Interacting Multiple Model Algorithm with the Unscented Particle Filter (UPF)

Abstract

Combining interacting multiple model (IMM) and unscented particle filter (UPF), a new multiple model filtering algorithm is presented. Multiple models can be adapted to targets' high maneuvering. Particle filter can be used to deal with the nonlinear or non-Gaussian problems and the unscented Kalman filter (UKF) can improve the approximate accuracy. Compared with other interacting multiple model algorithms in the simulations, the results demonstrate the validity of the new filtering method.