How to train your robot with deep reinforcement learning: lessons we have learned
Deep reinforcement learning (RL) has emerged as a promising approach for autonomously
acquiring complex behaviors from low-level sensor observations. Although a large portion of …
acquiring complex behaviors from low-level sensor observations. Although a large portion of …
A review of physics simulators for robotic applications
The use of simulators in robotics research is widespread, underpinning the majority of recent
advances in the field. There are now more options available to researchers than ever before …
advances in the field. There are now more options available to researchers than ever before …
Navigating to objects in the real world
Semantic navigation is necessary to deploy mobile robots in uncontrolled environments
such as homes or hospitals. Many learning-based approaches have been proposed in …
such as homes or hospitals. Many learning-based approaches have been proposed in …
A survey on learning-based robotic gras**
Abstract Purpose of Review This review provides a comprehensive overview of machine
learning approaches for vision-based robotic gras** and manipulation. Current trends and …
learning approaches for vision-based robotic gras** and manipulation. Current trends and …
Scalable deep reinforcement learning for vision-based robotic manipulation
In this paper, we study the problem of learning vision-based dynamic manipulation skills
using a scalable reinforcement learning approach. We study this problem in the context of …
using a scalable reinforcement learning approach. We study this problem in the context of …
Rlbench: The robot learning benchmark & learning environment
S James, Z Ma, DR Arrojo… - IEEE Robotics and …, 2020 - ieeexplore.ieee.org
We present a challenging new benchmark and learning-environment for robot learning:
RLBench. The benchmark features 100 completely unique, hand-designed tasks, ranging in …
RLBench. The benchmark features 100 completely unique, hand-designed tasks, ranging in …
Learning ambidextrous robot gras** policies
Universal picking (UP), or reliable robot gras** of a diverse range of novel objects from
heaps, is a grand challenge for e-commerce order fulfillment, manufacturing, inspection, and …
heaps, is a grand challenge for e-commerce order fulfillment, manufacturing, inspection, and …
Sim-to-real via sim-to-sim: Data-efficient robotic gras** via randomized-to-canonical adaptation networks
Real world data, especially in the domain of robotics, is notoriously costly to collect. One way
to circumvent this can be to leverage the power of simulation to produce large amounts of …
to circumvent this can be to leverage the power of simulation to produce large amounts of …
Learning robust, real-time, reactive robotic gras**
We present a novel approach to perform object-independent grasp synthesis from depth
images via deep neural networks. Our generative gras** convolutional neural network …
images via deep neural networks. Our generative gras** convolutional neural network …
Tossingbot: Learning to throw arbitrary objects with residual physics
We investigate whether a robot arm can learn to pick and throw arbitrary rigid objects into
selected boxes quickly and accurately. Throwing has the potential to increase the physical …
selected boxes quickly and accurately. Throwing has the potential to increase the physical …