Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Leitner, Jürgen"'
Autor:
Newbury, Rhys, Gu, Morris, Chumbley, Lachlan, Mousavian, Arsalan, Eppner, Clemens, Leitner, Jürgen, Bohg, Jeannette, Morales, Antonio, Asfour, Tamim, Kragic, Danica, Fox, Dieter, Cosgun, Akansel
Grasping is the process of picking up an object by applying forces and torques at a set of contacts. Recent advances in deep-learning methods have allowed rapid progress in robotic object grasping. In this systematic review, we surveyed the publicati
Externí odkaz:
http://arxiv.org/abs/2207.02556
We propose a novel iterative approach for crossing the reality gap that utilises live robot rollouts and differentiable physics. Our method, RealityGrad, demonstrates for the first time, an efficient sim2real transfer in combination with a real2sim m
Externí odkaz:
http://arxiv.org/abs/2109.04674
EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation
We present the Evolved Grasping Analysis Dataset (EGAD), comprising over 2000 generated objects aimed at training and evaluating robotic visual grasp detection algorithms. The objects in EGAD are geometrically diverse, filling a space ranging from si
Externí odkaz:
http://arxiv.org/abs/2003.01314
Deep reinforcement learning has been shown to solve challenging tasks where large amounts of training experience is available, usually obtained online while learning the task. Robotics is a significant potential application domain for many of these a
Externí odkaz:
http://arxiv.org/abs/1911.08666
We present a benchmark to facilitate simulated manipulation; an attempt to overcome the obstacles of physical benchmarks through the distribution of a real world, ground truth dataset. Users are given various simulated manipulation tasks with assigne
Externí odkaz:
http://arxiv.org/abs/1911.01557
This contribution comprises the interplay between a multi-modal variational autoencoder and an environment to a perceived environment, on which an agent can act. Furthermore, we conclude our work with a comparison to curiosity-driven learning.
C
C
Externí odkaz:
http://arxiv.org/abs/1911.00584
When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world control tasks such as robotics. In
Externí odkaz:
http://arxiv.org/abs/1910.03732
We quantify the accuracy of various simulators compared to a real world robotic reaching and interaction task. Simulators are used in robotics to design solutions for real world hardware without the need for physical access. The `reality gap' prevent
Externí odkaz:
http://arxiv.org/abs/1811.01484
Camera viewpoint selection is an important aspect of visual grasp detection, especially in clutter where many occlusions are present. Where other approaches use a static camera position or fixed data collection routines, our Multi-View Picking (MVP)
Externí odkaz:
http://arxiv.org/abs/1809.08564
Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating prior knowl
Externí odkaz:
http://arxiv.org/abs/1809.07480