Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Ali Ghadirzadeh"'
Publikováno v:
Buildings, Vol 14, Iss 7, p 1985 (2024)
Historical buildings account for a significant portion of the energy use of today’s building stock, and there are usually limited energy saving measures that can be applied due to antiquarian and esthetic restrictions. The purpose of this case stud
Externí odkaz:
https://doaj.org/article/8bff1b99521c484fb95da00a17d1a5fa
Autor:
Artur Czeszumski, Anna L. Gert, Ashima Keshava, Ali Ghadirzadeh, Tilman Kalthoff, Benedikt V. Ehinger, Max Tiessen, Mårten Björkman, Danica Kragic, Peter König
Publikováno v:
Frontiers in Neurorobotics, Vol 15 (2021)
Robots start to play a role in our social landscape, and they are progressively becoming responsive, both physically and socially. It begs the question of how humans react to and interact with robots in a coordinated manner and what the neural underp
Externí odkaz:
https://doaj.org/article/6679184c13d04d8f80c35509e89e8f8e
Publikováno v:
Frontiers in Robotics and AI, Vol 7 (2020)
To coordinate actions with an interaction partner requires a constant exchange of sensorimotor signals. Humans acquire these skills in infancy and early childhood mostly by imitation learning and active engagement with a skilled partner. They require
Externí odkaz:
https://doaj.org/article/0519447e36f642c991991c06d67bccfb
Publikováno v:
Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca91f1df6181999bc6960548a4387564
https://doi.org/10.5220/0011658100003417
https://doi.org/10.5220/0011658100003417
Autor:
Gabriel Skantze, Yuan Gao, Pian Yu, Agnes Axelsson, Danica Kragic, Ginevra Castellano, Sofie Ahlberg, Wenceslao Shaw Cortez, Ali Ghadirzadeh, Dimos V. Dimarogonas
Publikováno v:
Unmanned Systems. 10:187-203
The work presented here is a culmination of developments within the Swedish project COIN: Co-adaptive human-robot interactive systems, funded by the Swedish Foundation for Strategic Research (SSF), which addresses a unified framework for co-adaptive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::27dbfef83524e7ad6c866f8f1655f4ae
https://doi.org/10.1142/s230138502250011x
https://doi.org/10.1142/s230138502250011x
Autor:
Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman
Publikováno v:
Aalto University
We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. The framework, called GenRL, trains deep policies by introducin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cad459fefe80b4386ab9ca8f4d33013a
https://aaltodoc.aalto.fi/handle/123456789/116104
https://aaltodoc.aalto.fi/handle/123456789/116104
Autor:
Artur Czeszumski, Anna L. Gert, Ashima Keshava, Ali Ghadirzadeh, Tilman Kalthoff, Benedikt V. Ehinger, Max Tiessen, Mårten Björkman, Danica Kragic, Peter König
Robots start to play a role in our social landscape, and they are progressively becoming responsive, both physically and socially. It begs the question of how humans react to and interact with robots in a coordinated manner and what the neural underp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eaba97c6be99ea9d2330a4a3a625c21c
https://doi.org/10.1101/2021.03.26.437133
https://doi.org/10.1101/2021.03.26.437133
Publisher Copyright: IEEE Copyright: Copyright 2021 Elsevier B.V., All rights reserved. Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a671b5868eb271d5d9486152e7cce91
http://arxiv.org/abs/2010.08397
http://arxiv.org/abs/2010.08397
We present a reinforcement learning based framework for human-centered collaborative systems. The framework is proactive and balances the benefits of timely actions with the risk of taking improper actions by minimizing the total time spent to comple
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::da2e313aaca9553bc316f8eba33e00e8
http://arxiv.org/abs/2007.01009
http://arxiv.org/abs/2007.01009
Publikováno v:
ICRA
Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff8625b8e76d7c1e3767fff467c94c99
https://doi.org/10.1109/icra40945.2020.9197505
https://doi.org/10.1109/icra40945.2020.9197505