ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

A decentralized learning strategy to restore connectivity during multi-agent formation control

Dutta, R and Kandath, H and Jayavelu, S and Xiaoli, L and Sundaram, S and Pack, D (2023) A decentralized learning strategy to restore connectivity during multi-agent formation control. In: Neurocomputing, 520 . pp. 33-45.

[img] PDF
neu_520_33-45_2023.pdf - Published Version
Restricted to Registered users only

Download (3MB) | Request a copy
Official URL: https://doi.org/10.1016/j.neucom.2022.11.054


In this paper, we propose a decentralized learning algorithm to restore communication connectivity during multi-agent formation control. The time-varying connectivity profile of a mobile multi-agent system represents the dynamic information exchange capabilities among agents. While connected to the neighbors, each mobile agent in the proposed scheme learns to raise the team connectivity. When the inter-agent communication is lost, the associated trained neural network generates appropriate control actions to restore connectivity. The proposed learning technique leverages an adaptive control formalism, wherein a neural network tries to mimic the negative gradient of a value that relies on the agent-to-neighbor distances. All agents use the conventional consensus protocol during the connected multi-agent dynamics, and under communication loss, only the lost agent executes the neural network predicted actions to come back to the fleet. Simulation results demonstrate the effectiveness of our proposed approach for single/multiple agent loss even in the presence of velocity disturbances. © 2022 Elsevier B.V.

Item Type: Journal Article
Publication: Neurocomputing
Publisher: Elsevier B.V.
Additional Information: The copyright for this article belongs to Elsevier B.V.
Keywords: Adaptive control systems; Learning algorithms; Learning systems; Mobile agents; Restoration, Communication connectivity; Connectivity profile; Connectivity restorations; Decentralized learning; Dynamic information; Formation control; Learning strategy; Multi agent; Neural-networks; Time varying, Multi agent systems
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 09 Jan 2023 06:25
Last Modified: 09 Jan 2023 06:25
URI: https://eprints.iisc.ac.in/id/eprint/78892

Actions (login required)

View Item View Item