Related papers: An Efficient Image-to-Image Translation HourGlass-…

This paper introduces a challenging object grasping task and proposes a self-supervised learning approach. The goal of the task is to grasp an object which is not feasible with a single parallel gripper, but only with harnessing environment…

Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end…

Multi-Focus Image Fusion seeks to improve the quality of an acquired burst of images with different focus planes. For solving the task, an activity level measurement and a fusion rule are typically established to select and fuse the most…

Grasping an object when it is in an ungraspable pose is a challenging task, such as books or other large flat objects placed horizontally on a table. Inspired by human manipulation, we address this problem by pushing the object to the edge…

Deep reinforcement learning is a technique for solving problems in a variety of environments, ranging from Atari video games to stock trading. This method leverages deep neural network models to make decisions based on observations of a…

Multi-goal policy learning for robotic manipulation is challenging. Prior successes have used state-based representations of the objects or provided demonstration data to facilitate learning. In this paper, by hand-coding a high-level…

We investigate the "Visual Pushing for Grasping" (VPG) system by Zeng et al. and the "Hourglass" system by Ewerton et al., an evolution of the former. The focus of our work is the investigation of the capabilities of both systems to learn…

Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor…

Considering its advantages in dealing with high-dimensional visual input and learning control policies in discrete domain, Deep Q Network (DQN) could be an alternative method of traditional auto-focus means in the future. In this paper,…

This paper addresses the challenge of navigation in large, visually complex environments with sparse rewards. We propose a method that uses object-oriented macro actions grounded in a topological map, allowing a simple Deep Q-Network (DQN)…

While contemporary reinforcement learning research and applications have embraced policy gradient methods as the panacea of solving learning problems, value-based methods can still be useful in many domains as long as we can wrangle with…

Autonomous driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers. In…

The current success of Reinforcement Learning algorithms for its performance in complex environments has inspired many recent theoretical approaches to cognitive science. Artistic environments are studied within the cognitive science…

In this work we present a method for using Deep Q-Networks (DQNs) in multi-objective environments. Deep Q-Networks provide remarkable performance in single objective problems learning from high-level visual state representations. However,…

Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are…

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…

Extracting a known target object from a pile of other objects in a cluttered environment is a challenging robotic manipulation task encountered in many robotic applications. In such conditions, the target object touches or is covered by…

We study the problem of learning a navigation policy for a robot to actively search for an object of interest in an indoor environment solely from its visual inputs. While scene-driven visual navigation has been widely studied, prior…

This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically…

One of the most efficient ways for a learning-based robotic arm to learn to process complex tasks as human, is to directly learn from observing how human complete those tasks, and then imitate. Our idea is based on success of Deep…