Attention-based Reinforcement Learning for Real-Time UAV Semantic Communication

TL;DR

This paper introduces a novel attention-based multi-agent reinforcement learning framework, GAXNet, for real-time UAV communication that significantly improves reward, latency, and reliability in air-to-ground URLLC scenarios.

Contribution

The paper proposes GAXNet, a graph attention exchange network that enhances multi-UAV coordination and communication efficiency in real-time, collision avoidance, and low-latency tasks.

Findings

GAXNet achieves up to 4.5x higher training rewards.

GAXNet reduces latency by 6.5x compared to baselines.

GAXNet maintains ultra-reliable communication with 10^-7 error rate.

Abstract

In this article, we study the problem of air-to-ground ultra-reliable and low-latency communication (URLLC) for a moving ground user. This is done by controlling multiple unmanned aerial vehicles (UAVs) in real time while avoiding inter-UAV collisions. To this end, we propose a novel multi-agent deep reinforcement learning (MADRL) framework, coined a graph attention exchange network (GAXNet). In GAXNet, each UAV constructs an attention graph locally measuring the level of attention to its neighboring UAVs, while exchanging the attention weights with other UAVs so as to reduce the attention mismatch between them. Simulation results corroborates that GAXNet achieves up to 4.5x higher rewards during training. At execution, without incurring inter-UAV collisions, GAXNet achieves 6.5x lower latency with the target 0.0000001 error rate, compared to a state-of-the-art baseline framework.