An innovative Neural-Fuzzy adaptive Kalman filter for ultra-tightly coupled GPS/INS integrated system

Considering all integration methods of Global Positioning System (GPS) and Inertial Navigation System (INS) integrated system, ultra-tightly coupled method is with no doubt the best because the mutual assistance is further enhanced and navigation performance is obviously improved. However, UTC GPS/INS system is still affected by changing noise of GPS signals due to the pre-defined constant measurement noise model. To solve this problem a neural-fuzzy adaptive Kalman filter for UTC GPS/INS system is proposed. Fuzzy adaptive controller adjusts the measurement noise model online according to the innovation sequence provided by the Integration Kalman Filter (IKF). Since the design of the fuzzy logic controller is very empirical, a neural network (NN) is developed to achieve the parameter optimization for the fuzzy logic controller. To prove that the innovative neural-fuzzy adaptive IKF is efficient, a simulation package which includes all procedures of UTC GPS/INS system is employed and results are explained in detail. In conclusion, neural-fuzzy adaptive IKF further improves the performance of the UTC GPS/INS system in noise-changing environments.