Multisensor fusion using Hopfield neural network in INS/SMGS integrated system

This paper presents a novel multisensor fusion method using a Hopfield neural network in the INS/SMGS (inertial navigation system/scene matching guidance system) integrated systems. The state estimation of INS/SMGS systems has multirate and unequal interval characteristics due to the stochastic results of SMGS, so the classical state estimator such as Kalman filter is not competent. The method presented in this paper obtains the optimal fusion state estimation by minimizing the energy function of the Hopfield neural network, and this method is named the hop-filter. Simulation results show that the hop-filter performs much better than the Kalman filter in many factors such as fast convergence, unbias and high precision. Also as the parallel computational mode is easily carried out in hardware of the Hopfield neural network, this fusion method can improve the navigation/guidance accuracy, real time ability and practicability of the INS/SMGS.