Do you play Pokémon Go? You don’t know it, but you’re training an AI to map the world
Maybe you don’t know but if you have played or are still playing Pokémon Go (Have More than half a million active players), you are helping train an AI-powered geospatial model for the purpose of mapping the world.
ONE blog post from NianticThe software developer behind this popular game, explains how it works on “a large geospatial model to achieve spatial intelligence” and tries to build a “live navigation system”. perspective” to understand the world around us — and it uses data from Pokémon Go.
Also: AI transformation is the new digital transformation. Here’s why that change is important
To clarify, Niantic is saying it like data on the web train AI models, AI model it’s a building that needs to understand 3D space. A huge amount of 3D spatial data and imagery is available thanks to Pokémon Go players around the world.
Niantic explains it like this: A local AI mapping model might understand that a church is located in a particular location, but it might only see the front of that location and not be able to interpret love how the rest of the church looks. With data from Pokémon Go players, who may have walked around many churches and pedestrian areas inaccessible to cars (and photographed those areas), AI now has can accurately predict the general shape of a church.
Also: Traveling for the holidays? Google Maps discovers ‘hidden gems’ to add to your route now
The company also pointed out that it recently launched a new feature for the game called Pokémon Playground, which allows you to place a creature in a certain location in the real world for others to see. This means booking the character and watching it later convenient involves using your camera, taking pictures from multiple angles, and sending the resulting images to Niantic.
According to Niantic, they currently have 10 million scanned locations around the world, of which 1 million are activated and ready to use in their VPS service. They added that they receive about 1 million new scans every week, each containing hundreds of images.
Niantic says it will use this data for purposes such as AR glasses, robotics, content creation, and automated systems. So not only does the company make money from selling in-game items to players, but it also makes money from the maps that players have helped create.