DeepAI
Log In Sign Up

A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies

11/02/2021
by   Jan Blumenkamp, et al.
5

Graph Neural Networks (GNNs) are a paradigm-shifting neural architecture to facilitate the learning of complex multi-agent behaviors. Recent work has demonstrated remarkable performance in tasks such as flocking, multi-agent path planning and cooperative coverage. However, the policies derived through GNN-based learning schemes have not yet been deployed to the real-world on physical multi-robot systems. In this work, we present the design of a system that allows for fully decentralized execution of GNN-based policies. We create a framework based on ROS2 and elaborate its details in this paper. We demonstrate our framework on a case-study that requires tight coordination between robots, and present first-of-a-kind results that show successful real-world deployment of GNN-based policies on a decentralized multi-robot system relying on Adhoc communication. A video demonstration of this case-study can be found online. https://www.youtube.com/watch?v=COh-WLn4iO4

READ FULL TEXT
11/26/2020

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

The domains of transport and logistics are increasingly relying on auton...
07/20/2017

Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach

Learning cooperative policies for multi-agent systems is often challenge...
05/18/2021

Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection

In this paper, we develop a learning-based approach for decentralized su...
02/11/2021

Large Scale Distributed Collaborative Unlabeled Motion Planning with Graph Policy Gradients

In this paper, we present a learning method to solve the unlabelled moti...
03/08/2021

Learning Connectivity for Data Distribution in Robot Teams

Many algorithms for control of multi-robot teams operate under the assum...
09/24/2022

Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networks

We consider the problem of finding decentralized strategies for multi-ag...
07/17/2019

A Sequential Composition Framework for Coordinating Multi-Robot Behaviors

A number of coordinated behaviors have been proposed for achieving speci...