Lessons in Estimation Theory for Signal Processing, Communications, and Control, Second Edition

Lesson 16 State Estimation: Prediction

Summary

Prediction, filtering, and smoothing are three types of mean-squared state estimation that have been developed during the past 35 years. The purpose of this lesson is to study prediction.

A predicted estimate of a state vector x(k) uses measurements that occur earlier than t_k and a model to make the transition from the last time point, say t_j, at which a measurement is available to t_k. The success of prediction depends on the quality of the model. In state estimation we use the state equation model. Without a model, prediction is dubious at best.

Filtered and predicted state estimates are very tightly coupled together; hence, most of the results from this lesson cannot be implemented until we have ...