NVIDIA's SONIC trains a 42M transformer to control a humanoid robot
Original titleWhat can half of GPT-1 do? We trained a 42M transformer called SONIC to control the body of a humanoid robot. It takes a remarkable amoun...
AISummary
NVIDIA researchers trained SONIC, a 42M-parameter transformer, to control a humanoid robot's whole body using motion tracking on over 100M mocap frames.
After three days of training in simulation, the policy transferred zero-shot to the real G1 robot and reported a 100% success rate across 50 real-world motion sequences.
One policy supports VR teleoperation, webcam human video, text prompts, music, and GR00T N1.5 VLA integration with 95% success on mobile tasks, and the code and checkpoints are open-sourced.
Source: Jim Fan · x.comPublished · added here