Výsledky vyhledávání - "Natalia Lyubova"

Multi-modal Open World User Identification

Autor: Natalia Lyubova, Bahar Irfan, Michael Garcia Ortiz, Tony Belpaeme

Publikováno v: ACM Transactions on Human-Robot Interaction. 11:1-50

User identification is an essential step in creating a personalised long-term interaction with robots. This requires learning the users continuously and incrementally, possibly starting from a state without any known user. In this article, we describ

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2be74f30b31bf0d416ee4b65c0f23602
https://doi.org/10.1145/3477963

Zobrazit plný text záznamu

Mind the regularized GAP, for human action classification and semi-supervised localization based on visual saliency

Autor: Natalia Lyubova, Marc Moreaux, Frédéric Lerasle, Isabelle Ferrané

Publikováno v: Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications-Volume 4: VISAPP
13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 208)
13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 208), Jan 2018, Funchal, Portugal. pp.307-314, ⟨10.5220/0006548303070314⟩
13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Jan 2018, Funchal, Portugal
VISIGRAPP (4: VISAPP)

International audience; This work addresses the issue of image classification and localization of human actions based on visual data acquired from RGB sensors. Our approach is inspired by the success of deep learning in image classification. In this

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b89b605d97c27b6804f52977848be08
https://hal.laas.fr/hal-01763103/document

Zobrazit plný text záznamu

From passive to interactive object learning and recognition through self-identification on a humanoid robot

Autor: Natalia Lyubova, Serena Ivaldi, David Filliat

Publikováno v: Autonomous Robots
Autonomous Robots, Springer Verlag, 2015, pp.23. ⟨10.1007/s10514-015-9445-0⟩
Autonomous Robots, 2015, pp.23. ⟨10.1007/s10514-015-9445-0⟩

International audience; Service robots, working in evolving human environments , need the ability to continuously learn to recognize new objects. Ideally, they should act as humans do, by observing their environment and interacting with objects, with

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ce7d98215773c91c0c2d96f9c5ffa8e
https://hal.archives-ouvertes.fr/hal-01166110

Zobrazit plný text záznamu

Improving object learning through manipulation and robot self-identification

Autor: Natalia Lyubova, Serena Ivaldi, David Filliat

Publikováno v: IEEE International Conference on Robotics and Biomimetics (ROBIO)
IEEE International Conference on Robotics and Biomimetics (ROBIO), Dec 2013, Shenzen, China. ⟨10.1109/ROBIO.2013.6739655⟩
ROBIO

International audience; We present a developmental approach that allows a humanoid robot to continuously and incrementally learn entities through interaction with a human partner in a first stage before categorizing these entities into objects, human

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0dc7fbadd8cd91e55195f1133e117fd
https://hal.science/hal-00919649/document

Zobrazit plný text záznamu

Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot

Autor: Natalia Lyubova, Serena Ivaldi, Pierre-Yves Oudeyer, Sao Mai Nguyen, Vincent Padois, Olivier Sigaud, Alain Droniou, David Filliat, Damien Gerardeaux-Viret

Publikováno v: Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB)
Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Aug 2013, Osaka, Japan. pp.1--8, ⟨10.1109/DevLrn.2013.6652525⟩
ICDL-EPIROB

International audience; In this paper we address the problem of learning to recognize objects by manipulation in a developmental robotics scenario. In a life-long learning perspective, a humanoid robot should be capable of improving its knowledge of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15b656b0ad3abc43e2b02884035e2fdf
https://hal.archives-ouvertes.fr/hal-00919674/document

Zobrazit plný text záznamu

IEEE International Conference on Development and Learning and on Epigenetic Robotics

Autor: Sao Mai Nguyen, Serena Ivaldi, Natalia Lyubova, Alain Droniou, Damien Gerardeaux-Viret, David Filliat, Vincent Padois, Olivier Sigaud, Pierre-Yves Oudeyer

Publikováno v: Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=erc_________::1b9ecd241eebc0740fcc2442de185270

Zobrazit plný text záznamu

Object learning through active exploration

Autor: Vincent Padois, Pierre-Yves Oudeyer, Sao Mai Nguyen, David Filliat, Natalia Lyubova, Serena Ivaldi, Alain Droniou, Olivier Sigaud

Publikováno v: IEEE Transactions on Autonomous Mental Development
IEEE Transactions on Autonomous Mental Development, IEEE, 2013, pp.1-18. ⟨10.1109/TAMD.2013.2280614⟩
IEEE Transactions on Autonomous Mental Development, 2013, pp.1-18. ⟨10.1109/TAMD.2013.2280614⟩

International audience; This paper addresses the problem of active object learning by a humanoid child-like robot, using a developmental approach. We propose a cognitive architecture where the visual representation of the objects is built incremental

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb4bfb1e02f75430a0e867f8ff89db64
https://hal.archives-ouvertes.fr/hal-00919694/document

Zobrazit plný text záznamu

Perception and human interaction for developmental learning of objects and affordances

Autor: Salvatore Maria Anzalone, David Filliat, Alain Droniou, Damien Gerardeaux-Viret, Mohamed Chetouani, Natalia Lyubova, Serena Ivaldi, Olivier Sigaud

Publikováno v: Humanoids
Proc. of the 12th IEEE-RAS International Conference on Humanoid Robots-HUMANOIDS
Proc. of the 12th IEEE-RAS International Conference on Humanoid Robots-HUMANOIDS, Nov 2012, Santa Monica, United States. ⟨10.1109/HUMANOIDS.2012.6651528⟩

International audience; In this paper we describe a cognitive architecture for humanoids interacting with objects and caregivers in a developmental robotics scenario. The architecture is foundational to the MACSi project: it is designed to support ex

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9b94706cdbb1b9f7c479dd8ae3f0d421
https://doi.org/10.1109/humanoids.2012.6651528

Zobrazit plný text záznamu

Developmental Approach for Interactive Object Discovery

Autor: Natalia Lyubova, David Filliat

Publikováno v: Proceedings of the 2012 IJCNN International Joint Conference on Neural Networks
Neural Networks (IJCNN), The 2012 International Joint Conference on
Neural Networks (IJCNN), The 2012 International Joint Conference on, Jun 2012, Australia. pp.1-7, ⟨10.1109/IJCNN.2012.6252606⟩
IJCNN

International audience; We present a visual system for a humanoid robot that supports an efﬁcient online learning and recognition of various elements of the environment. Taking inspiration from child's perception and following the principles of dev

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::403fc24876672df73e0fd1aae46c11e6
https://hal.science/hal-00755298/document

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání