Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection

Collecting naturalistic human manipulation demonstrations with accurate contact force and hand pose is essential for robot dexterous manipulation policy and foundational world model learning - yet no existing wearable platform provides both calibrated fingertip force sensing and occlusion-resilient hand tracking in a form factor that preserves natural manipulation behavior. We present Tactus, a textile-integrated sensing glove that co-optimizes three design pillars: (1) a thin, conformal 3D-knit form factor (1.5 mm fingertip stackup) designed to minimize interference with natural manipulation, (2) strategically placed capacitive tactile sensors at manipulation-relevant regions informed by empirical contact studies, and (3) IMU-fused pose tracking that maintains accuracy through the hand-object occlusions where manipulation data is most valuable. Tactus includes a documented calibration pipeline for cross-glove consistency and per-session calibration for subject-dependent correction. To enable objective comparison, we introduce standardized benchmarking protocols for tactile force regression and hand pose estimation, and apply them to Tactus and two commercially available tactile gloves - to our knowledge the first quantitative cross-platform evaluation of this kind. Tactus resolves a minimum detectable force of 0.59 N at 95% confidence, 1.6 - 2.7x lower than the commercial baselines, and with 0.87 cross-participant consistency, while our pose tracking sustains 11.0 mm fingertip keypoint relative error during manipulation, when occlusion is heaviest. We show that these combined signals support object property estimation, slip detection, and representative recording of hand-object interaction - yielding demonstration data with the fidelity required for contact-aware manipulation policies and world models.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-10-29
DOI
https://doi.org/10.48550/arxiv.2610.39076
Primary Topic
Robot Manipulation and Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection

Garrett Simard, Ehsan Hajiesmaili, Rick James, Daniel Ma et al.
arXiv (Cornell University)
Robot Manipulation and Learning
preprint

Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection

Garrett Simard, Ehsan Hajiesmaili, Rick James, Daniel Ma, Susana Guerrero, Vatsal Mehta, Andrew Gwozdziowski, Elizabeth Casillas, Silvia Espino, David Perek, Jonas Schmidtler, Ergys Ristani, Alexandre Poulin, Sahar Aseeri, Henry Wei, Roger Boldú, Tristan Trutna, Dingtian Zhang, Jordan Brennan, Taylor D. Niehues, James O’Hara, Salwa Rasheed, Monica Ha, Stuart Dealey, Leah Resneck, Katie Rhodes, Rylan Wasson, Alexander Keener, Roham Pardakhtim, Ziyi Kou, Kristine Strøm, Joshua Lang, Mia Huang, Jason Osborne, Tiffany Nguyen, Michael Hurst, Nick Raines, Li Guan, Cameron Lynch, Julia Tanner, Daisy Isibor, Eliot Sosin, Beth Goodrich, Sai Sharan Thirunagari, Kyra Gould, Woo Kim, Adam Swett, Brian Shieh, Tyler Christensen, Ankit Kumar, Kristy Jost, Reed Belcher, Harrison Scarborough, Lizzy Li, Rachael Granberry, Lee Mincey, Nicholas Colonnese, Sahar Rostami, Eileen Wachs, Christina Matos, Ashish Deshpande, Kate Healy, Jesse White, Claire Ikemiya, Chris Doughty, Antonio Woods, Eric Whitmire, Rose Hope, Keagan McCurdy, Gabriel Geyne, Tyler Jorgensen, Beau Woodbyrne, Yashasvi Joginapally, Hector Martinon, Udara Somarathna, Einar Boyovich, Robert Drury, Sai Dhanooshi Marri, Joe Grisso, Hal Talbot-Mantooth, Emelia Black, Jonathan Stewart, Jason Pursel, Forrest Smith, Stuart Nezlek, David Christensen, Julian Blake, Alison Krauskopf, Curtis Torrey, Sean Bonaventure, Simge Uzun, Gaige DeHaven, Benjamin Shuman, Anik Sarker, Samuel Johnson, Katie Doran, Douglas Roberts, Slava Karulin, Jacky Pai, Ben Kamath
preprint en

Abstract

Collecting naturalistic human manipulation demonstrations with accurate contact force and hand pose is essential for robot dexterous manipulation policy and foundational world model learning - yet no existing wearable platform provides both calibrated fingertip force sensing and occlusion-resilient hand tracking in a form factor that preserves natural manipulation behavior. We present Tactus, a textile-integrated sensing glove that co-optimizes three design pillars: (1) a thin, conformal 3D-knit form factor (1.5 mm fingertip stackup) designed to minimize interference with natural manipulation, (2) strategically placed capacitive tactile sensors at manipulation-relevant regions informed by empirical contact studies, and (3) IMU-fused pose tracking that maintains accuracy through the hand-object occlusions where manipulation data is most valuable. Tactus includes a documented calibration pipeline for cross-glove consistency and per-session calibration for subject-dependent correction. To enable objective comparison, we introduce standardized benchmarking protocols for tactile force regression and hand pose estimation, and apply them to Tactus and two commercially available tactile gloves - to our knowledge the first quantitative cross-platform evaluation of this kind. Tactus resolves a minimum detectable force of 0.59 N at 95% confidence, 1.6 - 2.7x lower than the commercial baselines, and with 0.87 cross-participant consistency, while our pose tracking sustains 11.0 mm fingertip keypoint relative error during manipulation, when occlusion is heaviest. We show that these combined signals support object property estimation, slip detection, and representative recording of hand-object interaction - yielding demonstration data with the fidelity required for contact-aware manipulation policies and world models.

arXiv (Cornell University)
Robot Manipulation and Learning
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon