LAUSR

We propose a new particle filter for nonlinear continuous-discrete models. The proposed filter is based on the multiple distribution estimation with a bank of extended Kalman–Bucy filters. Compared to the simple application of a particle filter, i.e., the bootstrap filter (Monte Carlo filter), to the continuous-discrete models, the proposed filter retains superior integration and fewer particle impoverishment properties. The performance of the proposed filter is also verified using the benchmark simulation model of satellite re-entry.