Acquiring visual servoing reaching and grasping skills using neural reinforcement learning

Lampe, Thomas; Riedmiller, Martin

doi:10.1109/ijcnn.2013.6707053

Cited by 66 publications

(55 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practice, these voltages are roughly proportional to feedforward torques, but are also affected by friction and damping. 4 Three points fully define the pose of the end-effector.…”

Section: A Robotic Experiments Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Deep spatial autoencoders for visuomotor learning

Finn

Tan

Duan

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

984

1,127

View full text Add to dashboard Cite

Abstract-Reinforcement learning provides a powerful and flexible framework for automated acquisition of robotic motion skills. However, applying reinforcement learning requires a sufficiently detailed representation of the state, including the configuration of task-relevant objects. We present an approach that automates state-space construction by learning a state representation directly from camera images. Our method uses a deep spatial autoencoder to acquire a set of feature points that describe the environment for the current task, such as the positions of objects, and then learns a motion skill with these feature points using an efficient reinforcement learning method based on local linear models. The resulting controller reacts continuously to the learned feature points, allowing the robot to dynamically manipulate objects in the world with closed-loop control. We demonstrate our method with a PR2 robot on tasks that include pushing a free-standing toy block, picking up a bag of rice using a spatula, and hanging a loop of rope on a hook at various positions. In each task, our method automatically learns to track task-relevant objects and manipulate their configuration with the robot's arm.

show abstract

“…In practice, these voltages are roughly proportional to feedforward torques, but are also affected by friction and damping. 4 Three points fully define the pose of the end-effector.…”

Section: A Robotic Experiments Detailsmentioning

confidence: 99%

“…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 systems remain exceedingly difficult. The difficulties stem from two challenges.…”

Section: Introductionmentioning

confidence: 99%

Deep spatial autoencoders for visuomotor learning

Finn

Tan

Duan

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

984

1,127

View full text Add to dashboard Cite

show abstract

“…Again, the interaction matrix was numerically estimated. There has been significant work on reinforcement learning (RL) approaches [9], [10] for end-to-end visual servoing. However, parameters learned by RL are specific to the environment and task, hence it becomes difficult to generalise RL for new environments.…”

Section: Related Workmentioning

confidence: 99%

Exploring convolutional networks for end-to-end visual servoing

Saxena

Pandya

Kumar

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-Present image based visual servoing approaches rely on extracting hand crafted visual features from an image. Choosing the right set of features is important as it directly affects the performance of any approach. Motivated by recent breakthroughs in performance of data driven methods on recognition and localization tasks, we aim to learn visual feature representations suitable for servoing tasks in unstructured and unknown environments. In this paper, we present an end-to-end learning based approach for visual servoing in diverse scenes where the knowledge of camera parameters and scene geometry is not available a priori. This is achieved by training a convolutional neural network over color images with synchronised camera poses. Through experiments performed in simulation and on a quadrotor, we demonstrate the efficacy and robustness of our approach for a wide range of camera poses in both indoor as well as outdoor environments.

show abstract

“…For low-level motor control, however, a subsymbolic level is more suitable. Continuous RL has been used for reaching and grasping objects [30][31][32], as well as for the transportation of grasped objects [12,[32][33][34][35]. These methods are driven by feedback from tactile sensing [12,35], Cartesian-and joint-space coordinates [33,34], or both [32].…”

Section: Reinforcement Learning For Manipulationmentioning

confidence: 99%

Learning robot in-hand manipulation with tactile features

Hoof

Hermans

Neumann

et al. 2015

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)

132

View full text Add to dashboard Cite

Abstract-Dexterous manipulation enables repositioning of objects and tools within a robot's hand. When applying dexterous manipulation to unknown objects, exact object models are not available. Instead of relying on models, compliance and tactile feedback can be exploited to adapt to unknown objects. However, compliant hands and tactile sensors add complexity and are themselves difficult to model. Hence, we propose acquiring in-hand manipulation skills through reinforcement learning, which does not require analytic dynamics or kinematics models. In this paper, we show that this approach successfully acquires a tactile manipulation skill using a passively compliant hand. Additionally, we show that the learned tactile skill generalizes to novel objects.

show abstract

Acquiring visual servoing reaching and grasping skills using neural reinforcement learning

Cited by 66 publications

References 35 publications

Deep spatial autoencoders for visuomotor learning

Deep spatial autoencoders for visuomotor learning

Exploring convolutional networks for end-to-end visual servoing

Learning robot in-hand manipulation with tactile features

Contact Info

Product

Resources

About