← 回總覽

宝可梦 GO 玩家在不知不觉中训练了配送机器人

📅 2026-03-21 00:15 Rowan Cheung 人工智能 4 分鐘 3955 字 評分: 82
Niantic 宝可梦GO 配送机器人 视觉定位 Coco Robotics
📌 一句话摘要 宝可梦 GO 玩家在全球拍摄了 300 亿张图片,如今 Niantic 正利用这些数据为配送机器人提供视觉定位系统。 📝 详细摘要 这条推文揭示了宝可梦 GO 玩家多年来收集的数据如今如何被重新用于 AI 机器人技术。Niantic 剥离出了 Niantic Spatial,将这 300 亿张位置照片转化为在密集城市场景中优于 GPS 的视觉定位系统。该系统解决了 GPS 在城市中的局限性——信号在摩天大楼间反弹,导致高达 50 米的误差——这对于需要精确位置的配送机器人来说是个致命问题。coco Robotics 是首个商业合作伙伴,使用这项技术在洛杉矶、芝加哥和迈阿密引
Skip to main content ![Image 1: LogoBestBlogs](https://www.bestblogs.dev/ "BestBlogs.dev")Toggle navigation menu Toggle navigation menuArticlesPodcastsVideosTweetsSourcesNewsletters

⌘K

Change language Switch ThemeSign In

Narrow Mode

Pokémon Go Players Unknowingly Trained Delivery Robots

Pokémon Go Players Unknowingly Trained Delivery Robots

![Image 2: Rowan Cheung](https://www.bestblogs.dev/en/tweets?sourceId=SOURCE_827f00) ### Rowan Cheung

@rowancheung

Every Pokémon Go player unknowingly trained future robots.

Over the years, players photographed 30 billion images from cities around the world.

And now that data is teaching delivery robots to navigate streets.

Niantic (company behind Pokémon Go), spun out an AI company called Niantic Spatial that's turning years of player data into a visual positioning system for machines.

When 500 million people installed the game and pointed their phones at buildings, landmarks, and street corners, they were also capturing detailed location data that normal GPS can't match:

> GPS signals bounce off skyscrapers and lose accuracy by up to 50 meters in dense cities.

> That's a dealbreaker for sidewalk delivery robots that need to stop at exactly the right point.

> Niantic Spatial trained a model on those 30 billion images to pinpoint a robot's exact location based on what its cameras see, not satellite signals.

> Delivery startup Coco Robotics is the first partner, using the system to guide thousands of robots across LA, Chicago, and Miami.

Don't think anyone thought they were training robots when they were chasing Pikachu during COVID.Show More

!Image 3: 视频缩略图

01:17

Mar 20, 2026, 4:15 PM View on X

19 Replies

17 Retweets

78 Likes

16.4K Views ![Image 4: Rowan Cheung](https://www.bestblogs.dev/en/tweets?sourceid=827f00) Rowan Cheung @rowancheung

One Sentence Summary

Pokémon Go players photographed 30 billion images worldwide, and Niantic is now using that data to power visual positioning systems for delivery robots.

Summary

This tweet reveals how data collected by Pokémon Go players over the years is now being repurposed for AI robotics. Niantic spun out Niantic Spatial to transform the 30 billion location photos into a visual positioning system that outperforms GPS in dense urban areas. The system addresses GPS limitations in cities where signals bounce off skyscrapers, causing up to 50 meters of inaccuracy - problematic for delivery robots needing precise locations. Coco Robotics is the first commercial partner, using this technology to guide thousands of delivery robots across Los Angeles, Chicago, and Miami.

AI Score

82

Influence Score 31

Published At Today

Language

English

Tags

Niantic

Pokémon Go

Delivery Robots

Visual Positioning

Coco Robotics HomeArticlesPodcastsVideosTweets

Pokémon Go Players Unknowingly Trained Delivery Robots | ...

查看原文 → 發佈: 2026-03-21 00:15:20 收錄: 2026-03-21 04:00:53

🤖 問 AI

針對這篇文章提問,AI 會根據文章內容回答。按 Ctrl+Enter 送出。