ART-CPN Based Aircraft Navigation by GPS/INS Data Integration

Abstract

GPS and INS are commonly integrated using a Kalman filter (KF) to provide a robust aircraft navigation solution, overcoming drawbacks of GPS satellite signals blockage. This work presents an alternative method of integrating GPS and INS data, called Artificial Neural Networks. This method uses Adaptive Resonance Theory-Counter Propagation Neural Networks (ART-CPN) to predict the INS position error. The performance of ART-CPN is analyzed using real time data in terms of Root Mean Square Error (RMSE), Performance Index (PI), number of hidden neuron, number of epochs and learning rate. The performance of Forward only Counter Propagation Network (FCPN) and Full Counter Propagation Network (Full CPN) are also analyzed and compared with ART-CPN. ART-CPN is found to have better clustering ability when compared to FCPN and Full CPN. ART-CPN also has better learning ability and network constructing ability when compared to FCPN and Full CPN. It has better learning speed due to its one step learning process.