Attitude estimation using a Neuro-Fuzzy tuning based adaptive Kalman filter

This paper presents the development of a Kalman Filter with Neuro-Fuzzy adaptation (KF-NFA) which is applied in attitude estimation, relying on information derived from triaxial accelerometer and gyroscope sensors contained in an inertial measurement unit (IMU). The adaptation process is performed on the filter statistical information matrices R or Q, which are tuned using an Adaptive Neuro Fuzzy Inference System (ANFIS) based on the filter innovation sequence through a covariance-matching technique. The test results show a better performance of the KF-NFA when it is compared with a traditional Kalman Filter (T-KF). This work is being developed in the context of a Pedestrian Dead Reckoning (PDR) algorithm for localization based services (LBS), currently in progress.