Improved Extend Kalman particle filter based on Markov chain Monte Carlo for nonlinear state estimation

Abstract

Considering the problem of poor tracking accuracy and particle degradation in the traditional particle filter algorithm, a new improved particle filter algorithm with the Markov chain Monte Carlo (MCMC) and extended particle filter is discussed. The algorithm uses Extend Kalman filter to generate a proposal distribution, which can integrate latest observation information to get the posterior probability distribution that is more in line with the true state. Meanwhile, the algorithm is optimized by MCMC sampling method, which makes the particles more diverse. The simulation results show that the improved extend Kalman particle filter solves particle degradation effectively and improves tracking accuracy.