Learning globally consistent maps by relaxation (2000)
Cached
Download Links
- [www.cs.cmu.edu]
- [www.cs.cmu.edu]
- [www.cs.cmu.edu]
- [aass.oru.se]
- DBLP
Other Repositories/Bibliography
| Venue: | In Proceedings of the IEEE International Conference on Robotics and Automation |
| Citations: | 54 - 4 self |
BibTeX
@INPROCEEDINGS{Duckett00learningglobally,
author = {Tom Duckett},
title = {Learning globally consistent maps by relaxation},
booktitle = {In Proceedings of the IEEE International Conference on Robotics and Automation},
year = {2000},
pages = {3841--3846}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Mobile robots require the ability to build their own maps to operate in unknown environments. A funda-mental problem is that odometry-based dead reckoning cannot be used to assign accurate global position infor-mation to a map because of drift errors caused by wheel slippage. This paper introduces a fast, on-line method of learning globally consistent maps, using only local metric information. The approach differs from previ-ous work in that it is computationally cheap, easy to implement and is guaranteed to find a globally optimal solution. Experiments are presented in which large, complex environments were successfully mapped by a real robot, and quantitative performance measures are used to assess the quality of the maps obtained. 1
