Self-adaptive Differential Evolution-Based Multiple Model Variable Rate Particle Filter for Trajectory Tracking

Abstract

In fixed rate, state space models are conventionally used to track the maneuvering objects. In contrast to fixed rate models, recently introduced variable rate particle filter (VRPF) is capable of tracking the target with a small number of states by imposing a Gamma distribution on the state arrival times, while the object trajectory is approached by a single dynamic motion model. It cannot estimate the position of targets in very high maneuvering regions. Thus, multiple model VRPF (MM-VRPF) method is utilized to overcome this shortage using various dynamic models. A weak point of particle filter is a phenomenon called degeneracy which even exists in MM-VRPF structure. In this study, differential evolution method is exploited to improve the mentioned method, and a novel structure called MM-VRPF with self-adaptive differential evolution is introduced. The simulation results, particularly those related to bearing only tracking achieved from the maneuvering target, revealed that the proposed structure has high performance, while it still takes advantage of variable rate structure.