W. Burgard, D. Fox, and D. Hennig
Fast Grid-based Position Tracking
for Mobile Robots
Proc. of the 21th German Conference on Artificial Intelligence
(KI-97)
Abstract
One of the fundamental problems in the field of mobile robotics is
the estimationof the robot's position in the environment. Position probability
grids havebeen proven to be a robust technique for the estimation of the
absolute positionof a mobile robot. In this paper we describe an application
of position probabilitygrids to position tracking. Given a starting
position our approach keepstrack of the robot's current position by matching
sensor readings againstametric model of the environment. The method
is designed to work with noisysensors and approximative models of the environment.
Furthermore, it is ableto integrate sensor readings of different types of
sensors over time. Byusing raw sensor data, the method exploits arbitrary
features of the environmentand, in contrast to many other approaches, is
not restricted to a fixed setof predefined features such as doors, openings
or corridor junction types. An adaptable sensor model allows a fast
integration of new sensings. Theresults described in this paper illustrate
the robustness of our method inthe presence of sensor noise and errors in
the environmental model.
Download
Full paper
[.ps.gz](503 kb, 12 pages)
Bibtex
@INPROCEEDINGS{Bur97Fas,
AUTHOR = {Burgard, W. and Fox, D. and Hennig, D},
TITLE = {Fast Grid-Based Position Tracking for Mobile
Robots},
BOOKTITLE = {Proc.~of the 21th German Conferenceon Artificial Intelligence,
Germany},
YEAR = {1997}
}