Deformability-Based Grasp Pose Detection From a Visible Image

In this study, we introduce a method for estimating deformability from the appearance of an object and a technique for detecting the grasp pose using a single-depth image. Deformability, defined as a score, provides an approximate measure of the ease with which an object can be deformed, based on th...

Full description

Saved in:
Bibliographic Details
Main Authors: Koshi Makihara, Yukiyasu Domae, Ryo Hanai, Ixchel G. Ramirez-Alpizar, Hirokatsu Kataoka, Kensuke Harada
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10776971/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850132093370105856
author Koshi Makihara
Yukiyasu Domae
Ryo Hanai
Ixchel G. Ramirez-Alpizar
Hirokatsu Kataoka
Kensuke Harada
author_facet Koshi Makihara
Yukiyasu Domae
Ryo Hanai
Ixchel G. Ramirez-Alpizar
Hirokatsu Kataoka
Kensuke Harada
author_sort Koshi Makihara
collection DOAJ
description In this study, we introduce a method for estimating deformability from the appearance of an object and a technique for detecting the grasp pose using a single-depth image. Deformability, defined as a score, provides an approximate measure of the ease with which an object can be deformed, based on the intuitive human assumption that appearance correlates with this property. Unlike previous approaches that synthesize the entire image in one step and struggle with accuracy in complex scenarios, such as cluttered environments with multiple objects, our method advances the field by employing an encoder-decoder model for simultaneous deformability estimation and instance segmentation from depth images, as well as by enhancing grasp pose detection for deformable objects under specific conditions using the outcomes of our deformability assessments. We demonstrated the efficacy of our integrated approach in diverse challenging settings, including the manipulation of deformable hollow objects in cluttered scenes, interaction with partially deformable objects, and displacement of nearby deformable objects in real-world environments.
format Article
id doaj-art-629e0a06cd124075a69e3b6cb8a5885d
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-629e0a06cd124075a69e3b6cb8a5885d2025-08-20T02:32:16ZengIEEEIEEE Access2169-35362024-01-011219064019064910.1109/ACCESS.2024.351154610776971Deformability-Based Grasp Pose Detection From a Visible ImageKoshi Makihara0https://orcid.org/0000-0003-4145-7595Yukiyasu Domae1https://orcid.org/0000-0002-1366-9657Ryo Hanai2https://orcid.org/0000-0003-4216-4866Ixchel G. Ramirez-Alpizar3https://orcid.org/0000-0002-7805-7539Hirokatsu Kataoka4https://orcid.org/0000-0001-8844-165XKensuke Harada5https://orcid.org/0000-0002-7576-756XGraduate School of Engineering Science, Osaka University, Osaka, JapanNational Institute of Advanced Industrial Science and Technology, Tokyo, JapanNational Institute of Advanced Industrial Science and Technology, Tokyo, JapanNational Institute of Advanced Industrial Science and Technology, Tokyo, JapanNational Institute of Advanced Industrial Science and Technology, Tokyo, JapanGraduate School of Engineering Science, Osaka University, Osaka, JapanIn this study, we introduce a method for estimating deformability from the appearance of an object and a technique for detecting the grasp pose using a single-depth image. Deformability, defined as a score, provides an approximate measure of the ease with which an object can be deformed, based on the intuitive human assumption that appearance correlates with this property. Unlike previous approaches that synthesize the entire image in one step and struggle with accuracy in complex scenarios, such as cluttered environments with multiple objects, our method advances the field by employing an encoder-decoder model for simultaneous deformability estimation and instance segmentation from depth images, as well as by enhancing grasp pose detection for deformable objects under specific conditions using the outcomes of our deformability assessments. We demonstrated the efficacy of our integrated approach in diverse challenging settings, including the manipulation of deformable hollow objects in cluttered scenes, interaction with partially deformable objects, and displacement of nearby deformable objects in real-world environments.https://ieeexplore.ieee.org/document/10776971/Graspingdeformable objectsdeformability estimation
spellingShingle Koshi Makihara
Yukiyasu Domae
Ryo Hanai
Ixchel G. Ramirez-Alpizar
Hirokatsu Kataoka
Kensuke Harada
Deformability-Based Grasp Pose Detection From a Visible Image
IEEE Access
Grasping
deformable objects
deformability estimation
title Deformability-Based Grasp Pose Detection From a Visible Image
title_full Deformability-Based Grasp Pose Detection From a Visible Image
title_fullStr Deformability-Based Grasp Pose Detection From a Visible Image
title_full_unstemmed Deformability-Based Grasp Pose Detection From a Visible Image
title_short Deformability-Based Grasp Pose Detection From a Visible Image
title_sort deformability based grasp pose detection from a visible image
topic Grasping
deformable objects
deformability estimation
url https://ieeexplore.ieee.org/document/10776971/
work_keys_str_mv AT koshimakihara deformabilitybasedgraspposedetectionfromavisibleimage
AT yukiyasudomae deformabilitybasedgraspposedetectionfromavisibleimage
AT ryohanai deformabilitybasedgraspposedetectionfromavisibleimage
AT ixchelgramirezalpizar deformabilitybasedgraspposedetectionfromavisibleimage
AT hirokatsukataoka deformabilitybasedgraspposedetectionfromavisibleimage
AT kensukeharada deformabilitybasedgraspposedetectionfromavisibleimage