Salvato in:
Dettagli Bibliografici
Autori principali: Liao, Zhongyuan, Wang, Junzhe, Liu, Qingyang, Huang, Zhenmin, Ma, Jun, Cai, Yi, Meng, Fei, Liang, Haobo, Wang, Michael Yu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.17929
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916052064010240
author Liao, Zhongyuan
Wang, Junzhe
Liu, Qingyang
Huang, Zhenmin
Ma, Jun
Cai, Yi
Meng, Fei
Liang, Haobo
Wang, Michael Yu
author_facet Liao, Zhongyuan
Wang, Junzhe
Liu, Qingyang
Huang, Zhenmin
Ma, Jun
Cai, Yi
Meng, Fei
Liang, Haobo
Wang, Michael Yu
contents Robotic in-hand manipulation requires reliable object-motion tracking under frequent visual occlusion, yet low-texture visuotactile images provide few stable correspondences for conventional image- or geometry-matching methods. This paper presents TacSE3, a tactile motion-estimation pipeline that converts low-texture visuotactile observations into a decoupled three-dimensional force field and estimates incremental rigid-body motion on SE(3). The method derives planar translation from contact-centroid motion and estimates rotation primarily from shear-related tactile responses, yielding a physically interpretable signal for in-gripper tracking and compensation. Experiments with paired DM-Tac fingertip sensors show that dual-sensor sensing reduces translation-rotation ambiguity, supports rotation tracking across axes and object geometries, and provides a lightweight compensation signal that improves disturbance tolerance in downstream manipulation tasks without retraining the base policy.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17929
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TacSE3: Equivariant SE(3) Motion Estimation from Low-Texture Visuotactile Images for In-Gripper Tracking and Compensation
Liao, Zhongyuan
Wang, Junzhe
Liu, Qingyang
Huang, Zhenmin
Ma, Jun
Cai, Yi
Meng, Fei
Liang, Haobo
Wang, Michael Yu
Robotics
Robotic in-hand manipulation requires reliable object-motion tracking under frequent visual occlusion, yet low-texture visuotactile images provide few stable correspondences for conventional image- or geometry-matching methods. This paper presents TacSE3, a tactile motion-estimation pipeline that converts low-texture visuotactile observations into a decoupled three-dimensional force field and estimates incremental rigid-body motion on SE(3). The method derives planar translation from contact-centroid motion and estimates rotation primarily from shear-related tactile responses, yielding a physically interpretable signal for in-gripper tracking and compensation. Experiments with paired DM-Tac fingertip sensors show that dual-sensor sensing reduces translation-rotation ambiguity, supports rotation tracking across axes and object geometries, and provides a lightweight compensation signal that improves disturbance tolerance in downstream manipulation tasks without retraining the base policy.
title TacSE3: Equivariant SE(3) Motion Estimation from Low-Texture Visuotactile Images for In-Gripper Tracking and Compensation
topic Robotics
url https://arxiv.org/abs/2605.17929