Multiple model estimation by hybrid grid

This paper considers the problem of state estimation for a hybrid system with Markovian switching parameters which belong to a continuous space. A hybrid grid multiple model (HGMM) estimator is presented. The total model set for HGMM is the combination of a fixed coarse grid and an adaptive fine grid. Three practical algorithms in this scheme are developed. These algorithms are used for state estimation in maneuvering target tracking. Simulation results demonstrate that the HGMM estimator outperforms the corresponding fixed structure multiple model (FSMM) at a negligible extra computational cost.