ICML-98 Submission #119
Heading in the Right Direction
Hagit Shatkay and Leslie Pack Kaelbling
Surface Mail: Department of Computer Science
Box 1910
Brown University
Providence, RI 02912
USA
Abstract
Stochastic topological models, and hidden Markov models in particular,
are a useful tool for robotic navigation and planning. In previous
work we have shown how weak odometric data can be used to improve
learning topological models, overcoming the common problems of the
standard Baum-Welch algorithm.
Odometric data typically contain directional information, which
imposes two difficulties. First, the cyclicity of the data requires
the use of special circular distributions. Second, small errors in
the heading of the robot result in large displacements in the
odometric readings it maintains. The cumulative rotational error leads
to unreliable odometric readings.
In the paper, we present solutions to these problems by using a
circular distribution and relative coordinate systems. We validate
their effectiveness through experimental results from a model-learning
application.
Keywords: Directional/circular distribution, learning topological maps,
hidden Markov model, robots.
Email address for contact author: hs@cs.brown.edu
Phone number for contact author: (401)-863-7667