Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Juan Camilo Gamboa"'
We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only. Our approach decouples reward modelling from policy learning, unlike state-of-the-art adversarial methods which require updating the reward model du
Externí odkaz:
http://arxiv.org/abs/2205.09251
Autor:
Manderson, Travis, Higuera, Juan Camilo Gamboa, Wapnick, Stefan, Tremblay, Jean-François, Shkurti, Florian, Meger, David, Dudek, Gregory
We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided by a user w
Externí odkaz:
http://arxiv.org/abs/2006.16235
Autor:
Koreitem, Karim, Shkurti, Florian, Manderson, Travis, Chang, Wei-Di, Higuera, Juan Camilo Gamboa, Dudek, Gregory
We consider the task of underwater robot navigation for the purpose of collecting scientifically relevant video data for environmental monitoring. The majority of field robots that currently perform monitoring tasks in unstructured natural environmen
Externí odkaz:
http://arxiv.org/abs/2003.10010
Autor:
Jiang, Wei, Higuera, Juan Camilo Gamboa, Angles, Baptiste, Sun, Weiwei, Javan, Mehrsan, Yi, Kwang Moo
We propose an optimization-based framework to register sports field templates onto broadcast videos. For accurate registration we go beyond the prevalent feed-forward paradigm. Instead, we propose to train a deep network that regresses the registrati
Externí odkaz:
http://arxiv.org/abs/1909.08034
Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on th
Externí odkaz:
http://arxiv.org/abs/1906.00410
Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from demonstrations in various conditions can mitigate---but not completely
Externí odkaz:
http://arxiv.org/abs/1903.05697
We present an algorithm for rapidly learning controllers for robotics systems. The algorithm follows the model-based reinforcement learning paradigm, and improves upon existing algorithms; namely Probabilistic learning in Control (PILCO) and a sample
Externí odkaz:
http://arxiv.org/abs/1803.02291
Autor:
Shkurti, Florian, Chang, Wei-Di, Henderson, Peter, Islam, Md Jahidul, Higuera, Juan Camilo Gamboa, Li, Jimmy, Manderson, Travis, Xu, Anqi, Dudek, Gregory, Sattar, Junaed
We present a robust multi-robot convoying approach that relies on visual detection of the leading agent, thus enabling target following in unstructured 3-D environments. Our method is based on the idea of tracking-by-detection, which interleaves effi
Externí odkaz:
http://arxiv.org/abs/1709.08292
Autor:
Feng Shi, Paul Marchwica, Juan Camilo Gamboa Higuera, Mike Jamieson, Mehrsan Javan, Parthipan Siva
Publikováno v:
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36bd58ac768f3983ed3ec8a73b7db206
https://doi.org/10.1109/wacv51458.2022.00382
https://doi.org/10.1109/wacv51458.2022.00382
Autor:
Ken Goldberg, Ankur Handa, Christopher G. Atkeson, Sebastian Höfer, Shuran Song, Martha White, Melissa Mozifian, Dieter Fox, Juan Camilo Gamboa, Florian Golemo, John J. Leonard, Kostas E. Bekris, C. Karen Liu, Jan Peters, Peter Welinder
Publikováno v:
IEEE Transactions on Automation Science and Engineering. 18:398-400
To Perform reliably and consistently over sustained periods of time, large-scale automation critically relies on computer simulation. Simulation allows us and supervisory AI to effectively design, validate, and continuously improve complex processes,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::663ebe92835cb2c0f8849d6f5e090f0f
https://doi.org/10.1109/tase.2021.3064065
https://doi.org/10.1109/tase.2021.3064065