Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Anahita Mohseni-Kabir"'
Publikováno v:
IEEE Robotics and Automation Letters. 6:5873-5880
We focus on long-sighted planning for a class of problems with multiple independent tasks that are partially observable and evolve over time. An example problem that falls into this class is a robot waiting multiple tables, referred to as tasks, in a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::67b53e71619ed0c520b4431071031dbf
https://doi.org/10.1109/lra.2021.3086426
https://doi.org/10.1109/lra.2021.3086426
Autor:
Javier Cámara, Joydeep Biswas, Christian Kaestner, Arjun Guha, Jarrett Holtz, Jonathan Aldrich, Manuela Veloso, David Garlan, Anahita Mohseni-Kabir, Claire Le Goues, Bradley Schmerl, Ian Voysey, Selva Samuel, Ivan Ruchkin, Christopher Steven Timperley, Pooyan Jamshidi
Publikováno v:
IEEE Software. 36:83-90
We developed model-based adaptation, an approach that leverages models of software and its environment to enable automated adaptation. The goal of our approach is to build long-lasting software systems that can effectively adapt to changes in their e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::01f04f395865ad8ee85ad6a481375b04
https://doi.org/10.1109/ms.2018.2885058
https://doi.org/10.1109/ms.2018.2885058
Autor:
Candace L. Sidner, Anahita Mohseni-Kabir, Benjamin Hylak, Charles Rich, Sonia Chernova, Dmitry Berenson, Daniel Miller, Victoria Wu, Changshuo Li
Publikováno v:
Autonomous Robots. 43:859-874
We present a new interaction paradigm for robot learning from demonstration, called simultaneous learning of hierarchy and primitives (SLHAP), in which information about hierarchy and primitives is naturally interleaved in a single, coherent demonstr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03d07315ae8fd7d01d0e66b62295a998
https://doi.org/10.1007/s10514-018-9749-y
https://doi.org/10.1007/s10514-018-9749-y
Publikováno v:
ICRA
In a multi-agent setting, the optimal policy of a single agent is largely dependent on the behavior of other agents. We investigate the problem of multi-agent reinforcement learning, focusing on decentralized learning in non-stationary domains for mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::48a4712f2fa092a786f252f6cca85f1f
http://arxiv.org/abs/1909.12925
http://arxiv.org/abs/1909.12925
Publikováno v:
Big Data. 4:217-235
This work seeks to leverage semantic networks containing millions of entries encoding assertions of commonsense knowledge to enable improvements in robot task execution and learning. The specific application we explore in this project is object subst
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6774a853b5e822fe23177d0732ad932
https://doi.org/10.1089/big.2016.0038
https://doi.org/10.1089/big.2016.0038
Autor:
Anahita Mohseni-Kabir, Manuela Veloso
Publikováno v:
IJCAI
While mobile robots reliably perform each service task by accurately localizing and safely navigating avoiding obstacles, they do not respond in any other way to their surroundings. We can make the robots more responsive to their environment by equip
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6120c5e7ae8f9fc387d8f28c7dbb067a
https://doi.org/10.24963/ijcai.2018/686
https://doi.org/10.24963/ijcai.2018/686
Autor:
Candace L. Sidner, Victoria Wu, Changshuo Li, Charles Rich, Benjamin Hylak, Dmitry Berenson, Daniel Miller, Sonia Chernova, Anahita Mohseni-Kabir
Publikováno v:
HRI (Companion)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a2c40506e428c7728cbf929cd4429d9
https://doi.org/10.1145/3029798.3036641
https://doi.org/10.1145/3029798.3036641
Publikováno v:
RO-MAN
We present a novel algorithm to identify reusable motion trajectories corresponding to the primitive actions in a human demonstration of a symbolic plan with accompanying narration. Our approach involves a multi-step process starting with time-series
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b407d2deae5f89f408802ac3b332ff16
https://doi.org/10.1109/roman.2016.7745141
https://doi.org/10.1109/roman.2016.7745141
Publikováno v:
2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9103c72ab0ef24c42024fe0f90c7bc13
https://doi.org/10.1109/hri.2016.7451815
https://doi.org/10.1109/hri.2016.7451815
Publikováno v:
HRI
We have developed learning and interaction algorithms to support a human teaching hierarchical task models to a robot using a single demonstration in the context of a mixedinitiative interaction with bi-directional communication. In particular, we ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87cd49b43e6bcbd410b6aa2be2491569
https://doi.org/10.1145/2696454.2696474
https://doi.org/10.1145/2696454.2696474