Multiple Hypotheses Mixing Filter for hybrid Markovian switching systems | IEEE Conference Publication | IEEE Xplore

Multiple Hypotheses Mixing Filter for hybrid Markovian switching systems


Abstract:

This work addresses the problem of stochastic state estimation for hybrid Markovian switching systems. The proposed Multiple Hypotheses Mixing Filter (MHMF) combines the ...Show More

Abstract:

This work addresses the problem of stochastic state estimation for hybrid Markovian switching systems. The proposed Multiple Hypotheses Mixing Filter (MHMF) combines the Generalized Pseudo Bayes' (GPB) multiple hypotheses tracking with the Interacting Multiple Model's (IMM) estimates mixing in order to improve performance, the later being a particular case of the MHMF. A hypotheses pruning step prevents the filter's output to be degraded by estimates coming from very unlikely hypotheses and the mode transition probabilities are estimated online based on the measurements' likelihoods. A target tracking application shows the MHMF's utility as a stochastic filter for hybrid systems.
Date of Conference: 15-17 December 2010
Date Added to IEEE Xplore: 22 February 2011
ISBN Information:

ISSN Information:

Conference Location: Atlanta, GA, USA

References

References is not available for this document.