A Novel Robust IMM Filtering Method for Surface-Maneuvering Target Tracking with Random Measurement Delay

A proper filtering method for jump Markov system (JMS) is an effective approach tracking a maneuvering target. Since the coexisting of heavy-tailed measurement noises (HTMNs) and one-step random delay (OSRMD) in complex scenarios surface target tracking, effectiveness typical interacting multiple model (IMM) techniques may decline severely. To solve state estimation problem JMSs with HTMN OSRMD simultaneously, this article designs novel robust IMM filter utilizing variational Bayesian (VB) inference framework. This algorithm models HTMNs as student’s t-distribuitons, presents Bernoulli variable to describe JMSs. By transforming likelihood function form from weighted summation exponential product, paper constructs hierarchical Gaussian space models. Then, vectors, vairable, probability are inferred jointly according VB inference. The simulation example result indicates that presented achieves superior accuracy among existing filters.