Mini fridge-sized satellites are about to bring about major changes in space technology, but it's happening rapidly.
Researchers at UC Davis have created a new kind of satellite system that can use AI to monitor and predict unique states in real time. This is the first time a digital brain has been built into a spacecraft that operates independently in orbit. And the most impressive part? The entire project takes just 13 months from planning to launch. This is almost unprecedented in space missions.
Faster paths to space
Most satellite projects take years to develop and launch. However, the mission is scheduled to take off from a California base in October 2025, breaking records by cutting the timeline to just one year. This is partly due to the partnership between university scientists and engineers and the field of Proteus. Together, they built what they called the first “quickly design to deployment” satellite system of this kind.
Smart brain for satellites
The most exciting feature of this mission is the custom payload. This is a special package within a satellite built by researchers. This package features a digital twin, a computer model that functions like a mirror in a satellite power system. However, unlike previous versions of digital twins that stay on Earth and get the latest information from space, this lives inside the satellite itself.
This means that the satellite doesn't have to “call home” to understand how it is. Instead, we use built-in sensors and software to constantly check the health of your own battery, monitor power levels, and determine what happens next.
“The spaceship itself can let us know how it is, and this is all done by humans,” explained Adam Zufall, a graduate researcher who helps lead the project.
By using artificial intelligence, the satellite's brains don't just collect data. Also, you will learn from it. Over time, the system should improve by guessing how the battery and how the system will work next. This helps the satellite to tune the operations on its own, even before problems arise.
“You should get smarter as you go,” said Professor Stephen Robinson, who directs the lab that built the payload. “And we can predict how it will work in the near future. The current satellites don't have this capability.”
We will cooperate across fields
Building this kind of technology requires teamwork. The project brings together experts in robotics, space systems, computer science and battery research. In addition to Robinson and Zuhl, the team includes another mechanical engineering professor with a focus on battery management. His lab is studying how batteries behave under a variety of conditions, including space.
Graduate students in engineering and computer science also play a major role. One student will help design the software for the spacecraft, while the other students will work on how AI will make predictions and respond to changes in power levels.
Together they built models that could monitor voltages and other measurements, and understood the amount of energy that the satellite could store and use.
The satellite has several other payloads, both commercial and scientific. But the real highlight is looking at this AI-powered system and adjusting it on the spot.
What happens after booting
When fired from the Vandenberg Space Force Base, the satellite travels into low Earth orbit. It is designed to stay active for up to 12 months, collect data and test your smart brain in the harsh conditions of space. This type of orbit is hundreds of miles above the surface of the Earth, and is sufficient to test the system, but close enough for short communication times.
After the mission is completed, the satellite will continue in orbit for another two years. By the end of its lifespan, gravity and drag forces will pull it back to Earth, where it will burn safely in the atmosphere. This type of planned collapse helps keep the space clean and reduce the risk of debris collisions.
The entire mission shows how fast and flexible future space projects will become. Instead of waiting for the system to be built and tested, researchers were able to design, launch and operate smart satellites in a matter of months. This could open the door to more frequent missions, more advanced designs and smarter satellites.
Changing the future of spaceships
Satellites that can take care of themselves offer great benefits. Currently, spacecraft relies on ground teams to tell them what to do, perform checks and address issues. This will cause delays, increase costs and add additional risk.
With real-time digital twins on board, future satellites can be tailored to their own issues. They were able to shut down failed parts, save power if necessary, and alert engineers of upcoming issues a few days ago.
This reduces workload for ground teams and improves livelihood and safety on space missions.
The team behind this project believes their work is just the beginning. With more advanced AI tools and faster build times, space technology could move at a much faster pace. More importantly, it can be smarter, more reliable and more sensitive to change. The satellite may be small, but it could help to initiate major changes in the way space systems are built and executed.
