The Aerospace Corp. and Google Public Sector are collaborating to modernize satellite operations using agentic AI, the companies announced.
The two co-developed a proof-of-concept tool to help operators and engineers manage the growing complexity of Proliferated Low Earth Orbit constellations — networks of small satellites that enable faster communication and broader global coverage.
As constellations scale from dozens to thousands of satellites, the volume and velocity of data makes it harder to catch critical signals. Engineers currently monitor separate screens tracking bus telemetry, payload status and ground network availability. When an anomaly hits, on-call staff spend critical minutes manually correlating data to determine whether an alarm is a genuine threat.
Aerospace built the tool with Google Public Sector’s Rapid Innovation Team on Google Cloud’s Vertex AI platform. It fuses disparate telemetry streams into a single interface and moves beyond static threshold alarms toward predictive behavioral monitoring, flagging issues like a momentum wheel that oscillates only when a specific payload is active, before they escalate to component failure. The system also correlates anomalies with context such as recent payload tasks or space weather events and surfaces potential root causes.
“This concept demonstrates how AI can be a critical operational partner capable of handling the high-velocity demands of modern space domain awareness, helping on-call engineers focus their expertise where it matters most,” said Kevin Bell, senior vice president of Aerospace’s Engineering and Technology Group. “Collaborations like this are an important part of Aerospace’s ongoing work to build connections with industry and accelerate the adoption of innovative technologies to support national priorities in space.”
Cameron Groves, director of rapid innovation & specialist engineering at Google Public Sector, said the collaboration marks a milestone in bringing Google’s AI capabilities to space operations.
“This pathfinding effort demonstrates that by equipping engineers with the right data at the right time, we can help transform the operator experience from reactive firefighting to proactive problem-solving to accelerate operations,” he added. “We look forward to seeing this transition from a concept into operational use.”