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

Nvidia's GR00T 2 model learns robot tasks by transferring human hand movements from video to robotic arms, trained on roughly 400,000 hours of footage, according to The Decoder. Success rates range from 10 to 80 percent depending on the task, so the approach still varies widely in reliability. The model aims to replace laborious teleoperation as a way to teach robots new skills.

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 https://the-decoder.com/nvidias-model-gr00t-2-watches-humans-on-video-then-imagines-itself-as-the-robot/ appeared first on The Decoder https://the-decoder.com .