[ad_1]
Key Takeaways
- Niantic is developing a “Large Geospatial Model” (LGM) from data collected by players in its games such as Pokémon Go.
- The model learns from the scan using a Visual Position System (VPS), which can use a single image to determine its location on a 3D map.
- It is unclear how long Niantic has been collecting this location data.
He misses playing Pokémon Go back in the day and all the hype around it? All fun adventures to catch The Pokémon in your neighborhood with friends and family? Niantic certainly does.
Niantic is the developer behind Pokémon Go, and it recently announced that it is creating a new “Large Geospatial Model” (LGM) using millions of scans taken by Pokémon Go players on their smartphones (via IGN). How does LGM read these masks? Well, that’s thanks to Niantic’s new Visual Positioning System (VPS).
“For the past five years, Niantic has focused on developing a Visual Positioning System (VPS), which uses a single image from a phone to determine its location and position using a 3D map created from people scanning places of interest in our games and Scaniverse,” Niantic said in a release. in the media.
Related
The AI is running out of gas
Advances in AI have been moving at what feels like a lightening pace, but there are signs that it is starting to slow down.
How exactly does Niantic’s LMG work?
Lots of data and lots of training
You’ve probably heard of a large-scale linguistic model (LLM) before, such as ChatGPT For example. Its AI model is trained on a large amount of existing text to generate text that sounds good and consistent when the user commands it. LGM works similarly. It’s trained on what real-world places look like, like a church or a park, and can use that data to generate information about places it hasn’t seen before. Niantic says LGM will help computers see and interact with virtual spaces in new ways, and can be used in AR glasses, robots, content creation, and autonomous systems.
So how does Niantic get all this location data? Well, its games, of course. Pokémon Go is still a popular mobile game, and has users walking around and pointing their phones at locations trying to catch Pokémon. Those location scans are being returned to Niantic, though it’s unclear how long it’s been collecting them. The advantage of Niantic’s Pokémon Go is that it gets location data that other services like Google Maps can’t.
To map and create spaces with AI, you need more than just looking at a car on the road. You need the perspective of a pedestrian at street level looking at places and seeing things differently, and that’s exactly what Pokémon Go players inadvertently bring. I haven’t played Pokémon Go in years, but it’s amazing to think that I might be contributing my data to creating an AI product like this. I think the terms of service I didn’t read have more to them.
Related
This app just brought your ’90s Pokémon obsession back to life
The Pokémon Company has launched Pokémon TCG Pocket, which allows players to collect and battle Pokémon cards virtually.
Source link
