The Particle Filter - Application and Theory |
Back |
Abstract: Positioning of moving platforms has been a technical driver for real-time applications of the particle filter. For this reason, we will spend some time to explain several such applications concerning positioning of underwater vessels, cars, and aircraft using geographical information systems (GIS) containing a database with features of the surrounding. In the robotics community, the PF has been developed into one of the main algorithms (fastSLAM) for solving the simultaneous localization and mapping (SLAM) problem. This can be seen as an extension to the aforementioned applications, where the features in the GIS are dynamically detected and updated on the fly. We will also discuss the technical enabler for many applications, the Rao-Blackwellized particle filter (also referred to as the marginalized particle filter). It allows the use of high-dimensional state-space models as long as the (severe) nonlinearities only affect a small subset of the states. In this way, the structure of the model is utilized, so that the particle filter is used to solve the most difficult tasks, and the (extended) Kalman filter is used for the(almost) linear Gaussian states. For more information regarding the research please have a look at: www.control.isy.liu.se/~schon/ |
Type of Seminar: Public Seminar |
Speaker: Dr. Thomas Schön Linköping University, Sweden | |
Date/Time: Apr 22, 2008 17:15 / | |
Location: ETH Zentrum, Building ETZ , Room E6 | |
Contact Person: Prof. John Lygeros | |
File Download: Request a copy of this publication. | |
Biographical Sketch: Thomas Schön was born in Sweden in 1977. He received the B.Sc. degree in Business Administration and Economics in Feb. 2001, the M.Sc. degree in Applied Physics and Electrical Engineering in Feb. 2001 and the Ph.D. degree in Automatic Control in Feb. 2006, all from Linköping University, Linköping, Sweden. He has held visiting positions at the University of Cambridge (UK) and the University of Newcastle (Australia). His research interests are mainly within the areas of signal processing, sensor fusion and system identification, with applications to the automotive and aerospace industry. He is currently a Research Associate at Linköping University. |