Liquid-Graph Time-Constant Network for Multi-Agent Systems Control - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Liquid-Graph Time-Constant Network for Multi-Agent Systems Control

Résumé

In this paper, we propose the Liquid-Graph Time- constant (LGTC) network, a continuous graph neural network (GNN) model for control of multi-agent systems based on the recent Liquid Time Constant (LTC) network. We analyse its stability leveraging contraction analysis and propose a closed- form model that preserves the model contraction rate and does not require solving an ODE at each iteration. Compared to discrete models like Graph Gated Neural Networks (GGNNs), the higher expressivity of the proposed model guarantees remarkable performance while reducing the large amount of communicated variables normally required by GNNs. We evaluate our model on a distributed multi-agent control case study (flocking) taking into account variable communication range and scalability under non-instantaneous communication
Fichier principal
Vignette du fichier
root.pdf (532.72 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04552893 , version 1 (19-04-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04552893 , version 1

Citer

Antonio Marino, Claudio Pacchierotti, Paolo Robuffo Giordano. Liquid-Graph Time-Constant Network for Multi-Agent Systems Control. 2024. ⟨hal-04552893⟩
0 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More