# Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot

Source: [The Decoder](https://the-decoder.com/nvidias-model-gr00t-2-watches-humans-on-video-then-imagines-itself-as-the-robot/) · 2026-11-10 · AI
Page: https://themorning.dev/story/nvidia-s-model-gr00t-2-watches-humans-on-video-then-imagines-itself-as-the-robot-5b0782046247728b
Kind: research · Impact: medium

## In brief

- Nvidia's new AI model GR00T 2 is designed to teach robots new tasks without laborious teleoperation.
- It transfers human hand movements from videos to robotic arms and was trained on about 400,000 hours of video footage.
- Success rates still vary widely across tasks.

## Why it matters

If video-based learning works reliably, robot teams could train new manipulation tasks from recorded human demonstrations instead of costly teleoperation sessions. The wide variation in success rates means it is not yet a dependable replacement.

## Versions

- GR00T 2

## Coverage

- [Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot](https://the-decoder.com/nvidias-model-gr00t-2-watches-humans-on-video-then-imagines-itself-as-the-robot/) — The Decoder, 2026-11-10

Tags: robotics, machine-learning, nvidia, imitation-learning, foundation-models

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Dev – https://themorning.dev