行业动态
x.com ·
@a16z (@a16z)
World Labs联合创始人：五张照片即可教会机器人适应新环境
World Labs联合创始人Justin Johnson介绍，通过手机拍摄几张照片，利用Atlas重建空间并生成仿真，可快速训练机器人适应新环境。他提到两种技术路径：完全上下文学习和真实到仿真再到真实。
AI推荐理由 World Labs联合创始人介绍Atlas，通过手机照片快速生成仿真环境以训练机器人，概念新颖，但处于早期阶段，实际效果未验证。
75
浏览 30,367
点赞 120
评论 12
转发 15
正文
World Labs联合创始人Justin Johnson谈如何用手机里的五张照片教会机器人在一个从未见过的房间里工作：“我认为人们正在研究几种不同的技术路线。一种是完全上下文学习的概念。也许我有一个机器人基础模型，然后我可以向机器人演示一次任务应该如何执行，这就足以让机器人弄清楚那个任务。”
“另一种版本是我们所说的‘真实到模拟再到真实’。也许我有预训练的机器人基础模型，但我想让它适应这个特定的环境。”
“比如这个工作室……你可以走进来，用手机拍几段随意的视频或几张图片，使用Atlas重建空间，然后在这个工作室空间中特别地布置各种机器人交互。”
“实际上你可以在五分钟内完成。拍五张照片，上传到Atlas，让它生成一个模拟，用自然语言描述你希望机器人执行的任务，让一个代理为你构建那个模拟，对通用机器人基础模型进行强化学习微调，然后你就得到了一个机器人……它完美地适应了这个空间。”
@jcjohnss在@MTSlive上
您的浏览器不支持视频标签。🔗在Twitter上查看
World Labs@theworldlabs
介绍Atlas：世界上第一个多模态世界模型，能够生成具有像素级完美相机控制的图像和视频帧，并在3D中重建它们。对世界建模，移动相机，模拟空间与时间。
您的浏览器不支持视频标签。🔗在Twitter上查看
🔗查看引用推文
💬14🔄23❤️156👀35832📊27
⚡由xgo.ing提供支持
查看原文（中文正文为 AI 翻译）
World Labs co-founder Justin Johnson on how five photos from your phone could teach a robot to work in a room it has never seen: "I think there's a couple different tech trees that people are working on. One is this notion of fully in-context learning. Maybe I've got a robotics foundation model, then I can demonstrate to the robot once how a task should be performed, and that's enough for the robot to figure out that task." "Another version is what we're calling real-to-sim-to-real. Maybe I've got my pre-trained robotics foundation model, but I want to adapt it to this particular environment." "Like this studio... You could come in here and take just a couple casual videos with your phone or a couple images with your phone, use Atlas to reconstruct the space, and now stage all kinds of robotics interactions in this studio space in particular." "Literally you could do it in five minutes. Take five photos, upload it to Atlas, have it generate a simulation, describe in natural language what kind of task you want the robot to do, have an agent go build that simulation for you, RL fine-tune your general purpose robotics foundation model, and now you've got a robot... that's perfectly adapted to this space." @jcjohnss on @MTSlive Your browser does not support the video tag. 🔗 View on Twitter World Labs@theworldlabs Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬14🔄23❤️156👀35832📊27 ⚡ Powered by xgo.ing