SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

TL;DR

This paper introduces SONIC, a large-scale motion tracking foundation model that enables natural, robust humanoid whole-body control by leveraging extensive motion-capture data, scaling model size, and compute resources.

Contribution

The paper demonstrates that scaling model capacity, data, and compute creates a generalist humanoid controller capable of diverse, natural movements and downstream tasks.

Findings

Scaling improves motion tracking performance steadily.

Learned policies generalize to unseen motions.

Real-time planning enables interactive humanoid control.

Abstract

Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs. We show that scaling model capacity, data, and compute yields a generalist humanoid controller capable of natural, robust whole-body movements. We position motion tracking as a scalable task for humanoid control, leveraging dense supervision from diverse motion-capture data to acquire human motion priors without manual reward engineering. We build a foundation model for motion tracking by scaling along three axes: network size (1.2M to 42M parameters), dataset volume (100M+ frames from 700 hours of motion capture), and compute (21k GPU hours). Beyond demonstrating the benefits of scale, we further show downstream utility through: (1) a real-time kinematic planner bridging motion tracking to tasks such as navigation, enabling natural and interactive control, and (2) a unified token space supporting VR teleoperation and vision-language-action (VLA) models with a single policy. Through this interface, we demonstrate autonomous VLA-driven whole-body loco-manipulation requiring coordinated hand and foot placement. Scaling motion tracking exhibits favorable properties: performance improves steadily with compute and data diversity, and learned policies generalize to unseen motions, establishing motion tracking at scale as a practical foundation for humanoid control.