Nvidia 发布 GR00T 2：从视频学习人类动作来训练机器人
Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot
Nvidia 这次把机器人训练的数据来源换成了 40 万小时人类视频，不用人工遥操作逐个示范了。不过成功率从 10% 到 80% 不等，离稳定可用还有距离。做机器人或具身智能的团队值得对比一下自家数据管线，看看视频学习路线能不能省成本。
Nvidia 发布机器人基础模型 GR00T 2，核心思路是让机器人通过观看约 40 万小时的人类视频来学习新任务，绕开传统遥操作数据采集的高成本流程。模型会将视频中人类手部动作迁移到机械臂上，相当于让模型在想象中“把自己当成机器人”来理解动作如何执行。
从效果看，GR00T 2 目前还不够稳定：任务成功率在 10% 到 80% 之间大幅波动，具体取决于任务类型。这意味着简单任务已可用，复杂操作仍需额外微调或人工介入。
对机器人行业来说，用互联网视频替代人工示教是降低数据成本的关键方向，Nvidia 的 40 万小时视频训练规模在同类机器人基础模型中属于激进尝试。开发者可以关注其在 Isaac 生态中的落地方式，企业用户则需留意不同任务场景下成功率的差异。
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. The article Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot appeared first on The Decoder .
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include GR00T 2, Nvidia, 机器人, 具身智能.
Source attribution: curated from Decoder (@Maximilian Schreiner).
