aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分47

Nvidia 发布机器人模型 GR00T 2

AI 导读

GR00T 2 面向机械臂、机器人手和人形机器人。材料称,模型预训练使用了 402,730 小时人类头戴摄像头视频、10,184 小时手持夹爪演示,以及 23,500 小时遥控机器人数据,尝试利用缺少电机指令的普通人类视频。

原帖引用 · 原文

@rohanpaul_ai

https://t.co/WSiF7EY4JN

回复Rohan Paul@rohanpaul_ai
Nvidia released GR00T 2, an open world-action model that runs arms, robot hands and humanoids. Robots normally learn from recordings that pair each camera frame with exact motor commands, and those only come from a person steering a real robot. Ordinary human video is far cheaper and more plentiful, but it has no motor commands, so earlier models could barely use it. GR00T 2 eases that by pretraining on 402,730 hours of human head-camera video plus 10,184 hours of handheld-gripper demos, but only 23,500 teleoperated robot hours.
在 X 查看这条帖子 ↗

来源:Rohan Paul · x.com

模型
发现内容有误?提交纠错