Niantic is constructing a ‘geospatial’ AI mannequin primarily based on Pokémon Go participant information

Niantic has introduced that it’s constructing a brand new “Massive Geospatial Mannequin” (LGM) that mixes thousands and thousands of scans taken from the smartphones of gamers of Pokémon Go and different Niantic merchandise. This AI mannequin may enable computer systems and robots to grasp and work together with the world in new methods, the corporate stated in a weblog submit noticed by Rubbish Day.

The LGM’s “spatial intelligence” is constructed on the neural networks developed as a part of Niantic’s Visible Positioning System. The weblog submit explains that “Over the previous 5 years, Niantic has centered on constructing our Visible Positioning System (VPS), which makes use of a single picture from a cellphone to find out its place and orientation utilizing a 3D map constructed from folks scanning attention-grabbing places in our video games and Scaniverse,” and “This information is exclusive as a result of it’s taken from a pedestrian perspective and contains locations inaccessible to automobiles.”

Niantic Chief Scientist Victor Prisacariu was extra express in a 2022 Q&A, saying, “Utilizing the info our customers add when enjoying video games like Ingress and Pokémon Go, we constructed high-fidelity 3D maps of the world, which embrace each 3D geometry (or the form of issues) and semantic understanding (what stuff within the map is, reminiscent of the bottom, sky, timber, and so on).”

As 404 Media factors out, no person who downloaded Pokémon Go in 2016 may have predicted their information would “sooner or later gasoline one of these AI product.”