An order insensitive optimal generalised sequential fusion estimation for stochastic uncertain multi-sensor systems with correlated noise

The globally optimal generalised sequential fusion (GSF) algorithm in the sense of linear minimum variance for multi-sensor stochastic uncertain systems is investigated by the authors. Specifically, in the GSF algorithm, the estimation of measurement noise is considered, and m_a (m_a ≥ 1) sensors' measurement data are fused at the ath reception instant, which makes it very flexible and suitable for practical applications. The centralised and sequential fusion algorithms are special cases of the proposed GSF algorithm. Furthermore, for any m_a, a = 1, 2, …, M, the estimated values of the GSF algorithm remain invariant and globally optimal. Moreover, the independence between the estimated values and fusion order is proved in the proposed GSF algorithm. Finally, simulation results are given to demonstrate the usefulness of the developed algorithm.