Overview#

BEHAVIOR Robot Suite (BRS) is a comprehensive framework for learning whole-body manipulation in diverse household tasks. Rooted in the BEHAVIOR-1K project, BRS builds on a bimanual, wheeled robot with a 4-DoF torso, achieving three essential whole-body control capabilities for successfully performing household tasks: bimanual coordination, stable and accurate navigation, and extensive end-effector reachability. BRS integrates a cost-effective whole-body teleoperation interface for data collection and a novel algorithm for learning whole-body visuomotor policies. Key features include:

  • JoyLo, an open-sourced, cost-effective whole-body teleoperation interface paired with the Galaxea R1 robot;

  • brs_ctrl, a real-time controller for JoyLo and the Galaxea robots with user-friendly Python interfaces;

  • WB-VIMA, a novel and competent learning algorithm that effectively models coordinated whole-body actions.

../../_images/brs_tasks_overview.png

Paper and Citation#

Our paper is available on arXiv. If you find our work useful, please consider citing us!

@article{jiang2025brs,
  title   = {BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities},
  author  = {Yunfan Jiang and Ruohan Zhang and Josiah Wong and Chen Wang and Yanjie Ze and Hang Yin and Cem Gokmen and Shuran Song and Jiajun Wu and Li Fei-Fei},
  year    = {2025},
  journal = {arXiv preprint arXiv: 2503.05652}
}