An Attention-Driven Heterogeneous Multiagent Framework for UAV and Satellite-Assisted Task Offloading in Hybrid Ground Device Networks

This paper proposes an integrated satellite-Unmanned Aerial Vehicle (UAV)-terrestrial collaborative computing framework that incorporates Low Earth Orbit (LEO) satellite, UAVs equipped with Mobile Edge Computing (MEC) servers, ground infrastructures, and terrestrial users. A novel three-tier hybrid task decomposition and computation architecture is designed to support efficient task offloading in dynamic and heterogeneous environments. By exploiting the complementary advantages of LEO satellite and UAVs in communication coverage and deployment flexibility, and by utilizing remote high-performance servers, the system ensures improved Quality of Service (QoS), enhanced coverage, scalability, and robustness. To address the heterogeneity in computation demand, latency sensitivity, and mobility patterns of ground devices, the cross-regional task offloading and decomposition problem is formulated as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP), enabling efficient collaborative decision-making among agents with overlapping observations. Furthermore, under the centralized training with decentralized execution (CTDE) paradigm, we propose a hierarchical scheduling algorithm based on heterogeneous multi-agent deep reinforcement learning (DRL), allowing LEO satellite and UAVs to jointly learn optimal strategies during training while autonomously executing decisions in real time. To address the challenges posed by high-dimensional state spaces, we introduce an attention-driven UAV and satellite-assisted task offloading algorithm (ADUS). A multi-head attention mechanism is incorporated into the critic networks, allowing agents to focus on critical features and avoid reliance on full joint state-action representations. Experimental results demonstrate that the proposed algorithm significantly outperforms other baseline methods, including ADUS-NAT, ADUS-NPP, MADDPG, DDPG and MATORA, achieving improvements of 5.45%, 11.25%, 12.04%, 19.61%, 33.25%, and 42.35%, respectively.