Header logo is ei

Learning Visual Representations for Interactive Systems

2011

Conference Paper

ei


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 classification 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.

Author(s): Piater, J. and Jodogne, S. and Detry, R. and Kraft, D. and Krüger, N. and Kroemer, O. and Peters, J.
Book Title: Robotics Research
Journal: Proceedings of the 14th International Symposium on Robotics Research (ISRR 2009)
Pages: 399-416
Year: 2011
Month: January
Day: 0
Editors: Pradalier, C. , R. Siegwart, G. Hirzinger
Publisher: Springer

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Address: Berlin, Germany
Digital: 0
DOI: 10.1007/978-3-642-19457-3_24
Event Name: 14th International Symposium on Robotics Research (ISRR 2009)
Event Place: Luzern, Switzerland
ISBN: 978-3-642-19457-3
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{6070,
  title = {Learning Visual Representations for Interactive Systems},
  author = {Piater, J. and Jodogne, S. and Detry, R. and Kraft, D. and Kr{\"u}ger, N. and Kroemer, O. and Peters, J.},
  journal = {Proceedings of the 14th International Symposium on Robotics Research (ISRR 2009)},
  booktitle = {Robotics Research},
  pages = {399-416},
  editors = {Pradalier, C. , R. Siegwart, G. Hirzinger},
  publisher = {Springer},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Berlin, Germany},
  month = jan,
  year = {2011},
  month_numeric = {1}
}