Enhancing the Update Procedure of Neuro - Fuzzy Modules Used for Multi-Sensor Navigation Systems

Land vehicles rely mainly on Global Positioning System (GPS) to provide its position with consistent accuracy. However, GPS receivers may encounter frequent GPS outages within urban areas where satellite signals are blocked. In order to overcome this problem, GPS is usually combined with inertial sensors (accelerometers and gyroscopes) mounted inside the vehicle to obtain a reliable navigation solution, especially during GPS outages. Neuro-fuzzy modules were used to fuse data from GPS and inertial sensors in real-time. This research optimizes the operation of these modules by implementing a temporal window-based cross-validation approach during the update procedure. A field test data was used to examine the performance of the proposed method and the results discuss the merits and the limitations of the proposed technique.