SONIC: Supersizing motion tracking for natural humanoid whole-body control
Science Robotics · 12.08.2026 · 11 (117)
DOI: 10.1126/scirobotics.aed4592 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Robotics, erschienen am 12.08.2026. Verfasst von Zhengyi Luo und 27 weiteren Autor:innen. Beteiligte Einrichtung: NVIDIA, Santa Clara, CA, USA. Hauptthemen laut MEDLINE: Robotics. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 71 Literaturangaben.
Abstract (Originalsprache)
Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (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 (1.2 to 42 million parameters), dataset volume (more than 100 million frames from 700 hours of motion capture), and compute (21,000 GPU hours). Beyond demonstrating the benefits of scale, we further show downstream utility through a real-time kinematic planner that bridges motion tracking to tasks such as navigation, enabling natural and interactive control, as well as a unified token space that supports virtual reality (VR) teleoperation and vision-language-action (VLA) models with a single policy. Through this interface, we demonstrate autonomous VLA-driven whole-body locomanipulation 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- NVIDIA, Santa Clara, CA, USA.
ORCID-Profile: Zhengyi Luo, Ye Yuan, Tingwu Wang, Chenran Li, Fernando Castañeda, Sirui Chen, Jiefeng Li, Qingwei Ben, Jinhyung Park, David Sami, Lina Song, Edy Lim, Eugene Jeong, Wenli Xiao, Simon Yuen, Yan Chang, Yuke Zhu
Zitieren
APA
Luo, Z., Yuan, Y., Wang, T., Li, C., Castañeda, F., Chen, S., Cao, Z. A., Li, J., Minor, D., Ben, Q., Park, J., Sami, D., Wang, Z., Da, X., Ding, R., Hogg, C., Song, L., Lim, E., Jeong, E., …, & Zhu, Y. (2026). SONIC: Supersizing motion tracking for natural humanoid whole-body control. Science Robotics, 11(117). https://doi.org/10.1126/scirobotics.aed4592
Vancouver
Luo Z, Yuan Y, Wang T, Li C, Castañeda F, Chen S, et al. SONIC: Supersizing motion tracking for natural humanoid whole-body control. Science Robotics. 2026;11(117). doi:10.1126/scirobotics.aed4592
BibTeX
@article{Luo2026,
author = {Luo, Zhengyi and Yuan, Ye and Wang, Tingwu and Li, Chenran and Castañeda, Fernando and Chen, Sirui and Cao, Zi-Ang and Li, Jiefeng and Minor, David and Ben, Qingwei and Park, Jinhyung and Sami, David and Wang, Zi and Da, Xingye and Ding, Runyu and Hogg, Cyrus and Song, Lina and Lim, Edy and Jeong, Eugene and He, Tairan and Xue, Haoru and Xiao, Wenli and Yuen, Simon and Kautz, Jan and Chang, Yan and Iqbal, Umar and Fan, Linxi Jim and Zhu, Yuke},
title = {SONIC: Supersizing motion tracking for natural humanoid whole-body control},
journal = {Science Robotics},
year = {2026},
volume = {11},
number = {117},
doi = {10.1126/scirobotics.aed4592}
}
EUVIMED