Learning Spatial Object Localization from Vision on a Humanoid Robot

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@Article{Leitner:2012:IJARS,
  author =       "Juergen Leitner and Simon Harding and 
                 Mikhail Frank and Alexander Forster and Jurgen Schmidhuber",
  title =        "Learning Spatial Object Localization from Vision on a
                 Humanoid Robot",
  journal =      "International Journal of Advanced Robotic Systems",
  year =         "2012",
  volume =       "9",
  publisher =    "InTech",
  keywords =     "genetic algorithms, genetic programming, spatial
                 Perception, Computer Vision, Machine Learning, Humanoid
                 Robotics, Object Localisation",
  ISSN =         "1729-8806",
  bibsource =    "OAI-PMH server at www.doaj.org",
  language =     "eng",
  oai =          "oai:doaj-articles:31e24b4d43ea5ad01dffb4748d976920",
  URL =          "http://www.intechopen.com/journals/international_journal_of_advanced_robotic_systems/learning-spatial-object-localization-from-vision-on-a-humanoid-robot",
  DOI =          "doi:10.5772/54657",
  abstract =     "We present a combined machine learning and computer
                 vision approach for robots to localise objects. It
                 allows our iCub humanoid to quickly learn to provide
                 accurate 3D position estimates (in the centimetre
                 range) of objects seen. Biologically inspired
                 approaches, such as Artificial Neural Networks (ANN)
                 and Genetic Programming (GP), are trained to provide
                 these position estimates using the two cameras and the
                 joint encoder readings. No camera calibration or
                 explicit knowledge of the robot{'}s kinematic model is
                 needed. We find that ANN and GP are not just faster and
                 have lower complexity than traditional techniques, but
                 also learn without the need for extensive calibration
                 procedures. In addition, the approach is localising
                 objects robustly, when placed in the robot's workspace
                 at arbitrary positions, even while the robot is moving
                 its torso, head and eyes.",
}

Genetic Programming entries for Juergen Leitner Simon Harding Mikhail Frank Alexander Forster Jurgen Schmidhuber

Citations