SAN FRANCISCO – Before uploading a large language model to space-grade hardware, Boeing space mission systems engineers sought guidance from the hardware manufacturer.
“They told us it wasn’t possible, but we were skilled engineers looking for a way to make it possible,” said Arvel Chappell III, director of the Boeing Space Mission Systems AI Lab. Space News.
In recent ground tests, Boeing engineers demonstrated that a large language model running on commercial off-the-shelf hardware can examine telemetry and report in natural language on the satellite’s health.
“It accelerates latency,” Chappell said. “We were looking at talking to our satellite in natural language and getting meaningful responses instead of zeros and ones that had to be understood by ground software and engineers.”
space-based edge
Traditionally, satellites have sent telemetry to the ground for analysis. Increasingly, companies are developing cutting-edge computers for satellites and adapting terrestrial instruments for space applications.
“You want to do your calculations as close to where you need it as possible,” Chappell said. “In the case of satellite, if you have information that needs to be calculated, you want it to be done as close to the device as possible and then send the results down.”
However, space-efficient devices often lack the memory and power required for larger language models. Because hardware could take years to become space-capable, Boeing engineers modified a large language model to run on existing hardware.
“We wanted to provide a way for our existing groups to enable the processing of artificial intelligence models in space,” Chappell said. “We proved in the lab that we can enable this capability with a software upgrade.”
AI Lab
The Boeing Space Mission Systems AI Lab, formally established in 2025, is like an accelerator. Employees in El Segundo, California, where Boeing designs and builds communications satellites, present the idea.
“You can’t enter the lab until you’ve made a prototype of what you’re trying to build because we don’t want a lot of PowerPoint engineering,” Chappell said. “Come with your value proposition, we’ll give you some funding. Then, we’ll move fast, learn and iterate.”
Engineers in the AI Lab are testing ways to increase satellite autonomy and simplify satellite operations. AI models are based on physics to strengthen security and prevent hallucinations. Boeing has also focused on narrative alignment “to make sure the models can align with our customers’ values and our Boeing values as well,” Chappell said.
