Scaling Behavior Foundation Model for Humanoid Robots
- Published
- Source
- arXiv
- Paper number
- 643
- Field
- Robotics
- arXiv ID
- 2607.15163
Key points
- It adopts motion tracking as a unified training paradigm, combining diverse whole-body control problems under reference-motion imitation.
- Experiments show that the synergy between the quantity of on-policy rollouts and the diversity of reference motions is the key to scaling.
- It introduces the Humanoid Transformer, a scalable architecture in which structured action representations emerge naturally.
- Compared with existing humanoid controllers, it reduces MPKPE by 10% locally and 82% globally, and reaches an overall accuracy of 0.9836.
- It is validated in both simulation and on real robots, confirming its practicality.
Paper links
External research summaries. These are not HDATF publications or measured product results.