Broad Area Colloquium for Artificial Intelligence,
Geometry, Graphics, Robotics and Vision
What Do Mobile Robots And Bayesian Statistics Have In Common?
Sebastian Thrun
Carnegie Melon and Stanford
Monday, October 8, 2001, 4:15PM
Gates B01 http://robotics.stanford.edu/ba-colloquium/
Abstract
In recent years, several hard problems in mobile robotics have been
solved using probabilistic techniques. These solutions have led to
deployed mobile robot systems of unprecedented robustness, in
application domains ranging from autonomous underwater robotics to
interactive service robots that give tours to kids in museums. The
goal of this talk is to introduce the audience to a rich and
fascinating body of work on probabilistic robotics. The speaker will
present basic estimation and control techniques and show how they lead
to new and more robust solutions in problems such as mobile robot
localization, mapping, exploration, and people interaction. Special
emphasis will be given to the challenges that arise when transitioning
from basic statistical theory to physical systems operating in the
real world. To illustrate these concepts, the speaker plans to discuss
in depth several robot systems that his group recently developed, and
that were deployed in places like a Smithsonian museum in Washington,
DC, and an elderly care facility near Pittsburgh, PA.
About the Speaker
Sebastian Thrun is an Associate Professor of Computer Science and
Robotics at Carnegie Mellon University, presently on sabbatical at
Stanford University. Thrun pursues research in artificial
intelligence, machine learning, and robotics.
