Pokémon Go’s developer, Niantic, is building an advanced large geospatial model out of the data gathered. This artificial intelligence system specializes in recognizing and mapping 3D spaces worldwide. Niantic recently published a blog post discussing this large-scale project, which will help the company improve space awareness and real-world engagement for AR experiences.
LGM, a Niantic project, aims to map real-world locations with superior accuracy using inputs from millions of Pokémon Go players. This initiative is compared to Large Language Models (LLMs) like ChatGPT, but LGM researches space instead of processing text. When trained on information about landmarks and structures such as parks, churches, and buildings, the model can make likely predictions about unknown terrains.
The company highlights a hypothetical scenario to explain its utility: for instance, if a model only knows the front of a church, it may have challenges mapping its back. Using global data collected by players, the model finds common traits of similar landmarks and can accurately place them even in locations not previously surveyed.
Niantic plans to use this technology beyond gaming in areas such as augmented reality glasses, robotics, and digital content creation. These advancements could pave the way for a very accurate real-life experience.
The Visual Positioning System, or VPS, is an independent technology critical to Niantic's mapping. This system detects location and facing direction with centimeter-level accuracy using images captured by mobile devices. Pokémon Go players help in this regard by constantly capturing images and scanning places, feeding the developers data essential for developing the AI system.
Niantic has collected 10 million locations and included one million of these in its VPS. The organization processes one million new scans every seven days, containing hundreds of images each. With such a large amount of data, the model can refine the perception of real 3D spaces and ensure accurate mapping.
The Pokémon Playground feature within Pokémon Go illustrates this technology well. Players can also place Pokémon at certain places, and other people can engage with the Pokémon. These interactions demand that images be captured from different angles, which also enhances the data set for Niantic’s VPS.
Niantic is actively using such solutions, highlighting that the application of these technologies is not limited to gaming alone. LGM can support AR-based navigation, robotic systems, and enhanced content creation tools.
However, the extracted player data has been seen to cause issues regarding privacy and the ethical usage of people’s data in constructing AI for commercial purposes. Niantic has not explained these issues comprehensively, but the company states that it is more focused on developing solutions within the AR market.