Real-time INS/GPS data fusion using hybrid adaptive network based fuzzy inference

Kalman filter is used to integrate the data from inertial navigation systems (INS) and global position systems (GPS) for vehicle navigation to provide position, velocity and attitude. However several drawbacks of Kalman filter such as noise, modeling of the system, initial noise parameter are restricted its application and implementation. In this paper the real time implementation of GPS/INS integration using a hybrid Adaptive Neuro Fuzzy Inference System (ANFIS) is proposed. The proposed system is trained during the availability of GPS signal to map the error between the GPS and the INS. Then it will be used to predict the error of the INS position components during GPS signal blockage. The data from GPS and INS are used to build a structured knowledge base consisting of behavior of the INS in some special scenarios of vehicle motion. In the absence of the GPS information, the system will perform its task only with the data from INS and with the trained data provided by ANFIS. The system is evaluated while considering several intentionally introduced GPS outages for periods of 50 seconds, with the position accuracy mostly below 0.2m. The simulated results show the advantages of the proposed method of ANFIS techniques for INS/GPS integration.