Decentralized Control with Graph Neural Networks

by   Fernando Gama, et al.

Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information. While centralized controllers are readily available, they face limitations in terms of scalability and implementation, as they do not respect the distributed information structure imposed by the network system of agents. Given the difficulties in finding optimal decentralized controllers, we propose a novel framework using graph neural networks (GNNs) to learn these controllers. GNNs are well-suited for the task since they are naturally distributed architectures and exhibit good scalability and transferability properties. The problems of flocking and multi-agent path planning are explored to illustrate the potential of GNNs in learning decentralized controllers.


Graph Neural Networks for Decentralized Controllers

Dynamical systems comprised of autonomous agents arise in many relevant ...

Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning

The domains of transport and logistics are increasingly relying on auton...

Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks

We consider the problem of finding distributed controllers for large net...

Space-Time Graph Neural Networks with Stochastic Graph Perturbations

Space-time graph neural networks (ST-GNNs) are recently developed archit...

Wide and Deep Graph Neural Networks with Distributed Online Learning

Graph neural networks (GNNs) learn representations from network data wit...

On the Stability of Gated Graph Neural Networks

In this paper, we aim to find the conditions for input-state stability (...

Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Control

When designing large-scale distributed controllers, the information-shar...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset