NASA is developing Artificial intelligence for a machine to drive on the Moon: it’s called LunaNet, with capabilities similar to the Internet. Alvin Yew, a research engineer from the US aerospace agency is leading the project.
The Americans compare the system with reference points on Earth: the device, trained by NASA, will use the same characteristics with the horizon of our natural satellite.
Yew is an engineer at NASA’s Goddard Space Flight Center in Greenbelt, Maryland, and spoke in a press release about the work.
“For scientific and security geotagging, it is important that explorers know exactly where they are while exploring the lunar landscape. Equipping an onboard device with a local map would support any mission, be it robotic or human,” Yew noted.
The geolocation system created by Yew will take advantage of the capabilities of GIANT, an image navigation and analysis tool from the Goddard center. Artificial Intelligence is helping humans to deep space exploration.
The Artificial Intelligence that will be used by NASA on the Moon
Let’s remember that Artificial Intelligence is the attempt to recreate human intelligence in machines or computers. Thus, these devices can make decisions by themselves.
They are based on machine learning and deep learning: in the first part they are trained by human beings (with images, voices, texts or other elements); in the second, the machines make decisions or issue responses using what they initially learned.
In the case of LunaNet, it is trained on data from NASA’s Lunar Reconnaissance Orbiter, specifically the Lunar Orbiter Laser Altimeter (LOLA). It measures the slopes and roughness of the lunar surface and generates high-resolution topographic maps of the Moon.
With digital panoramas, the device can correlate known rocks and ridges, giving you precise location identification for any given region.
