A Hierarchical Adaptive Interacting Multiple Model Algorithm

Abstract

When the interacting multiple model (IMM) algorithm is applied to the multiple model estimation problems, more models have to be used to improve the algorithm performance, but the use of too many models can degrade the algorithm performance. In view of this problem, a hierarchical adaptive IMM algorithm is presented in this paper. The center model of each sub-model set is calculated by using the adaptive model set algorithm, of which the model set in the IMM is composed. The resulting output of the algorithm is the data fusion of the model set estimation. The Monte Carlo simulation results show that the performance of the proposed algorithm is superior to the conventional IMM with equivalent computational complexity.