Graphical Games for UAV Swarm Control Under Time-Varying Communication Networks

TL;DR

This paper introduces a unified graphical game framework for coordinating UAV swarms under dynamic communication networks, enabling scalable, decentralized control with potential extensions to stochastic settings.

Contribution

It presents a novel graphical game-based approach for UAV swarm coordination that handles time-varying networks and scalable decentralized solutions.

Findings

Framework effectively models UAV interactions in dynamic networks

Decomposition approach enables scalable decentralized solutions

Potential for extension to stochastic game settings with deep learning

Abstract

We propose a unified framework for coordinating Unmanned Aerial Vehicle (UAV) swarms operating under time-varying communication networks. Our framework builds on the concept of graphical games, which we argue provides a compelling paradigm to subsume the interaction structures found in networked UAV swarms thanks to the shared local neighborhood properties. We present a general-sum, factorizable payoff function for cooperative UAV swarms based on the aggregated local states and yield a Nash equilibrium for the stage games. Further, we propose a decomposition-based approach to solve stage-graphical games in a scalable and decentralized fashion by approximating virtual, mean neighborhoods. Finally, we discuss extending the proposed framework toward general-sum stochastic games by leveraging deep Q-learning and model-predictive control.