While it is generally acknowledged that force feedback is beneficial to
...
Robotic pick and place tasks are symmetric under translations and rotati...
Real-world grasp detection is challenging due to the stochasticity in gr...
Although equivariant machine learning has proven effective at many tasks...
Predicting the pose of objects from a single image is an important but
d...
Extensive work has demonstrated that equivariant neural networks can
sig...
Grasp learning has become an exciting and important topic in robotics. J...
Reinforcement learning in partially observable domains is challenging du...
In robotic manipulation, acquiring samples is extremely expensive becaus...
Given point cloud input, the problem of 6-DoF grasp pose detection is to...
Multi-goal policy learning for robotic manipulation is challenging. Prio...
Reasoning about 3D objects based on 2D images is challenging due to larg...
Model-free policy learning has been shown to be capable of learning
mani...
Real-world reinforcement learning tasks often involve some form of parti...
We present BulletArm, a novel benchmark and learning-environment for rob...
Grasp detection of novel objects in unstructured environments is a key
c...
The framework of mixed observable Markov decision processes (MOMDP) mode...
Object pose estimation methods allow finding locations of objects in
uns...
Recently, equivariant neural network models have been shown to be useful...
Equivariant neural networks enforce symmetry within the structure of the...
In planar grasp detection, the goal is to learn a function from an image...
Transporter Net is a recently proposed framework for pick and place that...
Shape completion, the problem of inferring the complete geometry of an o...
We consider the problem of selecting confounders for adjustment from a
p...
Recently, a variety of new equivariant neural network model architecture...
In robotics, it is often not possible to learn useful policies using pur...
Localizing and tracking the pose of robotic grippers are necessary skill...
Many important robotics problems are partially observable in the sense t...
In this paper we consider joint perception and control of a pick-place
s...
In the spatial action representation, the action space spans the space o...
Learning control policies for visual servoing in novel environments is a...
Abstraction is crucial for effective sequential decision making in domai...
Learning generalizable skills in robotic manipulation has long been
chal...
Abstraction of Markov Decision Processes is a useful tool for solving co...
Tasks in outdoor open world environments are now ripe for automation wit...
Many people with motor disabilities struggle with activities of daily li...
This paper proposes an approach to domain transfer based on a pairwise l...
In applications of deep reinforcement learning to robotics, it is often ...
We address a class of manipulation problems where the robot perceives th...
Reinforcement Learning (RL) algorithms can suffer from poor sample effic...
We present a novel approach to hierarchical reinforcement learning calle...
We want to build robots that are useful in unstructured real world
appli...