Robotics Institute Seminar, February 6, 1998
Robotics Institute
Carnegie Mellon University
Pittsburgh PA 15213-3891
412/268-8525 . 412/268-5576 (fax)
Warning
This page is
provided for historical and archival purposes
only. While the seminar dates are correct, we offer no
guarantee of informational accuracy or link
validity. Contact information for the speakers, hosts and
seminar committee are certainly out of date.
Statistical Techniques for Building Maps With Mobile Robots
Sebastian Thrun
Department of Computer Science and the Robotics Institute
Carnegie Mellon University
Place and Time
Adamson Wing, Baker Hall
Refreshments 3:15 pm
Talk 3:30 pm
Abstract
This talk addresses the problem of building maps of large-scale indoor
environments with mobile robots. It poses the map building problem as
a constrained, probabilistic maximum-likelihood estimation problem. It
then devises practical algorithms for generating the most likely map
from data, along with the most likely path taken by the robot. Our
currently best algorithm constructs a coarse topological (graph-like)
map of the environment, followed by the construction of a metric map
with floating-point accuracy. The speaker will present practical
results that are, to his knowledge, an order of magnitude better
(larger, more accurate) than what previous approaches have been shown
to produce. The significance of these results with respect to the
speaker's ongoing "robotic museum tour-guide project" will be
discussed.
Speaker Biography
Sebastian Thrun is a scientist in the School of Computer Science at
Carnegie Mellon University. He received his Ph.D. degree in Computer
Science from the University of Bonn in 1995. Thrun's research
interests include machine learning and robotics.
Speaker Appointments
For appointments, please contact the speaker, Sebastian Thrun, at thrun@cs.cmu.edu.