Robust Model Reference Adaptive Consensus with Neural Networks

Dongdong Yue; Simone Baldi; Jinde Cao

doi:10.1109/CCDC55256.2022.10033441

Robust Model Reference Adaptive Consensus with Neural Networks

Dongdong Yue^*, Simone Baldi, Jinde Cao

^*Corresponding author for this work

Team Bart De Schutter

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

5 Downloads (Pure)

Abstract

This paper addresses distributed and robust leaderless consensus control for a class of uncertain multiagent systems with matched unknown nonlinearities and disturbances. The problem is challenging due to the lack of a leader (reference signal), the large uncertainties in agent dynamics, and the asymmetric communications among the agents. A novel neural network embedded model reference adaptive consensus (NN-MRACon) framework is proposed, which bridges NN and MRACon by means of nonsmooth control. Asymptotic consensus is proved based on robust analysis and input-to-state stability theory. Numerical examples on networks of second-order integrators and two-mass-spring systems are included to validate the effectiveness of NN-MRACon.

Original language	English
Title of host publication	Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022
Publisher	IEEE
Pages	2503-2508
Number of pages	6
ISBN (Electronic)	978-1-6654-7896-0
DOIs	https://doi.org/10.1109/CCDC55256.2022.10033441
Publication status	Published - 2022
Event	34th Chinese Control and Decision Conference, CCDC 2022 - Hefei, China Duration: 15 Aug 2022 → 17 Aug 2022

Conference

Conference	34th Chinese Control and Decision Conference, CCDC 2022
Country/Territory	China
City	Hefei
Period	15/08/22 → 17/08/22

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Consensus
Neural Networks
Nonsmooth control
Robust adaptive control

Access to Document

10.1109/CCDC55256.2022.10033441

Robust_Model_Reference_Adaptive_Consensus_with_Neural_NetworksFinal published version, 1.59 MB

Cite this

@inproceedings{5473b6129c79421f83ce7ba96494304f,

title = "Robust Model Reference Adaptive Consensus with Neural Networks",

abstract = "This paper addresses distributed and robust leaderless consensus control for a class of uncertain multiagent systems with matched unknown nonlinearities and disturbances. The problem is challenging due to the lack of a leader (reference signal), the large uncertainties in agent dynamics, and the asymmetric communications among the agents. A novel neural network embedded model reference adaptive consensus (NN-MRACon) framework is proposed, which bridges NN and MRACon by means of nonsmooth control. Asymptotic consensus is proved based on robust analysis and input-to-state stability theory. Numerical examples on networks of second-order integrators and two-mass-spring systems are included to validate the effectiveness of NN-MRACon.",

keywords = "Consensus, Neural Networks, Nonsmooth control, Robust adaptive control",

author = "Dongdong Yue and Simone Baldi and Jinde Cao",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 34th Chinese Control and Decision Conference, CCDC 2022 ; Conference date: 15-08-2022 Through 17-08-2022",

year = "2022",

doi = "10.1109/CCDC55256.2022.10033441",

language = "English",

pages = "2503--2508",

booktitle = "Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Robust Model Reference Adaptive Consensus with Neural Networks

AU - Yue, Dongdong

AU - Baldi, Simone

AU - Cao, Jinde

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - This paper addresses distributed and robust leaderless consensus control for a class of uncertain multiagent systems with matched unknown nonlinearities and disturbances. The problem is challenging due to the lack of a leader (reference signal), the large uncertainties in agent dynamics, and the asymmetric communications among the agents. A novel neural network embedded model reference adaptive consensus (NN-MRACon) framework is proposed, which bridges NN and MRACon by means of nonsmooth control. Asymptotic consensus is proved based on robust analysis and input-to-state stability theory. Numerical examples on networks of second-order integrators and two-mass-spring systems are included to validate the effectiveness of NN-MRACon.

AB - This paper addresses distributed and robust leaderless consensus control for a class of uncertain multiagent systems with matched unknown nonlinearities and disturbances. The problem is challenging due to the lack of a leader (reference signal), the large uncertainties in agent dynamics, and the asymmetric communications among the agents. A novel neural network embedded model reference adaptive consensus (NN-MRACon) framework is proposed, which bridges NN and MRACon by means of nonsmooth control. Asymptotic consensus is proved based on robust analysis and input-to-state stability theory. Numerical examples on networks of second-order integrators and two-mass-spring systems are included to validate the effectiveness of NN-MRACon.

KW - Consensus

KW - Neural Networks

KW - Nonsmooth control

KW - Robust adaptive control

UR - http://www.scopus.com/inward/record.url?scp=85149492889&partnerID=8YFLogxK

U2 - 10.1109/CCDC55256.2022.10033441

DO - 10.1109/CCDC55256.2022.10033441

M3 - Conference contribution

AN - SCOPUS:85149492889

SP - 2503

EP - 2508

BT - Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022

PB - IEEE

T2 - 34th Chinese Control and Decision Conference, CCDC 2022

Y2 - 15 August 2022 through 17 August 2022

ER -

Robust Model Reference Adaptive Consensus with Neural Networks

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this