Saved in:
Bibliographic Details
Main Authors: Hua, Qianxi, Li, Xinyue, Yan, Zheng, Li, Yang, Zhang, Chi, Li, Yongyao, Liu, Yufei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.20444
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915949074972672
author Hua, Qianxi
Li, Xinyue
Yan, Zheng
Li, Yang
Zhang, Chi
Li, Yongyao
Liu, Yufei
author_facet Hua, Qianxi
Li, Xinyue
Yan, Zheng
Li, Yang
Zhang, Chi
Li, Yongyao
Liu, Yufei
contents Embodied intelligence has advanced rapidly in recent years; however, bimanual manipulation-especially in contact-rich tasks remains challenging. This is largely due to the lack of datasets with rich physical interaction signals, systematic task organization, and sufficient scale. To address these limitations, we introduce the VTOUCH dataset. It leverages vision based tactile sensing to provide high-fidelity physical interaction signals, adopts a matrix-style task design to enable systematic learning, and employs automated data collection pipelines covering real-world, demand-driven scenarios to ensure scalability. To further validate the effectiveness of the dataset, we conduct extensive quantitative experiments on cross-modal retrieval as well as real-robot evaluation. Finally, we demonstrate real-world performance through generalizable inference across multiple robots, policies, and tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20444
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation
Hua, Qianxi
Li, Xinyue
Yan, Zheng
Li, Yang
Zhang, Chi
Li, Yongyao
Liu, Yufei
Robotics
Artificial Intelligence
Databases
Machine Learning
Embodied intelligence has advanced rapidly in recent years; however, bimanual manipulation-especially in contact-rich tasks remains challenging. This is largely due to the lack of datasets with rich physical interaction signals, systematic task organization, and sufficient scale. To address these limitations, we introduce the VTOUCH dataset. It leverages vision based tactile sensing to provide high-fidelity physical interaction signals, adopts a matrix-style task design to enable systematic learning, and employs automated data collection pipelines covering real-world, demand-driven scenarios to ensure scalability. To further validate the effectiveness of the dataset, we conduct extensive quantitative experiments on cross-modal retrieval as well as real-robot evaluation. Finally, we demonstrate real-world performance through generalizable inference across multiple robots, policies, and tasks.
title VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation
topic Robotics
Artificial Intelligence
Databases
Machine Learning
url https://arxiv.org/abs/2604.20444