Systems with Heterogeneous Unknown Dynamics

AU - Lehmann, Dustin

AU - Drebinger, Philipp

AU - Seel, Thomas

AU - Raisch, Jörg

N1 - Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - Learning input signals that make a dynamic system respond with a desired output is often data intensive and time consuming. It is therefore natural to ask whether, in a heterogeneous multi-agent scenario, an input signal learned by one agent can be suitably adapted and transferred to make the other agents respond with the same desired output, despite exhibiting different dynamics. In this paper, we propose a novel method to achieve this by employing a dynamic input transfer map. The method does not require any a-priori knowledge of the individual agents' dynamics. Instead, a small amount of experimental data from the source and target systems are used to estimate the transfer map. We evaluate the proposed method and compare it to existing approaches using static input transfer maps by investigating two example scenarios: (i) a simulation scenario for muscle dynamics, (ii) an experimental setting with a group of two-wheeled inverted pendulum robots and a sim-to-real motion learning problem.

AB - Learning input signals that make a dynamic system respond with a desired output is often data intensive and time consuming. It is therefore natural to ask whether, in a heterogeneous multi-agent scenario, an input signal learned by one agent can be suitably adapted and transferred to make the other agents respond with the same desired output, despite exhibiting different dynamics. In this paper, we propose a novel method to achieve this by employing a dynamic input transfer map. The method does not require any a-priori knowledge of the individual agents' dynamics. Instead, a small amount of experimental data from the source and target systems are used to estimate the transfer map. We evaluate the proposed method and compare it to existing approaches using static input transfer maps by investigating two example scenarios: (i) a simulation scenario for muscle dynamics, (ii) an experimental setting with a group of two-wheeled inverted pendulum robots and a sim-to-real motion learning problem.

UR - http://www.scopus.com/inward/record.url?scp=85184804007&partnerID=8YFLogxK

U2 - 10.1109/cdc49753.2023.10383433

DO - 10.1109/cdc49753.2023.10383433

M3 - Conference contribution

AN - SCOPUS:85184804007

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 2358

EP - 2365

BT - 2023 62nd IEEE Conference on Decision and Control, CDC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 62nd IEEE Conference on Decision and Control, CDC 2023

Y2 - 13 December 2023 through 15 December 2023

ER -

Von denselben Autoren