Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Yu, Wanming"'
Autor:
Atanassov, Vassil, Yu, Wanming, Mitchell, Alexander Luis, Finean, Mark Nicholas, Havoutis, Ioannis
Representation learning and unsupervised skill discovery can allow robots to acquire diverse and reusable behaviors without the need for task-specific rewards. In this work, we use unsupervised reinforcement learning to learn a latent representation
Externí odkaz:
http://arxiv.org/abs/2410.07877
Autor:
Mao, Xiaofeng, Xu, Yucheng, Wen, Ruoshi, Kasaei, Mohammadreza, Yu, Wanming, Psomopoulou, Efi, Lepora, Nathan F., Li, Zhibin
Imitation learning for robot dexterous manipulation, especially with a real robot setup, typically requires a large number of demonstrations. In this paper, we present a data-efficient learning from demonstration framework which exploits the use of r
Externí odkaz:
http://arxiv.org/abs/2307.04619
Autor:
Yu, Wanming, Yang, Chuanyu, McGreavy, Christopher, Triantafyllidis, Eleftherios, Bellegarda, Guillaume, Shafiee, Milad, Ijspeert, Auke Jan, Li, Zhibin
Robot motor skills can be learned through deep reinforcement learning (DRL) by neural networks as state-action mappings. While the selection of state observations is crucial, there has been a lack of quantitative analysis to date. Here, we present a
Externí odkaz:
http://arxiv.org/abs/2306.17101
For model-free deep reinforcement learning of quadruped locomotion, the initialization of robot configurations is crucial for data efficiency and robustness. This work focuses on algorithmic improvements of data efficiency and robustness simultaneous
Externí odkaz:
http://arxiv.org/abs/2109.11191
Publikováno v:
Science Robotics, Vol. 5, Issue 49, eabb2174 (2020)
Achieving versatile robot locomotion requires motor skills which can adapt to previously unseen situations. We propose a Multi-Expert Learning Architecture (MELA) that learns to generate adaptive skills from a group of representative expert skills. D
Externí odkaz:
http://arxiv.org/abs/2012.05810
Autor:
Mao, Xiaofeng, Xu, Yucheng, Wen, Ruoshi, Kasaei, Mohammadreza, Yu, Wanming, Psomopoulou, Efi, Lepora, Nathan F., Li, Zhibin
This work develops a data-efficient learning from demonstration framework which exploits the use of rich tactile sensing and achieves fine dexterous bimanual manipulation. Specifically, we formulated a convolutional autoencoder network that can effec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::233a593cfe3651b0e680ced2468ab405
Publikováno v:
2018 3rd International Conference on Robotics and Automation Engineering (ICRAE).
In fixed-wing UAV close formation flight adopting the leader-follower configuration, the follower dynamics is affected by the leader-induced trailing vortex effect. This paper considers the trailing vortex effect as external disturbances, and propose
Publikováno v:
Optics and Lasers in Engineering. 40:189-200
Combining color imaging with phase shifting, a technique named five-step color phase shifting is presented to determine the whole-field isoclinic parameter. Relevant theory is derived and explicit conditions for directly determining the isoclinic par
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.