Optimization of the low-cost INS/GPS navigation system using ANFIS for high speed vehicle application

Both Global Positioning System (GPS) and Inertial Navigation System (INS) have complementary characteristics and their integration provides continuous and accurate navigation solution, compared to standalone INS or GPS. Extended Kalman filtering (EKF) is the most common INS/GPS integration technique used for this purpose. Kalman filter methods require prior knowledge of the error model of INS, which increases the complexity of the system. These methods have some disadvantages in terms of stability, robustness, immunity to noise effect, and observability, especially when used with low-cost MEMS-based inertial sensors. Therefore, in this paper, low-cost INS/GPS integration is enhanced based on artificial intelligence (AI) techniques that are aimed at providing high-accuracy vehicle state estimates. First, the INS and GPS measurements are fused via an EKF method. Second, an artificial intelligence-based approach for the integration of INS/GPS measurements is improved based upon an Adaptive Neuro-Fuzzy Inference System (ANFIS). The performance of the two sensor fusion approaches are evaluated using a real field test data. The experiments have been conducted using a high speed vehicle. The results show great improvements in positioning for low-cost MEMS-based inertial sensors in terms of GPS blockage compared to the EKF-based approach.