Consensus-Based Distributed Multiple Model UKF for Jump Markov Nonlinear Systems

Wenling Li, Yingmin Jia · IEEE Transactions on Automatic Control · 2011

This note studies the problem of distributed estimation for jump Markov nonlinear systems (JMNLSs) in a not fully connected sensor network. Based on the consensus theory, a distributed unscented Kalman filter (UKF) is first derived for nonlinear systems without jumping parameters and then it is extended to develop a distributed multiple model UKF for JMNLSs. The proposed filtering algorithm is illustrated via a simulation example involving tracking a maneuvering target.

Read the paper · More papers on PaperTik