Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection

TL;DR: This survey will cover central algorithms in deep RL, including the deep Q-network (DQN), trust region policy optimization (TRPO), and asynchronous advantage actor critic, and highlight the unique advantages of deep neural networks, focusing on visual understanding via RL.

TL;DR: This work uses reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand, and these policies transfer to the physical robot despite being trained entirely in simulation.

TL;DR: This tutorial article aims to provide the reader with the conceptual tools needed to get started on research on offline reinforcement learning algorithms: reinforcementlearning algorithms that utilize previously collected data, without additional online data collection.

TL;DR: In this article, the authors demonstrate a simple method to bridge the "reality gap" by randomizing the dynamics of the simulator during training and develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained.

TL;DR: In this article, a deep generative model, belonging to the family of variational autoencoders, is used to generate image trajectories from a latent space in which the dynamics is constrained to be locally linear.

TL;DR: A survey of data-driven grasp synthesis can be found in this article, where the authors divide the approaches into three groups based on whether they synthesize grasps for known, familiar or unknown objects.

TL;DR: This paper presents a complete design methodology for Cartesian position based visual servo control for robots with a single camera mounted at the end-effector and the implementation using a distributed computer architecture is described.

TL;DR: This work introduces a simple but powerful approach to computing descriptors for object views that efficiently capture both the object identity and 3D pose, and trains a Convolutional Neural Network to compute these descriptors by enforcing simple similarity and dissimilarity constraints between the descriptors.