Title :
Non-Gaussian models in particle filters
Author :
Piotr Kozierski;Talar Sadalla;Dariusz Horla
Author_Institution :
Faculty of Electrical Engineering, Institute of Control and Information Engineering, Poznan University of Technology, Piotrowo street 3a, 60-965 Poznan
Abstract :
The impact of the usage another than the Gaussian probability density functions in transition and measurement models has been verified in the article. Cases, in which wrong models have been assumed, also have been taken into account. Simulations have been performed for two different objects. Based on the obtained results, it can be said that in some cases incorrect modelling can allow the best estimation quality.
Keywords :
"Modeling","Atmospheric measurements","Particle measurements","Particle filters","Probability density function","Density measurement","Kalman filters"
Conference_Titel :
Methods and Models in Automation and Robotics (MMAR), 2015 20th International Conference on
DOI :
10.1109/MMAR.2015.7283858
