Vista scales sensor control for huge space object tracking tasks
VISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking
Machine LearningArtificial IntelligenceMultiagent Systems
Summary
Space is crowded with many objects orbiting Earth, making it hard to keep track of them all with limited sensors. The authors present VISTA, a new AI method that helps satellites and ground sensors decide where to look and when, even as the number of objects changes a lot. This approach uses smart attention techniques to handle big and changing numbers of space objects without slowing down. Tests show it tracks objects faster and more accurately than previous methods, and can handle up to 20,000 objects with realistic sensor networks. This could improve safety and awareness in space by better managing sensor resources.
What this means in practice
- •For satellite operations teams: Coordinate distributed sensors and satellites to efficiently monitor thousands of space objects by dynamically assigning sensor tasks based on changing uncertainties.
- •For air traffic controllers: Improve monitoring of large fleets of aircraft or drones by adapting sensor tasking to dynamic numbers of targets and sensor capabilities, inspired by VISTA’s approach.
Authors
Miguel Leiva-Vélez, Adalberto Claudio Quiros, Nicolas Gaston Rozado, Hodei Urrutxua, Víctor Rodríguez-Fernández
Abstract
The rapid growth of resident space objects is increasing the complexity of space situational awareness sensor tasking, challenging classical optimization methods as they allocate finite, heterogeneous, and distributed sensing resources across ever-larger catalogues. Existing deep reinforcement learning approaches show promise in reduced settings, but fixed-dimensional state and action representations limit their ability to scale to large, dynamic catalogues and distributed sensing networks. We introduce VISTA (Variable-Entity Intelligent Sensor Tasking Architecture), a scalable deep reinforcement learning architecture for persistent uncertainty-driven catalogue maintenance across variable object populations and sensor configurations. VISTA combines physics- and mission-informed top-K retrieval with entity-centric attention, recurrent memory, and pointer-based action decoding, thereby keeping each agent's observation and action spaces independent of catalogue size. We evaluate VISTA across different scenarios, from fixed-size single-sensor benchmarks to large-scale space-based tasking and heterogeneous cooperative sensing. With 30 orbiting targets, VISTA recovers the catalogue 31.2% faster than the fixed-dimensional recurrent baseline. In the large-scale regime, VISTA reduces five-hour uncertainty by 97.5% relative to the strongest classical reference and by 99.3% relative to the recurrent learner. Zero-shot tests up to 20,000 objects reveal near-linear relations between sensing capacity, catalogue size, and recovery horizon. Learned policies also exhibit sensor modality adaptation and generalization to population and initial-uncertainty shifts. Together, these results demonstrate that VISTA provides a scalable framework for adaptive space situational awareness sensor tasking across large, distributed networks of heterogeneous ground- and space-based sensors.