Nvidia Releases GR00T 2 World-Action Model Trained on 400K Hours of Human Video
Nvidia has released GR00T 2, an open world-action model that drives robotic arms, dexterous hands and humanoids. Its key advance is pretraining on 402,730 hours of human head-camera video plus 10,184 hours of handheld-gripper demos, requiring only 23,500 hours of teleoperated robot data and sharply reducing reliance on costly real-robot demonstrations.
Full Report
Rohan Paul (@rohanpaul_ai) · 2026-11-10 22
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.


