NASA Puts Google's Gemma Large Language Model in Orbit
The viability of orbital data centers hosting the largest and most capable large language models (LLMs) remains hotly contested. But enormous deployments that require thousands of GPUs aren't the only way LLMs might prove useful in space. NASA's Jet Propulsion Laboratory recently sent Google's Gemma 3 to space, achieving the first in-orbit demonstration of a vision-language model analyzing imagery from a satellite's own sensor.
Key Takeaways
- The system, known as NAVI-Orbital, used Gemma 3 to analyze images captured by a YAM-9 satellite built by Loft Orbital .
Delfa , technical group lead at NASA, said that though the goal in this case was image analysis, the project's success implies a fundamentally new way researchers on the ground can interact with spacecraft.
- Herson , a tech lead at Loft Orbital .
It coordinates operations with a LangGraph-based conductor and deploys a compressed, 4-bit format of Google's Gemma 3 4B , an open-weights LLM, to produce plain-text image descriptions.
- In addition to generating a text description of each image, NASA prompted Gemma 3 with a set of scripted questions about the images, such as whether they contain commercial or residential areas, or show natural features.
The image analysis also took place on-board YAM-9, which carries a compute cluster of several radiation-hardened processors (FPGAs, CPUs, and GPUs) to serve multiple customer payloads simultaneously.
- You can run it in a tiny, tiny computer," said Delfa.
Getting more useful data across limited bandwidth Paul Lasserre , general manager at Loft Orbital, said vision-capable LLMs could deliver a "paradigm shift" for orbital operations.
- "It lets you use your satellite in a tactical way, which until now was only in Hollywood movies.
Stats & Key Facts
- #NAVI-Orbital was 88 percent accurate when used to classify images in a benchmark dataset of 7,960 images.
The system, known as NAVI-Orbital, used Gemma 3 to analyze images captured by a YAM-9 satellite built by Loft Orbital . Delfa , technical group lead at NASA, said that though the goal in this case was image analysis, the project's success implies a fundamentally new way researchers on the ground can interact with spacecraft. "This is a major shift," said Delfa.
"Now, a scientist can write a prompt, upload it to the spacecraft, and that will be taken into account by the system. It's different from previous paradigms, where researchers have to write very structured commands that require an operations team and process. " Google Gemma 3 goes to space-no modifications required At its core, NAVI-Orbital is an agentic software framework developed by Delfa and his co-authors, Taran Cyriac John , an AI researcher at NASA JPL, and Andrew W.
Herson , a tech lead at Loft Orbital . It coordinates operations with a LangGraph-based conductor and deploys a compressed, 4-bit format of Google's Gemma 3 4B , an open-weights LLM, to produce plain-text image descriptions. NAVI-Orbital was 88 percent accurate when used to classify images in a benchmark dataset of 7,960 images.
For more details please read the original article at IEEE Spectrum AI.
Continue Learning
Comments
Sign in to join the conversation