Goal Reasoning for Satellite Constellation Decision Making

Case Study

Problem:

Insufficient personnel to control an increasing number of satellites while performing an increasing number of mission objectives in maritime recon scenarios.

Solution:

Automation of Surveillance Assets.

    • Utilize Goal Reasoning (GR) techniques to automate imaging tasks effectively for satellites in a constellation (group of satellites), while managing dynamically changing collection goals and priorities.
    • Utilize an AI model to automate constellation Observation, Orientation, Decisions, and Actions. 
    • Demonstrate possible AI agent response to various simulated dynamic events including satellite availability/blackouts, weather conditions, changing mission objectives/priorities, and unexpected observations/behavior. 

Outcome:

    • GR proven it can be used to automate 100s of satellites and 1000s of image tasks in maritime reconnaissance scenarios through extensive testing.
    • GR can task a constellation of 50 satellites over an area the size of the South China Sea while managing hundreds of goals within seconds proven through simulation.
    • By automating satellites, constellation management now requires significantly less manpower.