Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Englert, Péter"'
Autor:
Liu, I-Chun Arthur, Uppal, Shagun, Sukhatme, Gaurav S., Lim, Joseph J., Englert, Peter, Lee, Youngwoon
Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations. Prior work tackles the exploration problem by integratin
Externí odkaz:
http://arxiv.org/abs/2111.06383
In this work we propose Pathfinder Discovery Networks (PDNs), a method for jointly learning a message passing graph over a multiplex network with a downstream semi-supervised model. PDNs inductively learn an aggregated weight for each edge, optimized
Externí odkaz:
http://arxiv.org/abs/2010.12878
Autor:
Yamada, Jun, Lee, Youngwoon, Salhotra, Gautam, Pertsch, Karl, Pflueger, Max, Sukhatme, Gaurav S., Lim, Joseph J., Englert, Peter
Deep reinforcement learning (RL) agents are able to learn contact-rich manipulation tasks by maximizing a reward signal, but require large amounts of experience, especially in environments with many obstacles that complicate exploration. In contrast,
Externí odkaz:
http://arxiv.org/abs/2010.11940
Autor:
Sutanto, Giovanni, Fernández, Isabel M. Rayas, Englert, Peter, Ramachandran, Ragesh K., Sukhatme, Gaurav S.
Constrained robot motion planning is a widely used technique to solve complex robot tasks. We consider the problem of learning representations of constraints from demonstrations with a deep neural network, which we call Equality Constraint Manifold N
Externí odkaz:
http://arxiv.org/abs/2009.11852
Autor:
Fernández, Isabel M. Rayas, Sutanto, Giovanni, Englert, Peter, Ramachandran, Ragesh K., Sukhatme, Gaurav S.
Motion planning with constraints is an important part of many real-world robotic systems. In this work, we study manifold learning methods to learn such constraints from data. We explore two methods for learning implicit constraint manifolds from dat
Externí odkaz:
http://arxiv.org/abs/2006.07746
We address the problem of planning robot motions in constrained configuration spaces where the constraints change throughout the motion. The problem is formulated as a fixed sequence of intersecting manifolds, which the robot needs to traverse in ord
Externí odkaz:
http://arxiv.org/abs/2006.02027
Autor:
Englert, Peter, Toussaint, Marc
The transfer of a robot skill between different geometric environments is non-trivial since a wide variety of environments exists, sensor observations as well as robot motions are high-dimensional, and the environment might only be partially observed
Externí odkaz:
http://arxiv.org/abs/1803.01777
Successful human-robot cooperation hinges on each agent's ability to process and exchange information about the shared environment and the task at hand. Human communication is primarily based on symbolic abstractions of object properties, rather than
Externí odkaz:
http://arxiv.org/abs/1701.06450
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for continuou
Externí odkaz:
http://arxiv.org/abs/1307.0813