STATE ESTIMATION BASED ON STOCHASTIC AND ZONOTOPIC APPROACHES: PART II - NONLINEAR SYSTEMS

Alesi Augusto de Paula¹; Bruno Otávio Soares Teixeira¹; Guilherme Vianna Raffo¹

¹ Universidade Federal de Minas Gerais

Baixar PDF doi:10.20906/CPS/CBA2018-0639

Resumo

This paper presents a comparative review on the most cited stochastic and zonotopic filtering methods in the literature for state estimation of uncertain nonlinear systems. To achieve that, a unified notation for both approaches is proposed. While the unscented Kalman filter provides an suboptimal estimate for the mean based on the minimum-variance criterion, the zonotopic filter seeks to guarantee that the true states of a given system are contained into the corresponding estimated membership sets. Two numerical examples illustrate the revisited methods.

Palavras-chave: Unscented Kalman filter; Zonotopic filter; State estimation; Nonlinear systems