An adaptive particle filter (APF) for estimating states of nonlinear system with unknown parameters

This paper presents an adaptive particle filter (APF) for estimating the states of the nonlinear system with unknown parameters. To implement this algorithm, the process noise covariance is adjusted according to the innovation-based adaptive estimation (IAE) approach, which only takes advantage of one state model without the requirement of knowing the parameters. In addition, the Maximum-A-Posterior (MAP) method is used to estimate the parameters to improving the performance of APF. Therefore, the APF can modify the prior distribution of the particles, and then alleviate the sample degeneracy problem which is common in particle filter (PF). Numerical simulations of Logistic map are conducted to demonstrate the effectiveness of our proposed method.