YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale

2026-06-08

AI Summary

This work addresses the poor ergonomics and low trajectory fidelity of conventional handheld teleoperation devices in bimanual dexterous manipulation. The authors propose YUBI, a compliant two-finger interface that leverages a soft finger actuation mechanism to achieve high-fidelity mapping of human hand motions onto a gripper, integrated with VR for six-degree-of-freedom trajectory capture. The study introduces a novel, finger-aligned universal gripper design paradigm, enabling plug-and-play policy transfer across multiple robotic platforms—including UR, Franka, and ELEY. A large-scale bimanual manipulation dataset is released, comprising 119 tasks, 1.2 million trajectories (8,434 hours), with full open-source availability of hardware, software, and data, significantly enhancing robotic dexterity and generalization capabilities.

Abstract

We introduce Yielding Universal Bidigital Interface (YUBI), a finger-aligned gripper designed to enable intuitive, ergonomic, and scalable data collection for bimanual dexterous manipulation. While handheld data collection systems such as Universal Manipulation Interface (UMI) enable affordable data collection, their bulky pistol-grip designs can pose ergonomic and usability challenges for fine-grained, dexterous manipulation tasks. To address this, YUBI presents a distinct design principle: yielding, finger-driven actuation that directly maps human finger movements to gripper jaw motion. Using the YUBI devices, we set up a data collection system with integrated VR-based 6 DoF tracking of the gripper, ensuring high-fidelity trajectory data acquisition. We curate a UMI-based dataset of unprecedented scale: 8,434 hours across 1.20M episodes and 119 tasks. Experiments show that YUBI offers advantages over the UMI gripper in versatility for complex bimanual tasks, dexterity, and operational efficiency. A single policy trained on the YUBI dataset transfers across multiple bimanual robots (UR, Franka, and ELEY) simply by mounting the gripper on each platform, confirming that the collected data are directly executable as policy supervision. We release the gripper hardware, data-collection software, and dataset as one integrated stack, offering the open community a reproducible path to large-scale data acquisition for advancing robotic foundation models.

Problem

• bimanual dexterous manipulation
• data collection
• ergonomic interface
• scalable robotics
• gripper design

Innovation

• YUBI
• bimanual dexterous manipulation
• finger-driven actuation
• scalable data collection
• policy transfer