Middlebury College
Department of Computer Science Seminar
DP-SLAM: Mapping Dense Environments with Speed and Precision
Ron Parr
Assistant Professor of Computer Science
Duke University
Simultaneous Localization and Mapping (SLAM) is the task of building an accurate map of an environment without getting lost in the process. This problem is of great significance in robotics for situations in which an accurate global position sensor, such as GPS, is not available. This includes undersea, subterranean, and space exploration missions, as well as most indoor environments.
A major challenge faced by SLAM algorithms is that of avoiding accumulating error: Small errors in localization that can lead to small errors in the map which, when compounded over a long exploration path, can lead to inconsistent and misaligned maps. I will present the DP-SLAM algorithm, an approach to the SLAM problem that avoids accumulating error by efficiently maintaining hundreds of map hypotheses using a particle filter and a novel map data structure.
Using DP-SLAM, we have built maps at 3cm resolution with no discernible alignment errors or blemishes for robot trajectories over 100m. Our approach can handle highly ambiguous environments with features such as glass and thin columns.
This talk is based on joint work with Austin Eliazar (Duke University). The web site for the project, which includes sample maps, is www.cs.duke.edu/~parr/dpslam.
Friday, October 14, 2005
12:20 p.m. to 1:15 p.m.
McCardell Bicentennial Hall 538
Lunch will be provided at 12:05 p.m.
All are welcome to attend!