With over 10,000 satellites planned for deployment by various international entities, verifying the operation of these satellites is critical.
"Agatha represents a breakthrough in how AI can deliver unparalleled space domain awareness, as its ability to find these needles in the haystack is something no human, or team of humans, could possibly execute," said Dr. Dylan Kesler, Director of Data Science and AI, Slingshot Aerospace.
"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. Our Agatha model has also proven its ability to deliver high-quality insights that provide 'explainability' or context for why specific objects were flagged."
Agatha was trained on over 60 years of simulated constellation data created by Slingshot. The system was tested by identifying non-nefarious outliers in real-world commercial constellations. Slingshot confirmed with satellite operators that the identified satellites had differences in hardware, mission, and operational parameters.
Agatha AI uses inverse reinforcement learning (IRL) to evaluate behaviors and identify policies and intentions of the tracked objects. This method focuses on the strategic questions of why satellites exhibit specific behaviors and their intentions. Agatha processes large amounts of data without requiring cues, identifying anomalies as they appear.
The need for AI technologies like Agatha is underscored by the planned satellite deployments. By early 2023, the International Telecommunication Union had received filings for over 300 constellations totaling more than 1 million satellites. Agatha analyzes high-resolution data from the Slingshot Platform's data lake, which includes data from the Slingshot Global Sensor Network, Slingshot Seradata, and other sources. The AI also evaluates satellites' communication locations and times with Earth and other data streams.
Slingshot's PRECOG program, which developed Agatha, began in March 2023 and was completed in January 2024. Slingshot is now focused on implementing Agatha and discussing deployment methods with the U.S. government and commercial space companies.
"As space activity shifts from satellites owned by a small number of operators to massive constellations operated by an array of owners, the need for transparency increases," said Kesler.
"The ability to quickly identify anomalies - whether a malfunctioning spacecraft or an intentionally nefarious 'wolf in sheep's clothing' - is an increasingly important aspect of maintaining safety and security in space and on Earth."
"Having worked previously in the BioTech world and with gene editing technologies like CRISPR, I know that tools like Agatha and approaches like inverse reinforcement learning almost certainly would have helped us find anomalies in the oceans of genomic data we analyzed," continued Kesler.
"Inverse reinforcement learning is an AI technique on the bleeding edge of development and we expect its use to grow exponentially in the years to come to solve a variety of problems, not just in space."
Agatha's adaptability and scalability make it applicable beyond space. Its ability to handle large data sets and find anomalies means it can be used in genomics, biomedicine, agriculture, and utility optimization.
Kylee Keskerian [email protected]
Related Links
Slingshot Aerospace
Military Space News at SpaceWar.com
| Subscribe Free To Our Daily Newsletters |
| Subscribe Free To Our Daily Newsletters |
