Vi-TacMan: Articulated Object Manipulation via Vision and Touch

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Leiyao, Zhao, Zihang, Xie, Sirui, Zhang, Wenhuan, Han, Zhi, Zhu, Yixin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915907354230784
author Cui, Leiyao
Zhao, Zihang
Xie, Sirui
Zhang, Wenhuan
Han, Zhi
Zhu, Yixin
author_facet Cui, Leiyao
Zhao, Zihang
Xie, Sirui
Zhang, Wenhuan
Han, Zhi
Zhu, Yixin
contents Autonomous manipulation of articulated objects remains a fundamental challenge for robots in human environments. Vision-based methods can infer hidden kinematics but can yield imprecise estimates on unfamiliar objects. Tactile approaches achieve robust control through contact feedback but require accurate initialization. This suggests a natural synergy: vision for global guidance, touch for local precision. Yet no framework systematically exploits this complementarity for generalized articulated manipulation. Here we present Vi-TacMan, which uses vision to propose grasps and coarse directions that seed a tactile controller for precise execution. By incorporating surface normals as geometric priors and modeling directions via von Mises-Fisher distributions, our approach achieves significant gains over baselines (all p<0.0001). Critically, manipulation succeeds without explicit kinematic models -- the tactile controller refines coarse visual estimates through real-time contact regulation. Tests on more than 50,000 simulated and diverse real-world objects confirm robust cross-category generalization. This work establishes that coarse visual cues suffice for reliable manipulation when coupled with tactile feedback, offering a scalable paradigm for autonomous systems in unstructured environments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06339
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vi-TacMan: Articulated Object Manipulation via Vision and Touch
Cui, Leiyao
Zhao, Zihang
Xie, Sirui
Zhang, Wenhuan
Han, Zhi
Zhu, Yixin
Robotics
Autonomous manipulation of articulated objects remains a fundamental challenge for robots in human environments. Vision-based methods can infer hidden kinematics but can yield imprecise estimates on unfamiliar objects. Tactile approaches achieve robust control through contact feedback but require accurate initialization. This suggests a natural synergy: vision for global guidance, touch for local precision. Yet no framework systematically exploits this complementarity for generalized articulated manipulation. Here we present Vi-TacMan, which uses vision to propose grasps and coarse directions that seed a tactile controller for precise execution. By incorporating surface normals as geometric priors and modeling directions via von Mises-Fisher distributions, our approach achieves significant gains over baselines (all p<0.0001). Critically, manipulation succeeds without explicit kinematic models -- the tactile controller refines coarse visual estimates through real-time contact regulation. Tests on more than 50,000 simulated and diverse real-world objects confirm robust cross-category generalization. This work establishes that coarse visual cues suffice for reliable manipulation when coupled with tactile feedback, offering a scalable paradigm for autonomous systems in unstructured environments.
title Vi-TacMan: Articulated Object Manipulation via Vision and Touch
topic Robotics
url https://arxiv.org/abs/2510.06339