NASA、Google の大規模言語モデル「Gemma」を軌道上へ投入

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.

The system, known as NAVI-Orbital, used Gemma 3 to analyze images captured by a YAM-9 satellite built by Loft Orbital. Juan M. 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 coauthors, 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. Notably, Gemma 3 classified the images without being trained or fine-tuned on this particular dataset or its categories; it’s the same base model you can download from Hugging Face and use on a laptop. The benchmark was conducted on the ground to validate the system before launch.

Once the system was in orbit, NASA researchers performed two live capture tests with a camera on Loft’s YAM-9 satellite: one over Toulouse, France, and a second over the coast of Argentina. Gemma 3 generated a text description of each image, and NASA also prompted the LLM 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 onboard YAM-9, which carries a compute cluster of several radiation-hardened processors (FPGAs, CPUs, and GPUs) to serve multiple customer payloads simultaneously. The satellite is powered by solar panels, which provide onboard systems with between 150 and 500 watts, depending on the position of the satellite.

For the live capture experiment, Gemma 3 ran on Nvidia’s Jetson Orin AGX, a small compute module frequently used for robotics and AI tasks. The 4-bit, 4-billion-parameter model requires only 8 gigabytes of memory, which makes it possible for it to run on a lower-power device such as the Orin AGX. “It conveys the message of how lightweight it is. 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.

Contrary to what spy movies would have you believe, most satellites can’t provide fast, high-fidelity image and video feeds to observers on the ground. Bandwidth is often limited and, in most cases, satellites can deliver data to ground stations only at set intervals based on their orbit.

Lasserre believes AI models can work around this problem with “semantic compression.” Instead of sending large amounts of raw image data, a satellite can report a text summary of noteworthy information.

“It doesn’t matter if the link is slow, because you’re downlinking dozens of kilobytes instead of dozens or hundreds of megabytes,” said Lasserre. “It lets you use your satellite in a tactical way, which until now was only in Hollywood movies.”

Delfa expanded on this with a real-world example: wildfire detection. Satellites are currently capable of detecting wildfires, but limits in downlink bandwidth and data processing can delay results by up to 90 minutes. A satellite capable of analyzing an image in space and reporting a plain-text warning might remove this delay.

image NASA’s Jet Propulsion Laboratory tested NAVI-Orbital on a YAM-9 satellite, made by Loft Orbital. Loft Orbital

From image analysis to spacecraft control

Quicker insight is only half of what NAVI-Orbital points toward. The other half relates to the “major shift” Delfa flagged. NAVI-Orbital provides a proof of concept for an alternate means of interacting with spacecraft.

That’s not to say Google Gemma 3 is currently at the controls. NAVI-Orbital is deliberately walled off from the flight software. It reads images and produces descriptions. The system has the capability to make decisions about how images are analyzed but has no access beyond that.

Still, the interface is novel. Retooling the system to search for a different kind of target—such as wildfires—is a matter of editing a text prompt. It doesn’t require rewriting and revalidating onboard software, or training and deploying a different AI model (as was often required with prior image-classification models).

The long-term vision for how this capability could be deployed goes beyond uncrewed satellites and image processing. Delfa said NAVI is rooted in thinking about how AI could serve as a companion for astronauts. “We thought, astronauts have a lot of limitations in the spacesuit in terms of dexterity, so we conceived this idea of having NAVI as a companion to the astronaut, to allow interaction via natural language…. This is the concept that we definitely want to push forward.”

A great deal of additional research will be required to push the technology that far, but NAVI-Orbital’s demonstration has shown that two elements—deploying a large language model in space and controlling it with prompts—are possible.