Learning visual representations for perception-action systems
By Justus H. Piater, Sébastien Jodogne, Renaud Detry, Dirk Kraft, Norbert Krüger, Oliver Kroemer, Jan Peters. 2011
41 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Jan Peters
- J. Bagnell
- Sergey Levine
- Jens Kober
- Rico Jonschkowski
- Oliver Brock
- Martin A. Riedmiller
- Luis Montesano
In Control and Systems Engineering
- Sergey Levine
- Jan Peters
- Jens Kober
- J. Bagnell
- Pieter Abbeel
- Thomas Lampe
- Martin A. Riedmiller
- Luis Montesano
Citations in the corpus
- Reinforcement learning in robotics: A survey (2013, background): “In the related field of computer vision, Piater et al. (2011) propose an approach that adaptively and incrementally discretizes a perceptual space into discrete states, training an image classifier based on the experience of the reinforcement learning agent to distinguish visual classes, which…”
- State Representation Learning in Robotics: Using Prior Knowledge about Physical Interaction (2014, methodology): “[21] use decision trees to incrementally discriminate between observations that have inconsistent stateaction values according to the reinforcement learning algorithm.”
- Acquiring visual servoing reaching and grasping skills using neural reinforcement learning (2013, background): “In contrast, visual servoing methods [8] inherently adhere to the reactive paradigm [9].”
- Active learning of visual descriptors for grasping using non-parametric smoothed beta distributions (2012, methodology): “This scheme has been widely used in many of the latest developed systems such as generic visual descriptors combined with planning [9], 3D object centered representations and reinforcement learning[10], 3D multi-modal features combined with a set of predefined grasp strategies [11], single image vis”
- Learning state representations with robotic priors (2015, methodology): “Piater et al. [26] use decision trees to incrementally discriminate between observations with inconsistent state-action values according to the reinforcement learning algo-rithm.”
- Unsupervised Learning of State Representations for Multiple Tasks (2017, methodology): “To enable the agent to localize, MNIST digits and a background pattern are printed on the ground, similar to the task proposed by Piater et al. (2011).”