Niantic has announced that it’s development a pristine “Large Geospatial Model” (LGM) that mixes hundreds of thousands of scans taken from the smartphones of avid gamers of Pokémon Progress and alternative Niantic merchandise. This AI type may just permit computer systems and robots to grasp and have interaction with the arena in pristine techniques, the corporate stated in a weblog submit spotted by Garbage Day.
The LGM’s “spatial intelligence” is constructed at the neural networks evolved as a part of Niantic’s Sight Positioning Machine. The weblog submit explains that “Over the past five years, Niantic has focused on building our Visual Positioning System (VPS), which uses a single image from a phone to determine its position and orientation using a 3D map built from people scanning interesting locations in our games and Scaniverse,” and “This data is unique because it is taken from a pedestrian perspective and includes places inaccessible to cars.”
Niantic Important Scientist Victor Prisacariu was once extra specific in a 2022 Q&A, pronouncing, “Using the data our users upload when playing games like Ingress and Pokémon Go, we built high-fidelity 3D maps of the world, which include both 3D geometry (or the shape of things) and semantic understanding (what stuff in the map is, such as the ground, sky, trees, etc).”
As 404 Media issues out, no person who downloaded Pokémon Progress in 2016 will have predicted their knowledge would “one day fuel this type of AI product.”
