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

2025-03-07

AI Summary

Mobile robots face three core challenges in performing whole-body manipulation tasks within real-world home environments: bimanual coordination, stable navigation, and large-scale end-effector reachability—exacerbated by hardware complexity that hinders vision–motor policy learning. To address these, we propose a whole-body teleoperated robotic system tailored for domestic settings: (1) an integrated dual-arm wheeled platform featuring a 4-DOF actuated torso and a low-cost full-body teleoperation interface; (2) a real-time vision–motor co-control architecture; and (3) an end-to-end whole-body teleoperation policy learning algorithm enabling hardware–policy co-optimization. Evaluated on five challenging household manipulation tasks, our system achieves significantly improved success rates. We open-source the complete system—including hardware schematics, software stack, and data collection framework—to advance embodied intelligence research in realistic deployment scenarios.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

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/

Problem

• Addresses challenges in real-world household robot manipulation.
• Focuses on bimanual coordination, navigation, and end-effector reachability.
• Introduces a framework for learning whole-body visuomotor policies.

Innovation

• Bimanual wheeled robot with 4-DoF torso
• Cost-effective whole-body teleoperation interface
• Novel algorithm for visuomotor policy learning