Dipartimento di Ingegneria informatica, automatica e gestionale

This paper studies the problem of recursive state estimation of stochastic linear systems with nonlinear measurements. The main idea is to rewrite the measurement map in a linear form by considering, as system output, a vector of “virtual” measurements. The result is a linear system with a non-Gaussian and nonstationary output noise. State estimation is therefore obtained using a Kalman filter or, alternatively, a quadratic filter, suitably designed for non-Gaussian systems. This work provides two sufficient conditions for the application of the virtual measurement approach and shows its effectiveness in the case of the maneuvering target tracking problem.