Distributed Kalman filter based on Metropolis-Hastings sampling strategy

The reasonable extraction and utilization of observation information are considered as the key of design and optimization of filters. By constructing the sampling steps of multi-sensor bootstrapped observations and the validation process of credible observations, a novel distributed Kalman filter in multi-sensor observations based on Metropolis-Hastings (M-H) sampling strategy is proposed in this paper. Firstly, combined with the latest observation information and the accuracy information of sensor which is also used to describe the prior modeling knowledge of observation system, we design the bootstrapped observation sampling for linear observation system. Secondly, aiming to the consistency deviation phenomenon appearing in the bootstrapped observations of single sensor, through constructing the likelihood degree of multi-sensor bootstrapped observations and the accept probability of credible observations, meanwhile, combined with the M-H sampling strategy, we give the validation method of credible observations. Finally, the realization steps of new algorithm are constructed according to the weighted fusion criterion. The advantage of new algorithm is to improve greatly the filtering precision with additional less hardware costs. The theoretical analysis and experimental results show the feasibility and efficiency of the proposed algorithm.