CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation

Automating contact-rich manipulation of viscoelastic objects with rigid robots faces challenges including dynamic parameter mismatches, unstable contact oscillations, and spatiotemporal force-deformation coupling. In our prior work, a Compliance-Aware Tactile Control and Hybrid Deformation Regulatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Haobo Kang, Hongjun Ma, Weichang Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11088097/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706416700391424
author Haobo Kang
Hongjun Ma
Weichang Li
author_facet Haobo Kang
Hongjun Ma
Weichang Li
author_sort Haobo Kang
collection DOAJ
description Automating contact-rich manipulation of viscoelastic objects with rigid robots faces challenges including dynamic parameter mismatches, unstable contact oscillations, and spatiotemporal force-deformation coupling. In our prior work, a Compliance-Aware Tactile Control and Hybrid Deformation Regulation (CATCH-FORM-3D) strategy fulfills robust and effective manipulations of 3D viscoelastic objects, which combines a contact force-driven admittance outer loop and a PDE-stabilized inner loop, achieving sub-millimeter surface deformation accuracy and &#x00B1;5% force tracking. However, this strategy requires fine-tuning of object-specific parameters and task-specific calibrations, to bridge this gap, a CATCH-FORM-ACTer is proposed, by enhancing CATCH-FORM-3D with a framework of Action Chunking with Transformer (ACT). An intuitive teleoperation system performs Learning from Demonstration (LfD) to build up a long-horizon sensing, decision-making and execution sequences. Unlike conventional ACT methods focused solely on trajectory planning, our approach dynamically adjusts stiffness, damping, and diffusion parameters in real time during multi-phase manipulations, effectively imitating human-like force-deformation modulation. Experiments on single arm/bimanual robots in three tasks show better force fields patterns and thus <inline-formula> <tex-math notation="LaTeX">$10\%-20\%$ </tex-math></inline-formula> higher success rates versus conventional methods, enabling precise, safe interactions for industrial, medical or household scenarios.
format Article
id doaj-art-dcc0922637f34c5482d6418a7fc10e29
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-dcc0922637f34c5482d6418a7fc10e292025-08-20T03:16:12ZengIEEEIEEE Access2169-35362025-01-011313199813200510.1109/ACCESS.2025.359149911088097CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object ManipulationHaobo Kang0Hongjun Ma1https://orcid.org/0000-0001-5739-8011Weichang Li2School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, ChinaSchool of Automation Science and Engineering, South China University of Technology, Guangzhou, ChinaSchool of Automation Science and Engineering, South China University of Technology, Guangzhou, ChinaAutomating contact-rich manipulation of viscoelastic objects with rigid robots faces challenges including dynamic parameter mismatches, unstable contact oscillations, and spatiotemporal force-deformation coupling. In our prior work, a Compliance-Aware Tactile Control and Hybrid Deformation Regulation (CATCH-FORM-3D) strategy fulfills robust and effective manipulations of 3D viscoelastic objects, which combines a contact force-driven admittance outer loop and a PDE-stabilized inner loop, achieving sub-millimeter surface deformation accuracy and &#x00B1;5% force tracking. However, this strategy requires fine-tuning of object-specific parameters and task-specific calibrations, to bridge this gap, a CATCH-FORM-ACTer is proposed, by enhancing CATCH-FORM-3D with a framework of Action Chunking with Transformer (ACT). An intuitive teleoperation system performs Learning from Demonstration (LfD) to build up a long-horizon sensing, decision-making and execution sequences. Unlike conventional ACT methods focused solely on trajectory planning, our approach dynamically adjusts stiffness, damping, and diffusion parameters in real time during multi-phase manipulations, effectively imitating human-like force-deformation modulation. Experiments on single arm/bimanual robots in three tasks show better force fields patterns and thus <inline-formula> <tex-math notation="LaTeX">$10\%-20\%$ </tex-math></inline-formula> higher success rates versus conventional methods, enabling precise, safe interactions for industrial, medical or household scenarios.https://ieeexplore.ieee.org/document/11088097/Contact-rich manipulationvision-tactile perceptionviscoelastic materialslearning from demonstrationrobotic hand3D Kelvin–Voigt and Maxwell models
spellingShingle Haobo Kang
Hongjun Ma
Weichang Li
CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation
IEEE Access
Contact-rich manipulation
vision-tactile perception
viscoelastic materials
learning from demonstration
robotic hand
3D Kelvin–Voigt and Maxwell models
title CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation
title_full CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation
title_fullStr CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation
title_full_unstemmed CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation
title_short CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation
title_sort catch form acter compliance aware tactile control and hybrid deformation regulation based action transformer for viscoelastic object manipulation
topic Contact-rich manipulation
vision-tactile perception
viscoelastic materials
learning from demonstration
robotic hand
3D Kelvin–Voigt and Maxwell models
url https://ieeexplore.ieee.org/document/11088097/
work_keys_str_mv AT haobokang catchformactercomplianceawaretactilecontrolandhybriddeformationregulationbasedactiontransformerforviscoelasticobjectmanipulation
AT hongjunma catchformactercomplianceawaretactilecontrolandhybriddeformationregulationbasedactiontransformerforviscoelasticobjectmanipulation
AT weichangli catchformactercomplianceawaretactilecontrolandhybriddeformationregulationbasedactiontransformerforviscoelasticobjectmanipulation