"A New Approach to Optimal Filter Design for Nonlinear Systems"

Dr. Carlo Novara, Dipartimento di Automatica e Informatica, Politecnico di Torino, Italy

July 5th (Tuesday), 3:00pm
Harold Frank Hall (HFH), Rm 4164

Optimal filters for nonlinear systems are in general difficult to derive or implement. The common approach is to use approximate solutions such as extended Kalman filters, ensemble filters or particle filters. However, no optimality properties can be guaranteed by these approximations, and even the stability of the estimation error cannot often be ensured. Another relevant issue is that, in most practical situations, the system to filter is not known, and a two-step procedure is adopted, based on model identification from data and filter design from the identified model. However, the filter designed by means of this procedure may display large performance deteriorations in the case of modeling errors. In this talk, a new approach overcoming these issues will be proposed, allowing the design of optimal filters for nonlinear systems in both the cases of known and unknown system. The approach is based on the direct filter design from a set of data generated by the system. Simulated data are used if the system equations are known, experimental data are used otherwise. A bound on the number of data necessary to ensure a given filter accuracy will be also provided, showing that the proposed approach is not affected by the curse of dimensionality. Two examples will be finally presented: the first, involving simulated data, regards the estimation of the Chua chaotic system; the second, involving real data, is about estimation of vehicle yaw rate.

About Dr. Carlo Novara:

Carlo Novara received the Laurea degree in Physics from Facoltà di Scienze M.F.N., Università di Torino in 1996 and the Ph.D. degree in Computer and System Engineering from Politecnico di Torino in 2002. He has been carrying out his research activity at Dipartimento di Automatica e Informatica of Politecnico di Torino since 1998, where he is now Assistant Professor. He held a visiting research position at the University of California, Berkeley in 2001 and 2004. He has participated in several national and international research projects, also in partnership with private companies. He is author of approximately 60 scientific papers, published in international journals and conference proceedings. He has organized several invited sessions in international conferences. His research interests include nonlinear system identification, filter design, system inversion and control from data, and automotive, environmental and sustainable energy applications.

Hosted by: CCDC Seminar