HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster

2026-05-29

AI Summary

This study addresses the failure of conventional scheduling methods for heterogeneous Earth observation satellite constellations in dynamic and uncertain environments by formulating resource allocation as a sequential decision-making process. The authors propose an adaptive real-time scheduling framework based on model-free multi-agent reinforcement learning. Its core innovation lies in a novel Transformer architecture tailored for heterogeneous satellite swarms, incorporating relational observation-action tokenization and a differential attention mechanism to effectively enable collaborative decision-making, sequence modeling, and cross-task transfer. Experimental results demonstrate that the proposed method significantly outperforms existing baselines across various constellation scales, achieving superior scheduling performance, scalability, and generalization capability.

Abstract

This work addresses the problem of autonomous resource management in heterogeneous satellite cluster conducting Earth Observation (EO) missions including optical and Synthetic Aperture Radar (SAR) satellites. In autonomous operation mode, satellites are equipped with intelligent capabilities enabling real-time decision-making based on the latest conditions, while requiring minimal interaction with ground operators. Traditional scheduling approaches typically rely on mathematical models to represent satellite mission and resource management. Then, this problem is solved by using optimization algorithms. However, such solutions become less effective when the underlying models are not available, over complex, and inaccurate due to dynamic changes and uncertainties inherent in the space mission environment. A promising alternative is to reformulate the problem as a sequential decision-making process and apply model-free reinforcement learning techniques to enable adaptive and real-time resource management. To this end, we propose a novel transformer-based architecture tailored for heterogeneous satellite cluster autonomous EO Mission with relational observations-actions tokenization and differential attention mechanism. Our experimental results demonstrate significant performance improvements compared to the available baselines. Moreover, the proposed architecture exhibits strong adaptability and transferability with respect to varying numbers of satellite clusters.

Problem

• autonomous resource management
• heterogeneous satellite cluster
• Earth Observation
• dynamic uncertainty
• real-time decision-making

Innovation

• Heterogeneous Multi-Agent
• Differential Transformer
• Autonomous Satellite Cluster
• Reinforcement Learning
• Earth Observation