First-Ever Dynamic Digital Twin Satellite to Launch in Space

• UC Davis and Proteus Space will launch the first self-monitoring digital twin into space aboard a satellite in October 2025.
• The onboard software will continuously assess and predict the satellite’s power system health using real-time AI.

The University of California, Davis has partnered with Proteus Space to launch a government-sponsored satellite featuring an AI-powered digital twin. Scheduled for launch in October 2025 from Vandenberg Space Force Base, the project will go from full approval to liftoff in just 13 months—an unprecedented timeline for a small satellite, which typically takes years to develop.

Developed by the Human/Robotics/Vehicle Integration and Performance (HRVIP) Lab at UC Davis, the digital twin is a software-based model that runs autonomously onboard the spacecraft. It monitors the satellite's power system using real-time sensor data to simulate its current condition and predict future battery performance. This enables the satellite to continuously assess its health without relying on ground-based systems.

“The spacecraft itself can let us know how it’s doing, which is all done by humans now,” said Adam Zufall, a graduate student in the HRVIP Lab who is overseeing the UC Davis side of the project, in a news release from UC Davis.

“It should get smarter as it goes,” said Professor Stephen Robinson in a news release from UC Davis, “and be able to predict how it’s going to perform in the near future. Current satellites do not have this capability.”

The satellite, about the size of a half refrigerator and carrying multiple commercial and research payloads, will launch from Vandenberg Space Force Base in California. It will settle into low Earth orbit and operate for up to 12 months. After three years, it will naturally fall back to Earth, burning up in the atmosphere.

🌀 Tom’s Take:

Digital twins enable machines to monitor and improve themselves, especially in high-risk, remote environments. By learning autonomously in space, they offer insights we might miss in human-led missions.

Source: UC Davis