@device(postscript)
@libraryfile(Mathematics10)
@libraryfile(Accents)
@style(fontfamily=timesroman,fontscale=11)
@pagefooting(immediate, left "@c<Technical Report 1996>",
center "@c<Computer Science>",
right "@c<Carnegie Mellon>")
@heading(A Bayesian Approach to Landmark Discovery and Active
Perception in Mobile Robot Navigation)
@heading(CMU-CS-96-122)
@center(@b(Sebastian Thrun))
@center(May 1996)
@center(FTP: CMU-CS-96-122.ps.Z)
@blankspace(1)
@begin(text)

To operate successfully in indoor environments, mobile
robots must be able to localize themselves. Over the past few years,
localization based on landmarks has become increasingly popular.
Virtually all existing approaches to landmark-based navigation,
however, rely on the human designer to decide what constitutes
appropriate landmarks.

This paper presents an approach that enables mobile robots to select
their landmarks by themselves. Landmarks are chosen based on their
utility for localization. This is done by training neural network
landmark detectors so as to minimize the a posteriori localization
error that the robot is expected to make after querying its sensors.
An empirical study illustrates that self-selected landmarks are
superior to landmarks carefully selected by a human. The Bayesian
approach is also applied to control the direction of the robot's
camera, and empirical data demonstrates the appropriateness of this
approach for active perception.

@blankspace(2line)
@begin(transparent,size=10)
@b(Keywords:@ )@c<Active perception, active vision, artificial neural
networks, Bayesian analysis, exploration, landmarks, mobile robots,
navigation, probabilistic navigation, sensor fusion>
@end(transparent)
@blankspace(1line)
@end(text)
@flushright(@b[(45 pages)])