Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ye, Jianglong, Wang, Keyi, Yuan, Chengjing, Yang, Ruihan, Li, Yiquan, Zhu, Jiyue, Qin, Yuzhe, Zou, Xueyan, Wang, Xiaolong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908415003983872
author Ye, Jianglong
Wang, Keyi
Yuan, Chengjing
Yang, Ruihan
Li, Yiquan
Zhu, Jiyue
Qin, Yuzhe
Zou, Xueyan
Wang, Xiaolong
author_facet Ye, Jianglong
Wang, Keyi
Yuan, Chengjing
Yang, Ruihan
Li, Yiquan
Zhu, Jiyue
Qin, Yuzhe
Zou, Xueyan
Wang, Xiaolong
contents Generating large-scale demonstrations for dexterous hand manipulation remains challenging, and several approaches have been proposed in recent years to address this. Among them, generative models have emerged as a promising paradigm, enabling the efficient creation of diverse and physically plausible demonstrations. In this paper, we introduce Dex1B, a large-scale, diverse, and high-quality demonstration dataset produced with generative models. The dataset contains one billion demonstrations for two fundamental tasks: grasping and articulation. To construct it, we propose a generative model that integrates geometric constraints to improve feasibility and applies additional conditions to enhance diversity. We validate the model on both established and newly introduced simulation benchmarks, where it significantly outperforms prior state-of-the-art methods. Furthermore, we demonstrate its effectiveness and robustness through real-world robot experiments. Our project page is at https://jianglongye.com/dex1b
format Preprint
id arxiv_https___arxiv_org_abs_2506_17198
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation
Ye, Jianglong
Wang, Keyi
Yuan, Chengjing
Yang, Ruihan
Li, Yiquan
Zhu, Jiyue
Qin, Yuzhe
Zou, Xueyan
Wang, Xiaolong
Robotics
Computer Vision and Pattern Recognition
Generating large-scale demonstrations for dexterous hand manipulation remains challenging, and several approaches have been proposed in recent years to address this. Among them, generative models have emerged as a promising paradigm, enabling the efficient creation of diverse and physically plausible demonstrations. In this paper, we introduce Dex1B, a large-scale, diverse, and high-quality demonstration dataset produced with generative models. The dataset contains one billion demonstrations for two fundamental tasks: grasping and articulation. To construct it, we propose a generative model that integrates geometric constraints to improve feasibility and applies additional conditions to enhance diversity. We validate the model on both established and newly introduced simulation benchmarks, where it significantly outperforms prior state-of-the-art methods. Furthermore, we demonstrate its effectiveness and robustness through real-world robot experiments. Our project page is at https://jianglongye.com/dex1b
title Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.17198