Nvidia's GR00T 2 pretrained on 402k hours of human video with only 23.5k robot hours
rohanpaul_ai · x · 2026-11-11
Nvidia released GR00T 2, an open world-action model that controls robot arms, hands, and humanoids.
The key advance is data efficiency: conventional robots learn from recordings pairing each camera frame with exact motor commands, which only come from a person steering a real robot. Ordinary human video is far cheaper and more plentiful but lacks motor commands, so earlier models could barely use it.
GR00T 2's pretraining recipe:
- 402,730 hours of human head-camera video
- 10,184 hours of handheld-gripper demos
- Only 23,500 hours of teleoperated robot data
Related event: NVIDIA Open-Sources GR00T 2, a World-Action Model for Robots(20 posts)→
More from Embodied
- Wired tries the OpenAI-powered Microduck, a tiny robot duck that chases cats — Wired AI · 2026-11-12
- RoboCap-10k released: 10,000 hours of open egocentric robot data with metric actions — databoydg · 2026-11-12
- Claude Fable 5.2 Solves Rubik's Cube on Trossen WidowX Robot Arms in Anthropic Launch Demo — kscottz · 2026-11-12
- Scoble: AI glasses will get smaller and cheaper, and China's market appetite dwarfs the US — Scobleizer · 2026-11-12
- Blackmagic launches 108-mic 7th-order ambisonic microphone priced at $1,909 — Scobleizer · 2026-11-12
- NVIDIA unveils GR00T 2 humanoid open world action model, benchmarked on AI2's MolmoSpaces — Kyle_L_Wiggers · 2026-11-12