Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Kojcev, Risto"'
Autor:
Nuin, Yue Leire Erro, Lopez, Nestor Gonzalez, Moral, Elias Barba, Juan, Lander Usategui San, Rueda, Alejandro Solano, Vilches, Víctor Mayoral, Kojcev, Risto
We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics to train a robot directly from joint states, using traditional robotic tools. We use an state-of-the-art implementation of the Proximal Policy Optimization, Trust
Externí odkaz:
http://arxiv.org/abs/1903.06282
Autor:
Lopez, Nestor Gonzalez, Nuin, Yue Leire Erro, Moral, Elias Barba, Juan, Lander Usategui San, Rueda, Alejandro Solano, Vilches, Víctor Mayoral, Kojcev, Risto
This paper presents an upgraded, real world application oriented version of gym-gazebo, the Robot Operating System (ROS) and Gazebo based Reinforcement Learning (RL) toolkit, which complies with OpenAI Gym. The content discusses the new ROS 2 based s
Externí odkaz:
http://arxiv.org/abs/1903.06278
Autor:
Vilches, Víctor Mayoral, Cordero, Alejandro Hernández, Calvo, Asier Bilbao, Ugarte, Irati Zamalloa, Kojcev, Risto
Rather than programming, training allows robots to achieve behaviors that generalize better and are capable to respond to real-world needs. However, such training requires a big amount of experimentation which is not always feasible for a physical ro
Externí odkaz:
http://arxiv.org/abs/1808.10369
We argue that hierarchical methods can become the key for modular robots achieving reconfigurability. We present a hierarchical approach for modular robots that allows a robot to simultaneously learn multiple tasks. Our evaluation results present an
Externí odkaz:
http://arxiv.org/abs/1802.04132
We argue that hardware modularity plays a key role in the convergence of Robotics and Artificial Intelligence (AI). We introduce a new approach for building robots that leads to more adaptable and capable machines. We present the concept of a self-ad
Externí odkaz:
http://arxiv.org/abs/1802.04082
We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics using traditional robotic tools that extend state-of-the-art DRL implementations and provide an end-to-end approach which trains a robot directly from joint states
Externí odkaz:
http://arxiv.org/abs/1802.02395
Today's landscape of robotics is dominated by vertical integration where single vendors develop the final product leading to slow progress, expensive products and customer lock-in. Opposite to this, an horizontal integration would result in a rapid d
Externí odkaz:
http://arxiv.org/abs/1802.01459
Autor:
Zamalloa, Irati, Kojcev, Risto, Hernández, Alejandro, Muguruza, Iñigo, Usategui, Lander, Bilbao, Asier, Mayoral, Víctor
Robotics is called to be the next technological revolution and estimations indicate that it will trigger the fourth industrial revolution. This article presents a review of some of the most relevant milestones that occurred in robotics over the last
Externí odkaz:
http://arxiv.org/abs/1704.08617
Publikováno v:
PLoS ONE. 2/25/2016, Vol. 11 Issue 2, p1-16. 16p.
Autor:
Vilches, V��ctor Mayoral, Cordero, Alejandro Hern��ndez, Calvo, Asier Bilbao, Ugarte, Irati Zamalloa, Kojcev, Risto
Rather than programming, training allows robots to achieve behaviors that generalize better and are capable to respond to real-world needs. However, such training requires a big amount of experimentation which is not always feasible for a physical ro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42ebca1585d28292525666ea7f96e6c7
http://arxiv.org/abs/1808.10369
http://arxiv.org/abs/1808.10369