Innovation-based fractional order adaptive Kalman filter

Abstract

Abstract Kalman Filter (KF) is the most widely used estimator to estimate and track the states of target. It works well when noise parameters and system models are well defined in advance. Its performance degrades and starts diverging when noise parameters (mainly measurement noise) changes. In the open literature available researchers has used the concept of Fractional Order Kalman Filter (FOKF) to stabilize the KF. However in the practical application there is a variation in the measurement noise, which will leads to divergence and degradation in the FOKF approach. An Innovation Adaptive Estimation (IAE) based FOKF algorithm is presented in this paper. In order to check the stability of the proposed method, Lyapunov theory is used. Position tracking simulation has been performed for performance evaluation, which shows the better result and robustness.