*Result*: Decentralized event-triggered online learning for safe consensus control of multi-agent systems with Gaussian process regression.

Title:
Decentralized event-triggered online learning for safe consensus control of multi-agent systems with Gaussian process regression.
Authors:
Dai, Xiaobing1 (AUTHOR) xiaobing.dai@tum.de, Yang, Zewen1,2 (AUTHOR) zewen.yang@tum.de, Xu, Mengtian1 (AUTHOR) mengtian.xu@tum.de, Zhang, Sihua3 (AUTHOR) sihua.zhang@bit.edu.cn, Liu, Fangzhou4 (AUTHOR) fangzhou.liu@hit.edu.cn, Hattab, Georges2,5 (AUTHOR) hattabg@rki.de, Hirche, Sandra1 (AUTHOR) hirche@tum.de
Source:
European Journal of Control. Nov2024:Part A, Vol. 80, pN.PAG-N.PAG. 1p.
Database:
Supplemental Index

*Further Information*

*Consensus control in multi-agent systems has received significant attention and practical implementation across various domains. However, managing consensus control under unknown dynamics remains a significant challenge for control design due to system uncertainties and environmental disturbances. This paper presents a novel learning-based distributed control law augmented by auxiliary dynamics. Gaussian processes are harnessed to compensate for the unknown components of the multi-agent system. For continuous enhancement in the predictive performance of the Gaussian process model, a data-efficient online learning strategy with a decentralized event-triggered mechanism is proposed. Furthermore, the control performance of the proposed approach is ensured via the Lyapunov theory, based on a probabilistic guarantee for prediction error bounds. To demonstrate the efficacy of the proposed learning-based controller, a comparative analysis is conducted, contrasting it with both conventional distributed control laws and offline learning methodologies. • A distributed learning-based consensus controller for uncertain multi-agent systems • Decentralized event-triggered online learning for individual agents • The analysis of probabilistic practical average consensus is conducted • Comparative simulations are conducted with an in-depth discussion [ABSTRACT FROM AUTHOR]*