DexViTac: Collecting Human Visuo-Tactile-Kinematic Demonstrations for Contact-Rich Dexterous Manipulation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Xitong, Pan, Yifeng, Li, Min, Ding, Xiaotian
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908898120695808
author Chen, Xitong
Pan, Yifeng
Li, Min
Ding, Xiaotian
author_facet Chen, Xitong
Pan, Yifeng
Li, Min
Ding, Xiaotian
contents Large-scale, high-quality multimodal demonstrations are essential for robot learning of contact-rich dexterous manipulation. While human-centric data collection systems lower the barrier to scaling, they struggle to capture the tactile information during physical interactions. Motivated by this, we present DexViTac, a portable, human-centric data collection system tailored for contact-rich dexterous manipulation. The system enables the high-fidelity acquisition of first-person vision, high-density tactile sensing, end-effector poses, and hand kinematics within unstructured, in-the-wild environments. Building upon this hardware, we propose a kinematics-grounded tactile representation learning algorithm that effectively resolves semantic ambiguities within tactile signals. Leveraging the efficiency of DexViTac, we construct a multimodal dataset comprising over 2,400 visuo-tactile-kinematic demonstrations. Experiments demonstrate that DexViTac achieves a collection efficiency exceeding 248 demonstrations per hour and remains robust against complex visual occlusions. Real-world deployment confirms that policies trained with the proposed dataset and learning strategy achieve an average success rate exceeding 85% across four challenging tasks. This performance significantly outperforms baseline methods, thereby validating the substantial improvement the system provides for learning contact-rich dexterous manipulation. Project page: https://xitong-c.github.io/DexViTac/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17851
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DexViTac: Collecting Human Visuo-Tactile-Kinematic Demonstrations for Contact-Rich Dexterous Manipulation
Chen, Xitong
Pan, Yifeng
Li, Min
Ding, Xiaotian
Robotics
Large-scale, high-quality multimodal demonstrations are essential for robot learning of contact-rich dexterous manipulation. While human-centric data collection systems lower the barrier to scaling, they struggle to capture the tactile information during physical interactions. Motivated by this, we present DexViTac, a portable, human-centric data collection system tailored for contact-rich dexterous manipulation. The system enables the high-fidelity acquisition of first-person vision, high-density tactile sensing, end-effector poses, and hand kinematics within unstructured, in-the-wild environments. Building upon this hardware, we propose a kinematics-grounded tactile representation learning algorithm that effectively resolves semantic ambiguities within tactile signals. Leveraging the efficiency of DexViTac, we construct a multimodal dataset comprising over 2,400 visuo-tactile-kinematic demonstrations. Experiments demonstrate that DexViTac achieves a collection efficiency exceeding 248 demonstrations per hour and remains robust against complex visual occlusions. Real-world deployment confirms that policies trained with the proposed dataset and learning strategy achieve an average success rate exceeding 85% across four challenging tasks. This performance significantly outperforms baseline methods, thereby validating the substantial improvement the system provides for learning contact-rich dexterous manipulation. Project page: https://xitong-c.github.io/DexViTac/.
title DexViTac: Collecting Human Visuo-Tactile-Kinematic Demonstrations for Contact-Rich Dexterous Manipulation
topic Robotics
url https://arxiv.org/abs/2603.17851