The moon is about to host a giant leap in artificial intelligence (AI).
A Canadian machine learning system will arrive on the lunar surface aboard a United Arab Emirates rover launched with SpaceX on December 11.
Hosted on the Japanese iSpace lander, the Rashid rover is expected to land this spring in search of minerals and other objects of interest on the lunar surface. Canada’s system will inform the rover’s decision-making in a major first for AI: No AI has ever reached beyond low-Earth orbit before, company officials say.
If this works, the technology will be huge for NASA’s lunar push, Mission Control Space Services (MCSS) Executive Director Ewan Reid told Space.com. “AI will be a critical tool for making decisions aboard spacecraft,” Reid said. This work extends not only to searching for water on the moon, as NASA plans to do with its Artemis missions, but also to making Earth observation more efficient. And MCSS, a company with just 40 people so far, aims to be in the driver’s seat.
Related: Canadian astronauts will begin flying to the moon in 2023 with NASA’s Artemis mission
When most people think of Canadian technology in space, they think of flashy projects like Canadarm: the series of robotic arms that have served the Space Shuttle, the International Space Station and soon NASA’s Gateway lunar station. More astute observers might also cite space medicine or even rocketry as fields of technology in which Canada has expertise.
MCSS represents what many small Canadian businesses do: provide essential software or components that fly in the background, fueling missions around the world. The company does not advertise all of its work; often, MCSS clients want media attention on their own mission, Reid said.
“That’s why this [AI] Demonstration with the Canadian Space Agency is nice because it’s very public and we’re allowed to talk about it, Reid said.
If all goes according to plan, Rashid will run for about one lunar day (29 Earth days) on the surface. It is not expected to last the entire lunar night, but as a demonstration mission it is perfectly fine for MCSS. It plans to make the most of its precious few days on the moon.
Related: Timeline of the Moon: Mankind’s Explorations of the Moon
MCSS will receive the Rashid rover’s navigation images via the Japanese lander, which will handle communications with Earth. With the Canadian company’s algorithm, “every single pixel in the image [will be] classified as a certain terrain type,” Reid said.
“This result will then be sent to the ground and will be used by scientists and engineers at our office in Ottawa, as well as at other Canadian universities, to help decide where the rover should go,” he added. Future missions will take the human “out of the loop” once the engineers are confident that the AI knows how to tell different minerals apart, and distinguish between critical mission objects such as rocks and craters.
On the moon, AI can save a lot of limited satellite bandwidth since it will only share data, images and videos that scientists need, Reid said. The technology can be reused throughout the solar system, including applications such as detecting “dark” ships on Earth trying to sail without registration, or filtering clouds from planetary images.
“We see a huge opportunity to deploy AI at the edge, in space,” Reid said. If all goes according to plan, the lunar demonstration will allow MCSS “to support other companies and organizations as they work to deploy AI in their missions in the future.”
Follow Elizabeth Howell on Twitter @howellspace (opens in a new tab). follow us @Spacedotcom (opens in a new tab)or on Facebook (opens in a new tab) and Instagram (opens in a new tab).