ABSTRACT
Estimation fusion, or data fusion for estimation, is the problem of how to best utilize useful information contained in multiple sets of data for the purpose of estimating a quantity—a parameter or a process. Estimation fusion has two basic architectures: centralized fusion and distributed fusion. This chapter presents constrained nonstandard distributed fusion and discusses the applicability of existing single-sensor-based constrained state estimators to the multisensor case through measurement stacking. For the single-sensor case, owing to the introduction of the linear equality constraint, the state estimator is different from the one for the unconstrained system. The idea of the null space method is to represent the general solution of the constraint equation as a summation of a deterministic special solution and a stochastic zero solution through null space decomposition. The direct elimination method represents part of the state vector as a linear function of the remaining part of the state vector.
