         
|
GRASP Lab Seminar 2003-2004
November 7, 11:00 AM, Levine Hall 307, hosted by Dan Lee.
Dieter Fox
University of Washington
Distributed Multi-robot Exploration and Mapping
Abstract: Efficient exploration of unknown environments is a fundamental problem in multi-robot coordination. As autonomous exploration and map building becomes increasingly robust on single robots, the next challenge is to extend these techniques to large teams of robots. In this talk I will give an overview of our approach to multi-robot exploration and mapping, which is part of the CentiBots project. This project aims at fielding 100 robots in an indoor exploration and surveillance task.
A general solution to distributed exploration must consider some difficult issues, including limited communication between robots, no assumptions about relative start locations of the robots, and dynamic assignments of processing tasks. In this talk I will give an overview of our solutions to the problems of robot localization, map merging, and coordinated exploration. Most of these techniques rely on particle filters for efficient state estimation. We additionally apply a hierarchical Bayesian approach to estimate the structure of an environment. During map merging, this structure is used to determine whether or not the partial maps built by two robots overlap. The Bayesian approach uses priors learned from previously explored environments. To increase the robustness of the system, false positive map merges are avoided by guiding robots to a meeting place. I will describe experiments illustrating our technique to multi robot exploration and mapping.Biography: Dieter Fox is currently an Assistant Professor of Computer Science at the University of Washington, Seattle. He obtained his Ph.D. from the University of Bonn, Germany, in the area of mobile robot localization and navigation. Before joining UW, he spent two years as a postdoctoral researcher at the robot learning lab of Carnegie Mellon University. Over the last five years Fox's research has focused on probabilistic sensor interpretation, state estimation, and multi-robot collaboration. Together with colleagues, he successfully deployed the mobile robots Rhino and Minerva as museum tour-guides in two populated museums, one of them the Smithsonian's National Museum of American History in Washington, DC. Fox introduced particle filters as a powerful tool for state estimation in robotics. In 2000, he established the Robotics and State Estimation Lab at UW's Computer Science and Engineering Department. Fox is the author of more than 75 refereed articles. He received an NSF CAREER award and several best paper awards at major robotics and artificial intelligence conferences
