Back to news

Robots · Article

Nvidia's GR00T 2 Learns Robot Tasks by Watching Human Videos

The Decoder ·

At a glance

Nvidia has unveiled GR00T 2, a new AI model for robots. It transfers human movements from videos to robotic arms, reducing the need for manual remote-control training.

Key points

Why it matters

It could cut the time and cost of teaching robots new jobs, which may help robots reach real-world use faster.

Original source

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

The Decoder · Nov 11, 03:41 KST

Read on The Decoder ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to The Decoder.

Other coverage

Robots