English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Learning Visual Representations for Interactive Systems

MPS-Authors
/persons/resource/persons84139

Piater,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84027

Krömer,  O.
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84135

Peters,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Piater, J., Jodogne, S., Detry, R., Kraft, D., Krüger, N., Krömer, O., et al. (2011). Learning Visual Representations for Interactive Systems. In C. Pradalier, R. Siegwart, & G. Hirzinger (Eds.), Robotics Research: The 14th International Symposium ISRR (pp. 399-416). Berlin, Germany: Springer.


Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-BCE0-A
Abstract
We describe two quite different methods for associating action parameters to visual percepts. Our RLVC algorithm performs reinforcement learning directly on the visual input space. To make this very large space manageable, RLVC interleaves the reinforcement learner with a supervised classiamp;amp;64257;cation algorithm that seeks to split perceptual states so as to reduce perceptual aliasing. This results in an adaptive discretization of the perceptual space based on the presence or absence of visual features. Its extension RLJC also handles continuous action spaces. In contrast to the minimalistic visual representations produced by RLVC and RLJC, our second method learns structural object models for robust object detection and pose estimation by probabilistic inference. To these models, the method associates grasp experiences autonomously learned by trial and error. These experiences form a non-parametric representation of grasp success likelihoods over gripper poses, which we call a gra sp d ensi ty. Thus, object detection in a novel scene simultaneously produces suitable grasping options.