Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural Network
Predicting the physics properties of deformable objects such as garments and fabrics is a challenge in robotic research. Directly measuring their physics properties in a real environment is difficult Bouman et al. (2010). Therefore, learning and predicting the physics property parameters of garments...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9931020/ |
| _version_ | 1811233094785564672 |
|---|---|
| author | Li Duan Lewis Boyd Gerardo Aragon-Camarasa |
| author_facet | Li Duan Lewis Boyd Gerardo Aragon-Camarasa |
| author_sort | Li Duan |
| collection | DOAJ |
| description | Predicting the physics properties of deformable objects such as garments and fabrics is a challenge in robotic research. Directly measuring their physics properties in a real environment is difficult Bouman et al. (2010). Therefore, learning and predicting the physics property parameters of garments and fabrics can be conducted in simulated environments. However, garments have collars, sleeves, pockets and buttons that change how garments deform and simulating these is time-consuming. Therefore, in this paper, we propose to predict the physics parameters of real fabrics and garments by learning the physics similarities between simulated fabrics via a Physics Similarity Network (PhySNet). For this, we estimate wind speeds generated by an electric fan and area weights to predict the bending stiffness parameters of real fabrics and garments. We found that PhySNet coupled with a Bayesian optimiser can predict physics property parameters and improve state-of-art by 34.0% for fabrics and 68.1% for garments. |
| first_indexed | 2024-04-12T11:14:39Z |
| format | Article |
| id | doaj.art-651057bbf63d47f8ad038e18587e838d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T11:14:39Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-651057bbf63d47f8ad038e18587e838d2022-12-22T03:35:31ZengIEEEIEEE Access2169-35362022-01-011011472511473410.1109/ACCESS.2022.32174589931020Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural NetworkLi Duan0https://orcid.org/0000-0002-0388-752XLewis Boyd1Gerardo Aragon-Camarasa2https://orcid.org/0000-0003-3756-5569School of Computing Science, University of Glasgow, Glasgow, U.K.National Manufacturing Institute Scotland, University of Strathclyde, Glasgow, U.K.School of Computing Science, University of Glasgow, Glasgow, U.K.Predicting the physics properties of deformable objects such as garments and fabrics is a challenge in robotic research. Directly measuring their physics properties in a real environment is difficult Bouman et al. (2010). Therefore, learning and predicting the physics property parameters of garments and fabrics can be conducted in simulated environments. However, garments have collars, sleeves, pockets and buttons that change how garments deform and simulating these is time-consuming. Therefore, in this paper, we propose to predict the physics parameters of real fabrics and garments by learning the physics similarities between simulated fabrics via a Physics Similarity Network (PhySNet). For this, we estimate wind speeds generated by an electric fan and area weights to predict the bending stiffness parameters of real fabrics and garments. We found that PhySNet coupled with a Bayesian optimiser can predict physics property parameters and improve state-of-art by 34.0% for fabrics and 68.1% for garments.https://ieeexplore.ieee.org/document/9931020/Physics similarity mapphysics similarity distanceBayesian optimizationdeformable objects |
| spellingShingle | Li Duan Lewis Boyd Gerardo Aragon-Camarasa Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural Network IEEE Access Physics similarity map physics similarity distance Bayesian optimization deformable objects |
| title | Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural Network |
| title_full | Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural Network |
| title_fullStr | Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural Network |
| title_full_unstemmed | Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural Network |
| title_short | Learning Physics Property Parameters of Fabrics and Garments With a Physics Similarity Neural Network |
| title_sort | learning physics property parameters of fabrics and garments with a physics similarity neural network |
| topic | Physics similarity map physics similarity distance Bayesian optimization deformable objects |
| url | https://ieeexplore.ieee.org/document/9931020/ |
| work_keys_str_mv | AT liduan learningphysicspropertyparametersoffabricsandgarmentswithaphysicssimilarityneuralnetwork AT lewisboyd learningphysicspropertyparametersoffabricsandgarmentswithaphysicssimilarityneuralnetwork AT gerardoaragoncamarasa learningphysicspropertyparametersoffabricsandgarmentswithaphysicssimilarityneuralnetwork |