mimic-one: a Scalable Model Recipe for General Purpose Robot Dexterity

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nava, Elvis, Montesinos, Victoriano, Bauer, Erik, Forrai, Benedek, Pai, Jonas, Weirich, Stefan, Gravert, Stephan-Daniel, Wand, Philipp, Polinski, Stephan, Grewe, Benjamin F., Katzschmann, Robert K.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913892431560704
author Nava, Elvis
Montesinos, Victoriano
Bauer, Erik
Forrai, Benedek
Pai, Jonas
Weirich, Stefan
Gravert, Stephan-Daniel
Wand, Philipp
Polinski, Stephan
Grewe, Benjamin F.
Katzschmann, Robert K.
author_facet Nava, Elvis
Montesinos, Victoriano
Bauer, Erik
Forrai, Benedek
Pai, Jonas
Weirich, Stefan
Gravert, Stephan-Daniel
Wand, Philipp
Polinski, Stephan
Grewe, Benjamin F.
Katzschmann, Robert K.
contents We present a diffusion-based model recipe for real-world control of a highly dexterous humanoid robotic hand, designed for sample-efficient learning and smooth fine-motor action inference. Our system features a newly designed 16-DoF tendon-driven hand, equipped with wide angle wrist cameras and mounted on a Franka Emika Panda arm. We develop a versatile teleoperation pipeline and data collection protocol using both glove-based and VR interfaces, enabling high-quality data collection across diverse tasks such as pick and place, item sorting and assembly insertion. Leveraging high-frequency generative control, we train end-to-end policies from raw sensory inputs, enabling smooth, self-correcting motions in complex manipulation scenarios. Real-world evaluations demonstrate up to 93.3% out of distribution success rates, with up to a +33.3% performance boost due to emergent self-correcting behaviors, while also revealing scaling trends in policy performance. Our results advance the state-of-the-art in dexterous robotic manipulation through a fully integrated, practical approach to hardware, learning, and real-world deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11916
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle mimic-one: a Scalable Model Recipe for General Purpose Robot Dexterity
Nava, Elvis
Montesinos, Victoriano
Bauer, Erik
Forrai, Benedek
Pai, Jonas
Weirich, Stefan
Gravert, Stephan-Daniel
Wand, Philipp
Polinski, Stephan
Grewe, Benjamin F.
Katzschmann, Robert K.
Robotics
We present a diffusion-based model recipe for real-world control of a highly dexterous humanoid robotic hand, designed for sample-efficient learning and smooth fine-motor action inference. Our system features a newly designed 16-DoF tendon-driven hand, equipped with wide angle wrist cameras and mounted on a Franka Emika Panda arm. We develop a versatile teleoperation pipeline and data collection protocol using both glove-based and VR interfaces, enabling high-quality data collection across diverse tasks such as pick and place, item sorting and assembly insertion. Leveraging high-frequency generative control, we train end-to-end policies from raw sensory inputs, enabling smooth, self-correcting motions in complex manipulation scenarios. Real-world evaluations demonstrate up to 93.3% out of distribution success rates, with up to a +33.3% performance boost due to emergent self-correcting behaviors, while also revealing scaling trends in policy performance. Our results advance the state-of-the-art in dexterous robotic manipulation through a fully integrated, practical approach to hardware, learning, and real-world deployment.
title mimic-one: a Scalable Model Recipe for General Purpose Robot Dexterity
topic Robotics
url https://arxiv.org/abs/2506.11916