Earth Observation Satellite Scheduling with Graph Neural Networks and Monte Carlo Tree Search
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911287821205504 |
|---|---|
| author | Jacquet, Antoine Infantes, Guillaume Benazera, Emmanuel Baudoui, Vincent Guerra, Jonathan Roussel, Stéphanie |
| author_facet | Jacquet, Antoine Infantes, Guillaume Benazera, Emmanuel Baudoui, Vincent Guerra, Jonathan Roussel, Stéphanie |
| contents | Earth Observation Satellite Planning (EOSP) is a difficult optimization problem with considerable practical interest. A set of requested observations must be scheduled on an agile Earth observation satellite while respecting constraints on their visibility window, as well as maneuver constraints that impose varying delays between successive observations. In addition, the problem is largely oversubscribed: there are much more candidate observations than can possibly be achieved. Therefore, one must select the set of observations that will be performed while maximizing their cumulative benefit and propose a feasible schedule for these observations. As previous work mostly focused on heuristic and iterative search algorithms, this paper presents a new technique for selecting and scheduling observations based on Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL). GNNs are used to extract relevant information from the graphs representing instances of the EOSP, and DRL drives the search for optimal schedules. A post-learning search step based on Monte Carlo Tree Search (MCTS) is added that is able to find even better solutions. Experiments show that it is able to learn on small problem instances and generalize to larger real-world instances, with very competitive performance compared to traditional approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15041 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Earth Observation Satellite Scheduling with Graph Neural Networks and Monte Carlo Tree Search Jacquet, Antoine Infantes, Guillaume Benazera, Emmanuel Baudoui, Vincent Guerra, Jonathan Roussel, Stéphanie Artificial Intelligence Machine Learning Systems and Control Earth Observation Satellite Planning (EOSP) is a difficult optimization problem with considerable practical interest. A set of requested observations must be scheduled on an agile Earth observation satellite while respecting constraints on their visibility window, as well as maneuver constraints that impose varying delays between successive observations. In addition, the problem is largely oversubscribed: there are much more candidate observations than can possibly be achieved. Therefore, one must select the set of observations that will be performed while maximizing their cumulative benefit and propose a feasible schedule for these observations. As previous work mostly focused on heuristic and iterative search algorithms, this paper presents a new technique for selecting and scheduling observations based on Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL). GNNs are used to extract relevant information from the graphs representing instances of the EOSP, and DRL drives the search for optimal schedules. A post-learning search step based on Monte Carlo Tree Search (MCTS) is added that is able to find even better solutions. Experiments show that it is able to learn on small problem instances and generalize to larger real-world instances, with very competitive performance compared to traditional approaches. |
| title | Earth Observation Satellite Scheduling with Graph Neural Networks and Monte Carlo Tree Search |
| topic | Artificial Intelligence Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2408.15041 |