Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Gerardo Aragon-Camarasa"'
Publikováno v:
IEEE Access, Vol 10, Pp 114725-114734 (2022)
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 pred
Externí odkaz:
https://doaj.org/article/651057bbf63d47f8ad038e18587e838d
Autor:
Juan Manuel Parrilla-Gutierrez, Abhishek Sharma, Soichiro Tsuda, Geoffrey J. T. Cooper, Gerardo Aragon-Camarasa, Kevin Donkers, Leroy Cronin
Publikováno v:
Nature Communications, Vol 11, Iss 1, Pp 1-8 (2020)
Unconventional computing architectures might outperform current ones, but their realization has been limited to solving simple specific problems. Here, a network of interconnected Belousov-Zhabotinski reactions, operated by independent magnetic stirr
Externí odkaz:
https://doaj.org/article/32f8cac6c127403e8bcab5b353b5904a
Publikováno v:
IEEE Access, Vol 6, Pp 76646-76662 (2018)
This paper presents a novel robot vision architecture for perceiving generic 3-D clothes configurations. Our architecture is hierarchically structured, starting from low-level curvature features to mid-level geometric shapes and topology descriptions
Externí odkaz:
https://doaj.org/article/a76e3620ce874866b7fc7354f27033f6
Autor:
Gerardo Aragon-Camarasa, Li Duan
Publikováno v:
IEEE Robotics and Automation Letters. 7:7950-7957
We present a continuous perception approach that learns geometric and physical similarities between garments by continuously observing a garment while a robot picks it up from a table. The aim is to capture and encode geometric and physical character
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f3c88f0e6f8890254a8f7c4606e6e5f
https://doi.org/10.1109/lra.2022.3186747
https://doi.org/10.1109/lra.2022.3186747
Autor:
Li Duan, Gerardo Aragon-Camarasa
Due to the high dimensionality of object states, a garment flattening pipeline requires recognising the configurations of garments for a robot to produce/select manipulation plans to flatten garments. In this paper, we propose a data-centric approach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::125b131904c0f92db399c950731828d2
https://doi.org/10.2139/ssrn.4361748
https://doi.org/10.2139/ssrn.4361748
Publikováno v:
2022 IEEE International Conference on Robotics and Biomimetics (ROBIO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ce1b0233ad375a2fb3d6fba5aa887a1d
https://doi.org/10.1109/robio55434.2022.10011774
https://doi.org/10.1109/robio55434.2022.10011774
Autor:
Li Duan, Gerardo Aragon-Camarasa
Publikováno v:
2022 4th International Conference on Robotics and Computer Vision (ICRCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac4ee1221188e03608201761c45a893c
https://doi.org/10.1109/icrcv55858.2022.9953186
https://doi.org/10.1109/icrcv55858.2022.9953186
Simulation software is a powerful tool for robotics research, allowing the virtual representation of the real world. However with the rise of the Robot Operating System (ROS), there are new simulation software packages that have not been compared wit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5dddc55da020339bca0f56ee38edbcd
http://arxiv.org/abs/2204.06433
http://arxiv.org/abs/2204.06433
Publikováno v:
International Journal of Advanced Robotic Systems, Vol 13 (2016)
In this paper, we investigate the contribution that visual perception affords to a robotic manipulation task in which a crumpled garment is flattened by eliminating visually detected wrinkles. In order to explore and validate visually guided clothing
Externí odkaz:
https://doaj.org/article/5664225435ef4c18b74d89f5f9dcb8b8
Autor:
Luca Marzari, Ameya Pore, Diego Dall'Alba, Gerardo Aragon-Camarasa, Alessandro Farinelli, Paolo Fiorini
Publikováno v:
2021 20th International Conference on Advanced Robotics (ICAR).
Deep Reinforcement Learning (DRL) is emerging as a promising approach to generate adaptive behaviors for robotic platforms. However, a major drawback of using DRL is the data-hungry training regime that requires millions of trial and error attempts,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50c91d313553a2c579339994c9891906
https://doi.org/10.1109/icar53236.2021.9659344
https://doi.org/10.1109/icar53236.2021.9659344