DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fang, Hao-Shu, Romero, Branden, Xie, Yichen, Hu, Arthur, Huang, Bo-Ruei, Alvarez, Juan, Kim, Matthew, Margolis, Gabriel, Anbarasu, Kavya, Tomizuka, Masayoshi, Adelson, Edward, Agrawal, Pulkit
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915483880521728
author Fang, Hao-Shu
Romero, Branden
Xie, Yichen
Hu, Arthur
Huang, Bo-Ruei
Alvarez, Juan
Kim, Matthew
Margolis, Gabriel
Anbarasu, Kavya
Tomizuka, Masayoshi
Adelson, Edward
Agrawal, Pulkit
author_facet Fang, Hao-Shu
Romero, Branden
Xie, Yichen
Hu, Arthur
Huang, Bo-Ruei
Alvarez, Juan
Kim, Matthew
Margolis, Gabriel
Anbarasu, Kavya
Tomizuka, Masayoshi
Adelson, Edward
Agrawal, Pulkit
contents We introduce perioperation, a paradigm for robotic data collection that sensorizes and records human manipulation while maximizing the transferability of the data to real robots. We implement this paradigm in DEXOP, a passive hand exoskeleton designed to maximize human ability to collect rich sensory (vision + tactile) data for diverse dexterous manipulation tasks in natural environments. DEXOP mechanically connects human fingers to robot fingers, providing users with direct contact feedback (via proprioception) and mirrors the human hand pose to the passive robot hand to maximize the transfer of demonstrated skills to the robot. The force feedback and pose mirroring make task demonstrations more natural for humans compared to teleoperation, increasing both speed and accuracy. We evaluate DEXOP across a range of dexterous, contact-rich tasks, demonstrating its ability to collect high-quality demonstration data at scale. Policies learned with DEXOP data significantly improve task performance per unit time of data collection compared to teleoperation, making DEXOP a powerful tool for advancing robot dexterity. Our project page is at https://dex-op.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04441
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation
Fang, Hao-Shu
Romero, Branden
Xie, Yichen
Hu, Arthur
Huang, Bo-Ruei
Alvarez, Juan
Kim, Matthew
Margolis, Gabriel
Anbarasu, Kavya
Tomizuka, Masayoshi
Adelson, Edward
Agrawal, Pulkit
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
We introduce perioperation, a paradigm for robotic data collection that sensorizes and records human manipulation while maximizing the transferability of the data to real robots. We implement this paradigm in DEXOP, a passive hand exoskeleton designed to maximize human ability to collect rich sensory (vision + tactile) data for diverse dexterous manipulation tasks in natural environments. DEXOP mechanically connects human fingers to robot fingers, providing users with direct contact feedback (via proprioception) and mirrors the human hand pose to the passive robot hand to maximize the transfer of demonstrated skills to the robot. The force feedback and pose mirroring make task demonstrations more natural for humans compared to teleoperation, increasing both speed and accuracy. We evaluate DEXOP across a range of dexterous, contact-rich tasks, demonstrating its ability to collect high-quality demonstration data at scale. Policies learned with DEXOP data significantly improve task performance per unit time of data collection compared to teleoperation, making DEXOP a powerful tool for advancing robot dexterity. Our project page is at https://dex-op.github.io.
title DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2509.04441