@device(postscript)
@libraryfile(Mathematics10)
@libraryfile(Accents)
@style(fontfamily=timesroman,fontscale=11)
@pagefooting(immediate, left "@c<Technical Report 1995>",
center "@c<Computer Science>",
right "@c<Carnegie Mellon>")
@heading(Learning Maps for Indoor Mobile Robot Navigation)
@heading(CMU-CS-96-121)
@center(@b(Sebastian Thrun, Arno Bucken@foot<Currently with the Computer Science Department III of the University of Bonn, Germany, where part of this research was carried out.>))
@center(April 1996)
@center(FTP: CMU-CS-96-121.ps.Z)
@blankspace(1)
@begin(text)

Autonomous robots must be able to learn and maintain models of their
environments.  Research on mobile robot navigation has produced two
major paradigms for mapping indoor environments:  grid-based and
topological. While grid-based methods produce accurate metric maps,
their complexity often prohibits efficient planning and problem solving
in large-scale indoor environments. Topological maps, on the other
hand, can be used much more efficiently, yet accurate and consistent
topological maps are considerably difficult to learn in large-scale
environments.

This paper describes an approach that integrates both paradigms:
grid-based and topological. Grid-based maps are learned using
artificial neural networks and Bayesian integration. Topological maps
are generated on top of the grid-based maps, by partitioning the latter
into coherent regions. By combining both paradigms@y(M)grid-based and
topological@y(M), the approach presented here gains the best of both
worlds: accuracy/consistency and efficiency. The paper gives results
for autonomously operating a mobile robot equipped with sonar sensors
in populated multi-room environments.

@blankspace(2line)
@begin(transparent,size=10)
@b(Keywords:@ )@c<Autonomous robots, exploration, mobile robots, neural
networks, occupancy grids, path planning, planning, robot mapping,
topological maps>
@end(transparent)
@blankspace(1line)
@end(text)
@flushright(@b[(38 pages)])