%A Xiao Huang
%A Juyang Weng
%T Covert Perceptual Capability Development
%X 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.
%K vision-based navigation, incremental hierarchical discriminant regression, K-nearest neighbor Q-learning, developmental robot
%P 107-110
%E Luc Berthouze
%E Fr?d?ric Kaplan
%E Hideki Kozima
%E Hiroyuki Yano
%E J?rgen Konczak
%E Giorgio Metta
%E Jacqueline Nadel
%E Giulio Sandini
%E Georgi Stojanov
%E Christian Balkenius
%V 123
%D 2005
%I Lund University Cognitive Studies
%L cogprints4981

<script src='https://archive-bar.soton.ac.uk/archive-bar.js'></script>
<script src='https://archive-bar.soton.ac.uk/google-analytics.js'></script>