Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/88086
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Robust loop closing over time |
Author: | Latif, Y. Cadena Lerma, C. Neira, J. |
Citation: | Proceedings of Robotics: Science and Systems VIII, 2012 / Roy, N., Newman, P., Srinivasa, S. (ed./s), vol.8, pp.233-240 |
Publisher: | MIT Press |
Publisher Place: | Online |
Issue Date: | 2012 |
ISBN: | 9780262519687 |
ISSN: | 2330-7668 2330-765X |
Conference Name: | Robotics: Systems and Science (RSS) 2012 (9 Jul 2012 - 13 Jul 2012 : Sydney, Australia) |
Editor: | Roy, N. Newman, P. Srinivasa, S. |
Statement of Responsibility: | Yasir Latif, Cesar Cadena and José Neira |
Abstract: | Long term autonomy in robots requires the ability to reconsider previously taken decisions when new evidence becomes available. Loop closing links generated by a place recognition system may become inconsistent as additional evidence arrives. This paper is concerned with the detection and exclusion of such contradictory information from the map being built, in order to recover the correct map estimate. We propose a novel consistency based method to extract the loop closure regions that agree both among themselves and with the robot trajectory over time. We also assume that the contradictory loop closures are inconsistent among themselves and with the robot trajectory. We support our proposal, the RRR algorithm, on well-known odometry systems, e.g. visual or laser, using the very efficient graph optimization framework g2o as back-end.We back our claims with several experiments carried out on real data. |
Rights: | © 2013 Massachusetts Institute of Technology |
DOI: | 10.15607/RSS.2012.VIII.030 |
Published version: | http://www.roboticsproceedings.org/rss08/p30.html |
Appears in Collections: | Aurora harvest 2 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_88086.pdf Restricted Access | Restricted Access | 1.64 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.