Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Antonio Gabas"'
Publikováno v:
ROBOMECH Journal, Vol 8, Iss 1, Pp 1-12 (2021)
Abstract Compared with more rigid objects, clothing items are inherently difficult for robots to recognize and manipulate. We propose a method for detecting how cloth is folded, to facilitate choosing a manipulative action that corresponds to a garme
Externí odkaz:
https://doaj.org/article/9d01c691d395460e9d6cd53b60bb95cd
Autor:
Mehdi Benallegue, Fumio Kanehiro, Iori Kumagai, Rohan P. Singh, Antonio Gabas, Yusuke Yoshiyasu
Publikováno v:
SII
In many robotic applications, the environment setting in which the 6-DoF pose estimation of a known, rigid object and its subsequent grasping is to be performed, remains nearly unchanging and might even be known to the robot in advance. In this paper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb9a12cc5c66bce35a6924d6e655e39a
http://arxiv.org/abs/2207.13264
http://arxiv.org/abs/2207.13264
Publikováno v:
ROBOMECH Journal, Vol 8, Iss 1, Pp 1-12 (2021)
Compared with more rigid objects, clothing items are inherently difficult for robots to recognize and manipulate. We propose a method for detecting how cloth is folded, to facilitate choosing a manipulative action that corresponds to a garment’s sh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5653f85cfa8f49b218eb220cda2d8919
https://doi.org/10.1186/s40648-021-00202-8
https://doi.org/10.1186/s40648-021-00202-8
Publikováno v:
ICIP
Recent advances in deep learning have shown high success in obtaining the 6-DoF pose of rigid objects. However, most works rely on a pre-existing dataset and do not tackle the data gathering part. The time-consuming and tedious tasks required to buil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5286031042bc026e854daa415aaac242
https://doi.org/10.1109/icip40778.2020.9190664
https://doi.org/10.1109/icip40778.2020.9190664
Publikováno v:
SII
In this research, we propose a method for estimating 6 DOF object pose (3D orientation and position), based on convolutional neural networks (CNN). We propose RotationCNN that predicts 3D orientation of the object. The position of the object is estim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0977c3d6a71764cec87dde9bac02219d
https://doi.org/10.1109/sii.2019.8700331
https://doi.org/10.1109/sii.2019.8700331
Publikováno v:
SIGGRAPH ASIA Posters
Object pose estimation based on a RGB image is essential in accomplishing many computer vision tasks, such as augmented reality and robot vision for grasping. Using structure from motion and domain randomization, we propose a method that, from a set
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8e41c42857ebaf2624574addfca311dd
https://doi.org/10.1145/3283289.3283326
https://doi.org/10.1145/3283289.3283326
Autor:
Yasuyo Kita, Antonio Gabas
Publikováno v:
ICAR
The physical edges of an object contain valuable information to recognize its shape and also to manipulate it. In the case of handling clothing items automatically, the physical edges give important clues to determine its type and shape as well as to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e348dbde1402a1a8fe1c8e79c01b7d9
https://doi.org/10.1109/icar.2017.8023660
https://doi.org/10.1109/icar.2017.8023660