Towards Realistic Earth-Observation Constellation Scheduling: Benchmark and Methodology

Beihang University
Header Image

This work introduces a comprehensive framework for Agile Earth Observation Satellites (AEOS) constellation scheduling. We present AEOS-Bench, a standardized benchmark with 3,907 satellite assets and 16,410 scenarios, enforcing realistic constraints and providing ground truth annotations. To our knowledge, AEOS-Bench is the first large-scale benchmark for realistic constellation scheduling. We also propose AEOS-Former, a Transformer-based scheduler featuring a novel constraint module. Through simulation-based iterative learning, AEOS-Former outperforms baselines across diverse scenarios, with ablation studies validating the effectiveness of each component. We hope AEOS-Bench and AEOS-Former will drive innovations in AEOS constellation scheduling.

Abstract

Agile Earth Observation Satellites (AEOSs) constellations offer unprecedented flexibility for monitoring the Earth's surface, but their scheduling remains challenging under large-scale scenarios, dynamic environments, and stringent constraints. Existing methods often simplify these complexities, limiting their real-world performance. We address this gap with a unified framework integrating a standardized benchmark suite and a novel scheduling model. Our benchmark suite, AEOS-Bench, contains 3,907 finely tuned satellite assets and 16,410 scenarios. Each scenario features 1 to 50 satellites and 50 to 300 imaging tasks. These scenarios are generated via a high-fidelity simulation platform, ensuring realistic satellite behavior such as orbital dynamics and resource constraints. Ground truth scheduling annotations are provided for each scenario. To our knowledge, AEOS-Bench is the first large-scale benchmark suite tailored for realistic constellation scheduling. Building upon this benchmark, we introduce AEOS-Former, a Transformer-based scheduling model that incorporates a constraint-aware attention mechanism. A dedicated internal constraint module explicitly models the physical and operational limits of each satellite. Through simulation-based iterative learning, AEOS-Former adapts to diverse scenarios, offering a robust solution for AEOS constellation scheduling. Experimental results demonstrate that AEOS-Former outperforms baseline models in task completion and energy efficiency, with ablation studies highlighting the contribution of each model component. Code and sample data are provided in the supplemental materials.

Visualization Demos