Sciweavers

ICRA
1998
IEEE

Hybrid, High-Precision Localisation for the Mail Distributing Mobile Robot System MOPS

13 years 7 months ago
Hybrid, High-Precision Localisation for the Mail Distributing Mobile Robot System MOPS
This paper describes the new localisation algorithms under implementation for the mail distributing mobile robot, MOPS, of the Institute of Robotics, Swiss Federal Institute of Technology Zurich. Using geometric primitives as features, we employ consistent probabilistic feature extraction, clustering, matching and estimation of the vehicle position and orientation. The extracted features and their jirst-order covariance estimates are used, together with a world model, by an extended Kalman filter so as to get an optimal estimate of MOPS' current pose vector and the associated uncertainty. The line extraction consists of an initial segmentation, based on a feature-independent compactness measure in the model space, and a subsequent probabilistic clustering step. This yielh a highly accurate and eficient localisation.
Kai Oliver Arras, Sjur J. Vestli
Added 04 Aug 2010
Updated 04 Aug 2010
Type Conference
Year 1998
Where ICRA
Authors Kai Oliver Arras, Sjur J. Vestli
Comments (0)