Cost Reference Particle Filter Based on Adaptive Particle Swarm Optimization in Observation Uncertainty

Aiming at the effective approximation of sampling particle set relative to system state in observation uncertainty, a novel cost reference particle filter based on adaptive particle swarm optimization is proposed. In the new algorithm, the cost function and the risk function are firstly introduced to realize reasonable utilization of the latest observation. In addition, according to the prior modeling information, a new adaptive method is given to solve the selection of limit velocity. And then the movement of particle set towards the region of high weight particle is completed by particle swarm optimization strategy. The algorithm realizes the dynamic combination of the cost reference particle filter and the adaptive particle swarm optimization, and the reliability and stabilize of sampling particle set relative to system state are improved. The theoretical analysis and experimental results show the efficiency of the proposed algorithm.