Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Auxiliary particle filter robot localization from high-dimensional sensor observations
Vlassis, Nikos; Terwijn, B.; Krose, B.
2002In IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS
Peer reviewed
 

Files


Full Text
download.pdf
Author postprint (182.77 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[en] We apply the auxiliary particle filter algorithm of Pitt and Shephard (1999) to the problem of robot localization. To deal with the high-dimensional sensor observations (images) and an unknown observation model., we propose the use of an inverted nonparametric observation model computed by nearest neighbor conditional density estimation. We show that the proposed model can lead to a fully adapted optimal filter, and is able to successfully handle image occlusion and robot kidnap. The proposed algorithm is very simple to implement and exhibits a high degree of robustness in practice. We report experiments involving robot localization from omnidirectional vision in an indoor environment.
Disciplines :
Computer science
Identifiers :
UNILU:UL-ARTICLE-2011-739
Author, co-author :
Vlassis, Nikos ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Terwijn, B.
Krose, B.
Language :
English
Title :
Auxiliary particle filter robot localization from high-dimensional sensor observations
Publication date :
2002
Event name :
IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS
Event date :
2002
Main work title :
IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS
Pages :
7-12
Peer reviewed :
Peer reviewed
Available on ORBilu :
since 17 November 2013

Statistics


Number of views
46 (1 by Unilu)
Number of downloads
579 (1 by Unilu)

Scopus citations®
 
80
Scopus citations®
without self-citations
68

Bibliography


Similar publications



Contact ORBilu