InvariantCloud: A Globally Invariant, Uniquely Indexed Point Cloud Framework for Robust 6-DoF Tactile Pose Tracking

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ye, Pengfei, Ma, Yuxiang, Zhou, Yi, Chen, Wei, Dong, Wenzhen, Duan, Molong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911715229171712
author Ye, Pengfei
Ma, Yuxiang
Zhou, Yi
Chen, Wei
Dong, Wenzhen
Duan, Molong
author_facet Ye, Pengfei
Ma, Yuxiang
Zhou, Yi
Chen, Wei
Dong, Wenzhen
Duan, Molong
contents Recent advances in imitation learning and vision-language models highlight the need for high-fidelity tactile perception, with 6-DoF tactile object pose estimation providing a crucial foundation for precise robotic manipulation. We introduce InvariantCloud, a 6-DoF pose estimation framework that leverages the global invariance of surface marker constellations on vision-based tactile sensors. In contrast to recent approaches, our one-shot globally invariant point cloud registration suppresses cumulative drift and overcomes long-standing limitations in accurately estimating yaw (Z-axis) rotation. Experimental verifications show that InvariantCloud achieves superior yaw tracking accuracy and re-localization repeatability compared to existing benchmarks, demonstrating its precision and robustness in long-sequence manipulation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25216
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle InvariantCloud: A Globally Invariant, Uniquely Indexed Point Cloud Framework for Robust 6-DoF Tactile Pose Tracking
Ye, Pengfei
Ma, Yuxiang
Zhou, Yi
Chen, Wei
Dong, Wenzhen
Duan, Molong
Robotics
Recent advances in imitation learning and vision-language models highlight the need for high-fidelity tactile perception, with 6-DoF tactile object pose estimation providing a crucial foundation for precise robotic manipulation. We introduce InvariantCloud, a 6-DoF pose estimation framework that leverages the global invariance of surface marker constellations on vision-based tactile sensors. In contrast to recent approaches, our one-shot globally invariant point cloud registration suppresses cumulative drift and overcomes long-standing limitations in accurately estimating yaw (Z-axis) rotation. Experimental verifications show that InvariantCloud achieves superior yaw tracking accuracy and re-localization repeatability compared to existing benchmarks, demonstrating its precision and robustness in long-sequence manipulation tasks.
title InvariantCloud: A Globally Invariant, Uniquely Indexed Point Cloud Framework for Robust 6-DoF Tactile Pose Tracking
topic Robotics
url https://arxiv.org/abs/2605.25216