For years, Pokémon Proceed players unknowingly contributed to a massive dataset that is now being used to guide autonomous delivery robots. The popular augmented reality game, which tasked players with scanning real-world locations, has generated over 30 billion images and scans that Niantic, the company behind the game, has repurposed to power Coco Robotics’ delivery bots.
The unexpected connection highlights the potential of crowdsourced data and the evolving applications of augmented reality technology. What began as a quest to “catch ‘em all” is now helping robots navigate complex urban environments with centimeter-level accuracy, a feat often impossible with traditional GPS systems. This advancement promises more efficient and reliable last-mile delivery services.
Niantic Spatial, an AI company spun out of Niantic, leveraged the data collected from Pokémon Go and its sister game, Ingress, to build a Visual Positioning System (VPS). According to MIT Technology Review, this system creates a detailed world model by recognizing buildings, signs, and street features with high precision. The VPS allows robots to pinpoint their location even in areas where GPS signals are weak or unavailable. “Everybody thought that AR was the future, that AR glasses were coming,” says Brian McClendon, CTO at Niantic Spatial. “And then robots became the audience.”
Coco Robotics, which deploys these robots in cities across the US and Europe, is the first major partner to utilize Niantic Spatial’s technology. The company’s robots, described as flight-case-size and capable of carrying up to eight extra-large pizzas or four cases of beverages, rely on the VPS to navigate sidewalks and deliver goods directly to customers. The technology is particularly valuable in dense urban areas where GPS signals can be blocked by tall buildings.
The sheer scale of the data is remarkable. According to Scopely, which acquired Pokémon Go from Niantic in May 2024, the game still attracted over 100 million players in 2024, eight years after its initial launch. The 30 billion images generated by these players provide a level of detail and accuracy that would be incredibly expensive and time-consuming to collect through traditional mapping methods. Niantic’s CTO, Brian McClendon, noted that 500 million people installed the app within the first 60 days of its release.
John Hanke, CEO of Niantic Spatial, articulated the surprising synergy between the game and the robotics application: “It turns out that getting Pikachu to realistically run around and getting Coco’s robot to safely and accurately move through the world is actually the same problem.” This observation underscores the fundamental challenges of spatial understanding and navigation, regardless of whether the agent is a virtual Pokémon or a physical robot.
The repurposing of Pokémon Go data has sparked amusement within the gaming community, with many players realizing the broader impact of their in-game activities. While players were aware their scans contributed to Niantic’s mapping system, few anticipated it would directly contribute to the development of commercial delivery robots.
The success of this collaboration between Niantic Spatial and Coco Robotics signals a potential shift in how robots interact with the physical world. By leveraging crowdsourced data and advanced computer vision techniques, companies can create more reliable and efficient autonomous systems. The future of delivery, it seems, may have been unknowingly built by Pokémon trainers.
As Niantic Spatial continues to refine its VPS and expand its partnerships, we can expect to see even more innovative applications of this technology. The company’s focus on building a detailed and accurate world model positions it as a key player in the emerging field of spatial AI. What comes next will be the expansion of this technology to other robotic applications and potentially, augmented reality experiences beyond gaming.
What are your thoughts on this unexpected application of Pokémon Go data? Share your comments below and let us understand how you believe this technology will impact the future of delivery!
