Nvidia’s SONIC Teaches Humanoids to Move

Humanoid robots can now be taught to walk, run, crawl, dance and manipulate objects using a single Nvidia foundation model.

Nvidia’s SONIC (supersizing motion tracking for natural humanoid control) is designed to give humanoid robots whole-body control, enabling them to coordinate their joints, maintain balance and adapt movements in real time.

The open source lightweight foundation model is now publicly available, with Nvidia releasing a checkpoint in July for applications including teleoperation and vision-language-action (VLA) driven control. The research behind SONIC was also published this month in Science Robotics, as part of Nvidia’s push to bring it to more engineers.

While language and vision models have rapidly expanded to incorporate billions of parameters trained on countless datasets, those used to control humanoid movement have remained relatively small, with a handful of GPUs tuned to a limited set of behaviors. Adding a new skill or movement to a robot’s repertoire has typically required building an entirely new controller.

SONIC is designed to change that, using more than 100 million motion-capture frames (representing around 700 hours of human movement), to create a single robot training model.

How it Works

“Whole body control requires every joint to coordinate while maintaining balance, handling contacts and adapting to changing motion goals in real time,” Yuke Zhu, director and distinguished research scientist at Nvidia, told AI Business.

SONIC has been demonstrated across three dimensions: model size, training data and compute, with training models ranging from 1.2 million to 42 million parameters. The result is a controller that can track a range of movements while also adapting to those it has not encountered during training.

For Zhu, that represents a change in how humanoid robots can be programmed.

That flexibility could become increasingly important as humanoid robots move from controlled demonstrations toward real-world, unpredictable environments.