https://www.popsci.com/technology/pokemon-go-delivery-robots-crowdsourcing/ [ ] Popular Science Logo Popular Science Logo [ ] Search for: [ ] * [ ]Science + Archaeology + Ask Us Anything + Biology + Dinosaurs + Physics + Popular Science Videos + Space + The Weirdest Thing I Learned This Week * [ ]Technology + AI + Aviation + Engineering + Internet + Military + Photography + Robots + Security + Best of What's New + Vehicles * [ ]Environment + Agriculture + Animals + Climate Change + Conservation + Energy + Sustainability + Weather * [ ]DIY + Life Skills + Projects + Tech Hacks * [ ]Gear + Audio + Cameras + Computers + Fitness Gear + Gaming + Gift Guides + Home + Home Theater + Outdoor Gear + Phones + Tablets + Wearables * [ ]MERCH + Cover Art + Store * Newsletter [ ] Search for: [ ] * * * * Technology Robots 'Pokemon Go' players unknowingly trained delivery robots with 30 billion images The massive crowdsourcing effort could use real-world to help robots deliver pizza. By Mack DeGeurin Published Mar 13, 2026 3:00 PM EDT A woman holds up her cell phone as she plays the Pokemon Go game in Lafayette Park in front of the White House in Washington, DC on July 12, 2016. A woman holds up her cell phone as she plays the Pokemon Go game in Lafayette Park in front of the White House in Washington, DC on July 12, 2016. Jim Watson/AFP via Getty Images Get the Popular Science daily newsletter Breakthroughs, discoveries, and DIY tips sent six days a week. Email address [ ] Sign up Thank you! Terms of Service and Privacy Policy. Nearly a decade ago, Pokemon Go turned the real world into a digital scavenger hunt, with virtual creatures hiding in plain sight. The early augmented reality smartphone app prompted hundreds of millions of players to wander into parks, parking lots, and even dimly lit alleyways, peering through their phone cameras in search of Pikachus and Charizards that the app superimposed onto their surroundings. It was a major hit. But 10 years on from the app's peak, it turns out that digital creature catching may now help that piping hot pizza you ordered find you. This week, Niantic Spatial, part of the team behind Pokemon Go, announced a partnership with Coco Robotics, a company that makes short-distance delivery robots for food and groceries. Soon, those robot couriers will scoot around sidewalks using Niantic's Visual Positioning System (VPS)--a navigation tool that can reportedly pinpoint location down to a few centimeters just by looking at nearby buildings and landmarks. Niantic trained that VPS model on more than 30 billion images captured by Pokemon Go users, and claims it will help robots operate in areas where GPS falls short. In other words, all that time users spent wandering around playing Pokemon Go will now help determine how well a courier robot can deliver your take out. It's a stark example of how crowdsourced data, seemingly collected for one purpose, can be quietly repurposed years later for something quite different. "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," Niantic Spatial CEO John Hanke said in a recent interview with MIT Technology Review. How Niantic repackages Pokemon Go data Instead of helping users navigate the way that GPS does, VPS determines where someone is based on their surroundings. That makes Pokemon Go particularly useful as a data source, because players had to physically travel to specific locations and point their phones at various angles. That mapping effort got a significant boost in 2020, when the app added what it called "Field Research," a feature prompting players to scan real-world statues and landmarks with their cameras in exchange for in-game rewards. A portion of the data also reportedly came from areas known as "Pokemon battle arenas." Whether players knew it or not, those scans were creating 3D models of the real world that would eventually power the Niantic model. More data means better accuracy, and because Niantic was collecting images of the same locations from many different users, it could capture the same spots across varying weather conditions, lighting, angles, and heights. There's no shortage of raw material to draw from either. At its peak in 2016, Pokemon Go had around 230 million monthly active players. Though less culturally relevant in 2026, the game still hovers around 50 million active users by some estimates. Related Stories Everything That's Been Blamed On Pokemon Go So Far Chess or video games--which actually makes you smarter? The answer may surprise you. If Pokemon existed in the wild, how would they compare to real animals? Robots in China are riding the subway to make 7-Eleven deliveries How Pokemon Go data could help robots find their way Niantic and Coco are betting that Pokemon Go data will help delivery robots understand precisely where they are simply by looking at landmarks around them. Though most autonomous robots currently use some form of GPS for navigation, it isn't always reliable. Other delivery robots tested on college campuses have been known to get lost or struggle to cross streets. That confusion can lead to delays. As any diner who has waited too long for a hot meal from a delivery app can attest, it's crucial these couriers arrive on time. After all, time is money. "The promise of last-mile robotics is immense, but the reality of navigating chaotic city streets is one of the hardest engineering challenges," Hanke said in a statement. And while most people associate spotty GPS with state parks or remote rural areas, reliability is also often compromised in the tall, densely packed buildings of a concrete jungle. All of those structures can interfere with signals, causing the location dot on a map to drift. The idea is that Coco's robots can use VPS and four cameras mounted around the machine to get a far more precise read on their surroundings. In turn, the well-equipped robot will deliver food on time. an illustration of a square delivery robot using cameras to scan on a city streetVPS uses four cameras to get a more precise reading of its surroundings. Image: Coco Robotics. This also wouldn't be the first time data freely scavenged by internet users for one