Naomi Cooper
Slingshot Aerospace has partnered with the Defense Advanced Research Projects Agency to develop a new system that uses artificial intelligence to identify anomalous spacecraft in large satellite constellations.
Slingshot said Wednesday that the Agatha AI platform uses new approaches to AI data analysis to find potentially nefarious outlier satellites operating within commercial constellations.
Agatha utilizes inverse reinforcement learning to evaluate the behaviors and intentions of space objects and ingests space information to identify anomalies without taking cues from operators.
The AI tool analyzes high-resolution astrometric, photometric and contextual data from sources such as Slingshot Global Sensor Network and Slingshot Seradata.
“Identifying malfunctioning or potentially nefarious objects and their objectives within large satellite constellations is a complex challenge that required us to reach beyond traditional approaches and develop a novel and scalable AI algorithm,” said Dylan Kesler, director of data science and AI at Slingshot Aerospace.
Agatha was developed as part of the Predictive Reporting and Enhanced Constellation Objective Guide program that began in March 2023.
