cs.RONov 17, 2026

HandUMI: A Modular Hand-Worn Parallel-Jaw Interface for Robot-Free Bimanual Data Capture

Authors: Brik Meza, Leonardo Perez, Alvaro Mendoza-Li, Aniela Ubillus, Mitshell Ramos, Raul Bastidas, Mauricio Olivera, Bryan Bastidas

Organizations: Mu Robotics · McGill University · Mila - Quebec AI Institute · Pontificia Universidad Católica del Perú (PUCP) · 

Abstract

HandUMI captures robot-free bimanual demonstrations with a hand-worn parallel-jaw interface. Swappable fingertips match the robot's installed gripper; Quest/PICO controllers track hands and encoders measure aperture. Robot-agnostic recordings are retargeted by inverse kinematics to seven simulated bimanual arms (median position error ≤1.2\leq 1.2 mm; ≤4.7\leq 4.7% of episodes rejected). On bimanual towel folding, 562 robot-free demonstrations train policies on real PiPER arms: ACT succeeds in 12/20 attempts and fine-tuned π0.5π_{0.5} in 7/20; ACT on the first 101 and base π0.5π_{0.5} each succeed in 0/20. Hardware and software are open source (Apache-2.0), and a pair costs USD 557 with Quest 3S, excluding the optional ZED Mini and host computer. Project website: https://murobotics.ai/research/handumi.

Figures & tables

Explore similar work

CardsList
  1. UMI-Live for In-The-Wild Bimanual Robotics Data Collection

    Oct 29, 2026Govind Velamoor, Adrian Lin, Sam Jung +3Robotic Data CollectionRobot Manipulation Datasets