purpose ended up powering something else entirely. Most famously, Google's CAPTCHA tests, which ask users to click on images of bicycles or traffic lights to verify they are human, have come under scrutiny. Computer scientists have long speculated that the CAPTCHA tests have been used to help train AI vision models. More recently, law enforcement has allegedly accessed or purchased user-generated content from the consumer mapping tool Waze to assist police investigations. And while Niantic hasn't suggested any plans to provide its VPS data to authorities, it's not hard to see how a tool that can accurately pinpoint a location based on landmarks in a photograph could look enticing to law enforcement. On a broader level, Niantic says its partnership with Coco Robotics is part of a longer-term effort to build a "living map" of the world that updates as new data becomes available. Once VPS-equipped delivery robots hit the streets, they will collect even more info that can be fed back into the model to bolster its accuracy further. This kind of continuous, real-world data collection is already central to how self-driving vehicle companies like Waymo and Tesla operate, and is a large part of why that technology has improved so significantly in recent years. So, next time you see someone in a park trying to "catch 'em all," it's quite possible the data gleaned from that scavenger hunt could play a key role in determining whether the pizzas of the future make it to their destinations on time. products on a page that says best of what's new 2025 2025 PopSci Best of What's New The 50 most important innovations of the year See it Mack DeGeurin Avatar Mack DeGeurin Contributor Mack DeGeurin is a tech reporter who's spent years investigating where technology and politics collide. His work has previously appeared in Gizmodo, Insider, New York Magazine, and Vice. --------------------------------------------------------------------- Trending A conceptual photograph of a young woman with light-colored hair and a tattoo on her forearm, wearing a white t-shirt against a plain white background. The image uses a multiple-exposure effect to create several overlapping, translucent silhouettes of her figure, conveying a sense of disorientation, dizziness, or blurred vision. She has a pained or nauseated facial expression and is resting her head against her hand. Evolution Why some people get motion sickness--and others don't By Laura Kiniry a bird chick sits on a nest Birds The world's oldest wild bird has a new grandchick By Margherita Bassi [Screenshot] Demystifying our weird world every day Sign up for the Popular Science newsletter, delivered to your inbox six days a week. Sign up By signing up you agree to our Terms of Service and Privacy Policy. More in Robots a robot moving along the corridors of a hotel Robot-run hotels are here, but guests have mixed reviews By Charlotte Hu a white driverless car drives in front of a large state capitol building Radio waves could help driverless cars see around corners By Mack DeGeurin A portrait of two brothers, Nico and Matteo Mucchetti, posing with their homemade, full-sized replica of a purple ride vehicle from Disney's "Big Hero 6" attraction. The younger brother sits inside the purple wooden structure, which is detailed with orange accents and a string of LED lights along the edge, while the older brother leans over the back. They are positioned in a dimly lit room, creating a dramatic spotlight effect on them and their project. Teen brothers build a Disney-inspired ride in family basement By Laura Kiniry robot working on rubik's cube Brothers build a robot to solve Rubik's cubes in record-setting time By Mack DeGeurin man standing under drone umbrella in the rain We may not have flying cars, but we have flying umbrellas By Eric Alt a stingray swimming in clear blue water Stingray-inspired robot cracks the mystery of how rays swim By Mack DeGeurin a black robot shaped like a human hand This robot hand can detach from its arm and crawl around By Mack DeGeurin a bat flying through the night A robot bat sheds new light on how they hunt in darkness By Mack DeGeurin SEE MORE More in Technology products on a page that says best of what's new 2025 The 50 greatest innovations of 2025 By Popular Science Team a variety of products on a banner reading 'best of what's new 2024' The 50 greatest innovations of 2024 By Popular Science Team The 100 greatest innovations of 2022 The 100 greatest innovations of 2022 By Popular Science Team The 100 greatest innovations of 2021 The 100 greatest innovations of 2021 By Popular Science Team This self-driving grocery delivery car will sacrifice itself to save pedestrians This self-driving grocery delivery car will sacrifice itself to save pedestrians By Rob Verger 100 greatest innovations of 2019: Best of What's New The 100 greatest innovations of 2019 By Popular Science Team a dog on a phone How the Ring Search Party feature works (and how to turn it off, if it's too creepy) By David Nield Silicon Landscapes is a collage of circuit boards interwoven with aerial photographs of water treatment facilities, agricultural lands, industrial sites and mining machinery. It represents the resource-intensive material realities of AI systems transforming the natural landscapes through extractivist processes. The Internet Archive records its 1 trillionth website By Andrew Paul SEE MORE [popsci_logo-horizontal-white] Get the Popular Science daily newsletter Breakthroughs, discoveries, and DIY tips sent six days a week. Thank you! Email address [ ] Sign up Terms of Service and Privacy Policy. * Editorial Standards * How We Test and Review Products * About Us * Contact Us * TV Channel * Privacy Policy * Terms & Conditions * Affiliate Disclosure * Sitemap * Deposit Photos FOLLOW US * * * * DISCLAIMER(S) Articles may contain affiliate links which enable us to share in the revenue of any purchases made.Registration on or use of this site constitutes acceptance of our Terms of Service. (c) 2026 Recurrent. All rights reserved. Do Not Sell or Share My Personal Information. * Science * Technology * Environment * DIY * Gear * Merch * SHOP