Cloth manipulation based on motion generation and shape prediction by EM*D-net
In this paper, we describe a motion planning method for cloth manipulation. We address the problem that only the current shape of the cloth product and its target shape are given. To accomplish this task, it is necessary to determine how to manipulate the cloth and to predict the manipulated shape o...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | Japanese |
Published: |
The Japan Society of Mechanical Engineers
2018-06-01
|
Series: | Nihon Kikai Gakkai ronbunshu |
Subjects: | |
Online Access: | https://www.jstage.jst.go.jp/article/transjsme/84/864/84_18-00069/_pdf/-char/en |
_version_ | 1797988996457955328 |
---|---|
author | Daisuke TANAKA Solvi ARNOLD Kimitoshi YAMAZAKI |
author_facet | Daisuke TANAKA Solvi ARNOLD Kimitoshi YAMAZAKI |
author_sort | Daisuke TANAKA |
collection | DOAJ |
description | In this paper, we describe a motion planning method for cloth manipulation. We address the problem that only the current shape of the cloth product and its target shape are given. To accomplish this task, it is necessary to determine how to manipulate the cloth and to predict the manipulated shape of the cloth. Therefore, we propose a novel method using deep neural network. An input of the network is a voxelized cloth shape and conceivable manipulations, and an output is a voxelized cloth shape after the manipulations. The effectiveness of the proposed method was proven by experiments using a dual-armed robot. It included quantitative evaluation about the manipulated shape of a rectangular cloth. It was also studied that how to prepare appropriate learning data and do learning well. |
first_indexed | 2024-04-11T08:13:13Z |
format | Article |
id | doaj.art-f407b0504fea4081a9c58c543620ecea |
institution | Directory Open Access Journal |
issn | 2187-9761 |
language | Japanese |
last_indexed | 2024-04-11T08:13:13Z |
publishDate | 2018-06-01 |
publisher | The Japan Society of Mechanical Engineers |
record_format | Article |
series | Nihon Kikai Gakkai ronbunshu |
spelling | doaj.art-f407b0504fea4081a9c58c543620ecea2022-12-22T04:35:16ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612018-06-018486418-0006918-0006910.1299/transjsme.18-00069transjsmeCloth manipulation based on motion generation and shape prediction by EM*D-netDaisuke TANAKA0Solvi ARNOLD1Kimitoshi YAMAZAKI2Mechanical Systems Engineering, Shinshu UniversityMechanical Systems Engineering, Faculty of Engineering, Shinshu UniversityMechanical Systems Engineering, Faculty of Engineering, Shinshu UniversityIn this paper, we describe a motion planning method for cloth manipulation. We address the problem that only the current shape of the cloth product and its target shape are given. To accomplish this task, it is necessary to determine how to manipulate the cloth and to predict the manipulated shape of the cloth. Therefore, we propose a novel method using deep neural network. An input of the network is a voxelized cloth shape and conceivable manipulations, and an output is a voxelized cloth shape after the manipulations. The effectiveness of the proposed method was proven by experiments using a dual-armed robot. It included quantitative evaluation about the manipulated shape of a rectangular cloth. It was also studied that how to prepare appropriate learning data and do learning well.https://www.jstage.jst.go.jp/article/transjsme/84/864/84_18-00069/_pdf/-char/encloth manipulationplanningmulti-step manipulation |
spellingShingle | Daisuke TANAKA Solvi ARNOLD Kimitoshi YAMAZAKI Cloth manipulation based on motion generation and shape prediction by EM*D-net Nihon Kikai Gakkai ronbunshu cloth manipulation planning multi-step manipulation |
title | Cloth manipulation based on motion generation and shape prediction by EM*D-net |
title_full | Cloth manipulation based on motion generation and shape prediction by EM*D-net |
title_fullStr | Cloth manipulation based on motion generation and shape prediction by EM*D-net |
title_full_unstemmed | Cloth manipulation based on motion generation and shape prediction by EM*D-net |
title_short | Cloth manipulation based on motion generation and shape prediction by EM*D-net |
title_sort | cloth manipulation based on motion generation and shape prediction by em d net |
topic | cloth manipulation planning multi-step manipulation |
url | https://www.jstage.jst.go.jp/article/transjsme/84/864/84_18-00069/_pdf/-char/en |
work_keys_str_mv | AT daisuketanaka clothmanipulationbasedonmotiongenerationandshapepredictionbyemdnet AT solviarnold clothmanipulationbasedonmotiongenerationandshapepredictionbyemdnet AT kimitoshiyamazaki clothmanipulationbasedonmotiongenerationandshapepredictionbyemdnet |