DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mandi, Zhao, Hou, Yifan, Fox, Dieter, Narang, Yashraj, Mandlekar, Ajay, Song, Shuran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912404335493120
author Mandi, Zhao
Hou, Yifan
Fox, Dieter
Narang, Yashraj
Mandlekar, Ajay
Song, Shuran
author_facet Mandi, Zhao
Hou, Yifan
Fox, Dieter
Narang, Yashraj
Mandlekar, Ajay
Song, Shuran
contents We study the problem of functional retargeting: learning dexterous manipulation policies to track object states from human hand-object demonstrations. We focus on long-horizon, bimanual tasks with articulated objects, which is challenging due to large action space, spatiotemporal discontinuities, and embodiment gap between human and robot hands. We propose DexMachina, a novel curriculum-based algorithm: the key idea is to use virtual object controllers with decaying strength: an object is first driven automatically towards its target states, such that the policy can gradually learn to take over under motion and contact guidance. We release a simulation benchmark with a diverse set of tasks and dexterous hands, and show that DexMachina significantly outperforms baseline methods. Our algorithm and benchmark enable a functional comparison for hardware designs, and we present key findings informed by quantitative and qualitative results. With the recent surge in dexterous hand development, we hope this work will provide a useful platform for identifying desirable hardware capabilities and lower the barrier for contributing to future research. Videos and more at https://project-dexmachina.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2505_24853
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
Mandi, Zhao
Hou, Yifan
Fox, Dieter
Narang, Yashraj
Mandlekar, Ajay
Song, Shuran
Robotics
Artificial Intelligence
Machine Learning
We study the problem of functional retargeting: learning dexterous manipulation policies to track object states from human hand-object demonstrations. We focus on long-horizon, bimanual tasks with articulated objects, which is challenging due to large action space, spatiotemporal discontinuities, and embodiment gap between human and robot hands. We propose DexMachina, a novel curriculum-based algorithm: the key idea is to use virtual object controllers with decaying strength: an object is first driven automatically towards its target states, such that the policy can gradually learn to take over under motion and contact guidance. We release a simulation benchmark with a diverse set of tasks and dexterous hands, and show that DexMachina significantly outperforms baseline methods. Our algorithm and benchmark enable a functional comparison for hardware designs, and we present key findings informed by quantitative and qualitative results. With the recent surge in dexterous hand development, we hope this work will provide a useful platform for identifying desirable hardware capabilities and lower the barrier for contributing to future research. Videos and more at https://project-dexmachina.github.io/
title DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.24853