Communication Dans Un Congrès Année : 2025

Learning the Feasibility of Sets of Acquisition Tasks for Earth Observation Satellites

Résumé

Planning Earth Observation satellite activities involves computing observation sequences while considering timedependent orientation maneuvers. We introduce a novel approach leveraging neural networks and image classification to learn scheduling feasibility for observation tasks. A 0/1 classifier takes an image of POIs along the satellite's orbit as input, estimating whether a schedulable sequence exists within temporal constraints. Learned offline, this classifier enables quick online selection of optimal POI subsets (among candidates) without requiring numerous costly maneuver computations. Experiments show our classifier achieves high accuracy in approximating scheduling feasibility, allowing for efficient optimization with minimal risk of misclassified solutions.

Fichier principal
Vignette du fichier
27_Learning_the_Feasibility_of.pdf (1.24 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05099261 , version 1 (05-06-2025)

Licence

Identifiants

  • HAL Id : hal-05099261 , version 1

Citer

Romain Barrault, Cédric Pralet, Gauthier Picard, Eric Sawyer, Adrien Chan-Hon-Tong. Learning the Feasibility of Sets of Acquisition Tasks for Earth Observation Satellites. IWPSS - International Workshops on Planning and Scheduling for Space, Apr 2025, Toulouse, France. ⟨hal-05099261⟩
59 Consultations
127 Téléchargements

Partager

  • More