Acquiring visual servoing reaching and grasping skills using neural reinforcement learning

By Thomas Lampe, Martin A. Riedmiller. 2013

71 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Reinforcement Learning

Citations in the corpus

End-to-End Training of Deep Visuomotor Policies (2015, background): “More recent work on sensorimotor deep learning has tackled simple task-space motion [17] and used unsupervised learning to obtain low-dimensional state spaces from images [34], but such methods are limited to tasks with a low-dimensional structure.”
Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection (2016, background): “…reinforcement learning applications, including playing video games (Mnih et al., 2015), executing simple task-space motions for visual servoing (Lampe & Riedmiller, 2013), controlling simple simulated robotic systems (Watter et al., 2015; Lillicrap et al., 2016), and performing a variety of…”
Deep spatial autoencoders for visuomotor learning (2015, background): “Directly learning a state space representation from raw sensory signals, such as images from a camera, is an active area of research [1], [2], and while considerable progress has been made in recent years [3], [4], applications to real robotic”
Collective robot reinforcement learning with distributed asynchronous guided policy search (2016, background): “While several works have extended deep learning methods to simulated [5, 6] and real-world [7, 10] robotic tasks, the kind of generalization exhibited by deep learning in passive perception domains has not yet been demonstrated for robotic skill learning.”
Learning dexterous manipulation for a soft robotic hand from human demonstrations (2016, methodology): “Controllers for reaching and grasping have been learned by approximating the Q-function with a multilayer perceptron [16].”
Learning robot in-hand manipulation with tactile features (2015, background): “In this section, we discuss related work on in-hand manipulation with and without tactile sensing, as well as reinforcement learning for various kinds of object manipulation.”
Zero-Shot Visual Imitation (2018, methodology): “Visual servoing is a standard problem in robotics [5, 10–12, 24, 26] that seeks to take actions that align the agent’s observation with carefully-designed visual features or raw pixel intensities.”
Kinova Modular Robot Arms for Service Robotics Applications (2017, background): “, 2013), artificial intelligence (Lampe and Riedmiller, 2013), teleoperation (Bidwell et al.”
Stable reinforcement learning with autoencoders for tactile and visual data (2016, methodology): “Reinforcement learning (RL) has been shown to be useful in optimizing, among others, reaching, grasping, and manipulation skills [3]–[5].”
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation (2019, background): “…that can execute complex behaviours from only pixel inputs has been a well studied problem, for example with visual servoing (Mohta et al., 2014; Espiau et al., 1992; Wilson et al., 1996; Yoshimi & Allen, 1994; Jagersand et al., 1997; Lampe & Riedmiller, 2013; Sadeghi et al., 2018; Sadeghi, 2019).”
Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders (2015, background): “been made in recent years [3], [4], applications to real robotic systems remain exceedingly difficult.”