Niantic has announced that it’s building a new “Large Geospatial Model” (LGM) that combines millions of scans taken from the smartphones of players of Pokémon Go and other Niantic products. This AI model could allow computers and robots to understand and interact with the world in new ways. https://image.nostr.build/d55d51ffcb1168ef71658350508ac1f2b72734fa393f81dfca54fc4617c7c959.jpg Photo by Sam Byford / The Verge https://www.theverge.com/2024/11/19/24300975/niantic-pokemon-go-data-large-geospatial-model
The LGM is designed to provide a form of "spatial intelligence," enabling machines to perceive and comprehend physical spaces more effectively. This capability is built upon the neural networks developed through Niantic's existing Visual Positioning System .Global Understanding: By integrating local data from various geographic locations, the LGM will create a shared understanding of these areas, even those that have not been fully scanned yet. This approach allows for a more comprehensive map