Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation

The last two decades have shown an increasing trend in the use of positioning and navigation technologies in land vehicles. Most of the present navigation systems incorporate global positioning system (GPS) and inertial navigation system (INS), which are integrated using Kalman filtering (KF) to provide reliable positioning information. Due to several inadequacies related to KF-based INS/GPS integration, artificial intelligence (AI) methods have been recently suggested to replace KF. Various neural network and neuro-fuzzy methods for INS/GPS integration were introduced. However, these methods provided relatively poor positioning accuracy during long GPS outages. Moreover, the internal system parameters had to be tuned over time of the navigation mission to reach the desired positioning accuracy. In order to overcome these limitations, this study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure. The ANFIS-based system considers a non-overlap moving window instead of the commonly used sliding window approach. The proposed system is tested using differential GPS and navigational grade INS field test data obtained from a land vehicle experiment. The results showed that the proposed system is a reliable modeless system and platform independent module that requires no priori knowledge of the navigation equipment utilized. In addition, significant accuracy improvement was achieved during long GPS outages.