Publikation

Closing a Million-Landmarks Loop

Udo Frese, Lutz Schröder

In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2006) October 9-15 Bejing China 2006.

Abstrakt

We present an improved version of the treemap SLAM algorithm which uses Cholesky factors for representing Gaussians and a Hierarchical Tree Partitioning algorithm derived from the established Kernighan-Lin heuristic for graph bisection. We demonstrate the algorithm's efficiency by mapping a simulated building with 1032271 landmarks. In the end, we close a million-landmarks loop in 21, providing an estimate for 10000 selected landmarks close to the robot, or in 442 for computing a full estimate.

Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence