Particle filter divergence monitoring with application to terrain navigation

Particle filters are an efficient Monte-Carlo method for Bayesian estimation in non-linear models. However, under certain circumstances, they are subject to divergence. Increasing the number of particles is not always possible so it is essential for many applications to assess the reliability of the...

Full description

Saved in:
Bibliographic Details
Published in2012 15th International Conference on Information Fusion pp. 794 - 801
Main Authors Murangira, A., Musso, C., Nikiforov, I.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2012
Subjects
Approximation methods
Atmospheric measurements
Delay
Navigation
Particle measurements
Reactive power
Technological innovation
Online AccessGet full text
ISBN1467304174
9781467304177

Cover

More Information
Summary:Particle filters are an efficient Monte-Carlo method for Bayesian estimation in non-linear models. However, under certain circumstances, they are subject to divergence. Increasing the number of particles is not always possible so it is essential for many applications to assess the reliability of the solution provided by the filter. In terrain navigation, trusting an erroneous position estimate can be problematic for obvious reasons. We introduce a framework for detecting filter divergence in the case of scalar measurements. The detector is based on a sequential change detection algorithm and we illustrate its performance on several terrain navigation scenarios.
ISBN:1467304174
9781467304177