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

📝 Original Info

• Title: SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
• ArXiv ID: 2511.07820
• Date: 2025-11-11
• Authors: ** 제공된 논문 초록에 저자 정보가 포함되어 있지 않습니다. (저자명 및 소속을 확인하려면 원문을 참고하십시오.) **

📝 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 over several days. We show that scaling up model capacity, data, and compute yields a generalist humanoid controller capable of creating natural and robust whole-body movements. Specifically, we posit motion tracking as a natural and 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 (from 1.2M to 42M parameters), dataset volume (over 100M frames, 700 hours of high-quality motion data), and compute (9k GPU hours). Beyond demonstrating the benefits of scale, we show the practical utility of our model through two mechanisms: (1) a real-time universal kinematic planner that bridges motion tracking to downstream task execution, enabling natural and interactive control, and (2) a unified token space that supports various motion input interfaces, such as VR teleoperation devices, human videos, and vision-language-action (VLA) models, all using the same policy. Scaling motion tracking exhibits favorable properties: performance improves steadily with increased compute and data diversity, and learned representations generalize to unseen motions, establishing motion tracking at scale as a practical foundation for humanoid control.

💡 Deep Analysis

📄 Full Content

Reference