Trusted Autonomous Operations of Distributed Satellite Systems Using Optical Sensors

Area of Science:

• Spacecraft Systems Engineering
• Artificial Intelligence in Space Applications
• Earth Observation

Background:

• Distributed Satellite Systems (DSS) offer enhanced mission value through reconfiguration and incremental updates.
• Trusted Autonomous Satellite Operation (TASO) relies on AI for predictive and reactive integrity.
• Autonomous reconfiguration is crucial for DSS in time-critical missions like disaster relief.

Purpose of the Study:

• To explore the application of intelligent Distributed Satellite Systems (iDSS) for near-real-time wildfire management.
• To propose a Low Earth Orbit (LEO) satellite constellation for continuous monitoring of Areas of Interest (AOI).
• To demonstrate the feasibility of AI-based wildfire detection on-board iDSS satellites.

Main Methods:

• Development of an iDSS architecture with reconfiguration capabilities and Inter-Satellite Links (ISL).
• Integration of AI, advanced sensing, and computing technologies for trusted autonomy.
• On-board AI-based data processing using hardware accelerators for wildfire detection.

Main Results:

• Demonstrated the feasibility of AI-based data processing on-board satellite hardware.
• Developed AI software for on-board wildfire detection within the iDSS framework.
• Simulation case studies validated the iDSS architecture for wildfire management across diverse geographic locations.

Conclusions:

• iDSS enables a responsive and resilient approach to Space Mission Management (SMM), particularly for data collection and processing.
• The proposed iDSS architecture supports extensive coverage and rapid revisit intervals essential for dynamic environmental monitoring.
• AI-powered on-board processing significantly enhances the capability of LEO constellations for near-real-time wildfire detection and management.