Paper Info
Title
Graph Neural Networks for Learning Robot Team Coordination.
Abstract
This paper shows how Graph Neural Networks can be used for learning distributed coordination mechanisms in connected teams of robots. We capture the relational aspect of robot coordination by modeling the robot team as a graph, where each robot is a node, and edges represent communication links. During training, robots learn how to pass messages and update internal states, so that a target behavior is reached. As a proxy for more complex problems, this short paper considers the problem where each robot must locally estimate the algebraic connectivity of the teamu0027s network topology.
Year
Venue
Field
2018
arXiv: Robotics
Graph,Graph neural networks,Control engineering,Algebraic connectivity,Network topology,Theoretical computer science,Engineering,Robot,Complex problems
DocType
Volume
ISSN
Journal
abs/1805.03737
Federated AI for Robotics Workshop, IJCAI-ECAI/ICML/AAMAS 2018
Citations 
PageRank 
References 
1
0.35
8
Authors
1
Name
Order
Citations
PageRank
Amanda Prorok1979.17