JNS/GPS Integrated System State Estimation Based on Hopfield Neural Network

This paper aims at introducing state estimation in INS/GPS integrated system utilizing Hopfield neural network. INS/GPS integration provides reliable navigation solutions by overcoming each of their shortcomings, including signal blockage for GPS and growth of position errors with time for INS. Most of the present navigation systems rely on Kalman filtering methods to fuse data. Present Kalman filtering INS/GPS integration techniques have several inadequacies related to sensor error model, immunity to noise and observability. The method presented in this paper, obtains the optimal state estimation by minimizing the energy function of the Hopfield neural network. This new estimator relaxes the assumptions made by the Kalman filter so that it is more versatile. Simulation results show that the new estimator performs similarly to the Kalman filter. Furthermore it has some advantages such as fast convergence, unbias and high precision during fusion process, despite of the inaccurate modeling errors, system disturbance, observation errors, and even the shortage of observation. Also as the parallel computational mode and 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/GPS