Výsledky vyhledávání - "Igor Kalevatykh"

Differentiable simulation for physical system identification

Autor: Igor Kalevatykh, Cordelia Schmid, Quentin Le Lidec, Justin Carpentier, Ivan Laptev

Publikováno v: IEEE Robotics and Automation Letters
IEEE Robotics and Automation Letters, IEEE 2021, 6 (2), pp.3413-3420. ⟨10.1109/LRA.2021.3062323⟩
IEEE Robotics and Automation Letters, IEEE 2021
IEEE Robotics and Automation Letters, 2021, 6 (2), pp.3413-3420. ⟨10.1109/LRA.2021.3062323⟩

International audience; Simulating frictional contacts remains a challenging research topic in robotics. Recently, differentiable physics emerged and has proven to be a key element in modelbased Reinforcement Learning (RL) and optimal control fields.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1db7ba3c45ccf283a7746907328d14eb
https://hal.archives-ouvertes.fr/hal-03025616

Zobrazit plný text záznamu

Learning visual policies for building 3D shape categories

Autor: Cordelia Schmid, Igor Kalevatykh, Ivan Laptev, Alexander Pashevich

Publikováno v: IROS 2020-International Conference on Intelligent Robots and Systems
IROS 2020-International Conference on Intelligent Robots and Systems, Oct 2020, Las Vegas, United States
IROS

Manipulation and assembly tasks require non-trivial planning of actions depending on the environment and the final goal. Previous work in this domain often assembles particular instances of objects from known sets of primitives. In contrast, we aim t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c550b7168c0522398f91b2100131b50
https://hal.archives-ouvertes.fr/hal-02945024

Zobrazit plný text záznamu

Learning to combine primitive skills: A step towards versatile robotic manipulation

Autor: Alexander Pashevich, Cordelia Schmid, Robin Strudel, Josef Sivic, Igor Kalevatykh, Ivan Laptev

Publikováno v: ICRA 2020-IEEE International Conference on Robotics and Automation
ICRA 2020-IEEE International Conference on Robotics and Automation, May 2020, Paris / Virtuel, France. ⟨10.1109/ICRA40945.2020.9196619⟩
ICRA

Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. Traditional task and motion planning (TAMP) methods can solve complex tasks but require full state observability and are not adapte

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51d17447cfd4831aa3b013b88529612f
https://hal.archives-ouvertes.fr/hal-02274969

Zobrazit plný text záznamu

Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning

Autor: Josef Sivic, Justin Carpentier, Ivan Laptev, Igor Kalevatykh, Yann Labbé, Mathieu Aubry, Sergey Zagoruyko

Publikováno v: IEEE Robotics and Automation Letters
IEEE Robotics and Automation Letters, IEEE 2020, 5 (2), pp.3715-3722. ⟨10.1109/LRA.2020.2980984⟩
IEEE Robotics and Automation Letters, 2020, 5 (2), pp.3715-3722. ⟨10.1109/LRA.2020.2980984⟩

We address the problem of visually guided rearrangement planning with many movable objects, i.e., finding a sequence of actions to move a set of objects from an initial arrangement to a desired one, while relying on visual inputs coming from an RGB c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4fd53168add245b11f224b59d59f3e8c
https://hal.archives-ouvertes.fr/hal-02108930

Zobrazit plný text záznamu

Learning to Augment Synthetic Images for Sim2Real Policy Transfer

Autor: Ivan Laptev, Alexander Pashevich, Robin Strudel, Cordelia Schmid, Igor Kalevatykh

Publikováno v: IROS 2019-IEEE/RSJ International Conference on Intelligent Robots and Systems
IROS 2019-IEEE/RSJ International Conference on Intelligent Robots and Systems, Nov 2019, Macao, China. pp.2651-2657, ⟨10.1109/IROS40897.2019.8967622⟩
IROS

Vision and learning have made significant progress that could improve robotics policies for complex tasks and environments. Learning deep neural networks for image understanding, however, requires large amounts of domain-specific visual data. While c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7186cb6936f10c35f92d4e5a5c32ff55
https://hal.archives-ouvertes.fr/hal-02273326

Zobrazit plný text záznamu

Learning joint reconstruction of hands and manipulated objects

Autor: Michael J. Black, Yana Hasson, Igor Kalevatykh, Ivan Laptev, Cordelia Schmid, Gül Varol, Dimitrios Tzionas

Publikováno v: CVPR 2019-IEEE Conference on Computer Vision and Pattern Recognition
CVPR 2019-IEEE Conference on Computer Vision and Pattern Recognition, Jun 2019, Long Beach, United States. pp.11799-11808, ⟨10.1109/CVPR.2019.01208⟩
CVPR

Estimating hand-object manipulations is essential for interpreting and imitating human actions. Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation. Yet, reconstructing hands and objects dur

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d4ca488093e36e5af56ff821bca594b
https://hal.science/hal-02429093/file/hassonCVPR2019.pdf

Zobrazit plný text záznamu

Distance robotics learning using Hybrid Simulating Testbed

Autor: Alexey Leskov, Vladimir Illarionov, Igor Kalevatykh, Svyatoslav Moroshkin, Alexander Zimin

Publikováno v: 2014 11th International Conference on Remote Engineering and Virtual Instrumentation (REV).

The authors examined the issues of building and educational use of Hybrid Simulating Testbed (HST) for robotic manipulator (RM). HST is based on the hybrid RM models, including computer models and physical RM models based on the serial industrial rob

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::8ee32ee78d120bd423634079fea7f1e9
https://doi.org/10.1109/rev.2014.6784261

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání