A Moving State Estimation Method Based on Interactive Multi-Model Algorithm

Abstract

In this paper, an interacting multiple model algorithm is proposed to estimate the motion state of a target. The motion state of a target in a certain period is constructed by four basic motion states of uniform linear motion, even accelerating of linear motion, variable speed linear motion and turning motion. Markov process is used to model the transfer probability of four basic motion states. Kalman filter is used to estimate and update the target's motion state. The simulation results show that the algorithm achieves better rate and smooth position observation of maneuvering targets, and is suitable for moving state estimation of ground maneuvering targets.