creators_name: Huang, Xiao
creators_name: Weng, Juyang
editors_name: Berthouze, Luc
editors_name: Kaplan, Frédéric
editors_name: Kozima, Hideki
editors_name: Yano, Hiroyuki
editors_name: Konczak, Jürgen
editors_name: Metta, Giorgio
editors_name: Nadel, Jacqueline
editors_name: Sandini, Giulio
editors_name: Stojanov, Georgi
editors_name: Balkenius, Christian
type: confpaper
datestamp: 2006-07-23
lastmod: 2011-03-11 08:56:29
metadata_visibility: show
title: Covert Perceptual Capability Development
ispublished: pub
subjects: comp-sci-stat-model
subjects: comp-sci-mach-learn
subjects: comp-sci-robot
full_text_status: public
keywords: vision-based navigation, incremental hierarchical discriminant regression, K-nearest neighbor Q-learning, developmental robot
abstract: In this paper, we propose a model to develop
robots’ covert perceptual capability using reinforcement learning. Covert perceptual behavior is treated as action selected by a motivational system. We apply this model to
vision-based navigation. The goal is to enable
a robot to learn road boundary type. Instead
of dealing with problems in controlled environments with a low-dimensional state space,
we test the model on images captured in non-stationary environments. Incremental Hierarchical Discriminant Regression is used to
generate states on the fly. Its coarse-to-fine
tree structure guarantees real-time retrieval
in high-dimensional state space. K Nearest-Neighbor strategy is adopted to further reduce training time complexity.
date: 2005
date_type: published
volume: 123
publisher: Lund University Cognitive Studies
pagerange: 107-110
refereed: TRUE
citation:   Huang, Xiao and Weng, Juyang  (2005) Covert Perceptual Capability Development.  [Conference Paper]     
document_url: http://cogprints.org/4981/1/huang.pdf