Embodied AI Breakthrough: SONIC System for Robot Motion Tracking Published in Science Robotics
zhengyiluo · x · 2026-08-13
The embodied AI research project SONIC has been published in Science Robotics. It formulates super-scaling motion tracking as the foundational task for achieving more natural and robust whole-body control in robots.
The learned tracker and latent space support the training of foundation models like VLA/WAM. The authors also announced that new model checkpoints will be released today.
More from Embodied
- VLA-Δ: Zhejiang University Adds Physical State Transition Supervision to VLA Models — OmniAI-ZJU · 2026-10-16
- PINT: Shared Predictive Intent Tokens Unify Reasoning, World Modeling, and Robot Actions — Xinyu Guo · 2026-10-16
- TouchScale releases 500 hours of unified egocentric vision-tactile data for scaling study — jiqizhixin · 2026-10-16
- Ghost raises $11M for Core, a personal AI computer that runs locally in your home — nick_linck · 2026-10-16
- Robot shows up at Costco to fetch the famous $1.50 hotdog — majidmanzarpour · 2026-10-16
- 15 Leju Kuavo humanoid robots run 2 months at Hangzhou auto-parts line, 98% success rate — CyberRobooo · 2026-10-16