AI 新闻 · The Decoder
Nvidia 的模型 GR00T 2 在视频中观看人类,然后将自己想象成机器人
发布于 · 本站收录 2026-11-11 03:01
Nvidia 的新 AI 模型 GR00T 2 旨在教机器人执行新任务,而无需费力的远程操作。相反,该系统将人类手部动作从视频传输到机械臂,并接受约 400,000 小时的视频片段训练。不过,成功率仍然相差很大,从 10% 到 80% 不等
英文原文标题与摘要
Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot
Nvidia's new AI model GR00T 2 is designed to teach robots new tasks without laborious teleoperation. Instead, the system transfers human hand movements from videos to robotic arms, trained on about 400,000 hours of video footage. Success rates still vary widely, though, ranging from 10 to 80 percent depending on the task.
本站程序每小时从公开 RSS / 官方博客自动收集,英文内容为机器翻译摘要,已自动过滤低俗、时政等敏感内容;细节以原文为准。