BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities

Yunfan Jiang, Ruohan Zhang, Josiah Wong, Chen Wang, Yanjie Ze, Hang Yin, Cem Gokmen, Shuran Song, Jiajun Wu, Li Fei-Fei

Workshop Statement:

Our work on the BEHAVIOR Robot Suite (BRS) advances human-centered robot learning by enabling whole-body visuomotor policy training for complex household tasks. BRS integrates a cost-effective teleoperation interface for collecting rich, human-guided demonstrations—addressing the critical challenge of acquiring grounded, high-quality data for embodied AI.

By focusing on bimanual mobile manipulation in realistic home settings, BRS supports the development of robust, generalizable policies aligned with human expectations. This aligns closely with the workshop’s goals around data accessibility, safe deployment, and the use of large models to enhance human-robot collaboration in everyday environments.

Keywords: Mobile Manipulation, Whole-Body Manipulation, Household Tasks, Robot Learning

TL;DR: BRS is a comprehensive framework for learning whole-body manipulation in real-world household tasks, combining novel hardware design with an advanced policy learning method.

Abstract:

Real-world household tasks present significant challenges for mobile manipulation robots. An analysis of existing robotics benchmarks reveals that successful task performance hinges on three key whole-body control capabilities: bimanual coordination, stable and precise navigation, and extensive end-effector reachability. Achieving these capabilities requires careful hardware design, but the resulting system complexity further complicates visuomotor policy learning. To address these challenges, we introduce the BEHAVIOR Robot Suite (BRS), a comprehensive framework for whole-body manipulation in diverse household tasks. Built on a bimanual, wheeled robot
with a 4-DoF torso, BRS integrates a cost-effective whole-body teleoperation interface for data collection and a novel algorithm for learning whole-body visuomotor policies. We evaluate BRS on five challenging household tasks that not only emphasize the three core capabilities but also introduce additional complexities, such as long-range navigation, interaction with articulated and deformable objects, and manipulation in confined spaces. We believe that BRS’s integrated robotic embodiment, data collection interface, and learning framework mark a significant step toward enabling real-world whole-body manipulation for everyday household tasks. BRS is open-sourced at https://behavior-robot-suite.github.io/

Submission Number: 7