Full Record

New Search | Similar Records

Author
Title Comparison of nonlinear filtering techniques
URL
Publication Date
Date Accessioned
Degree MS
Discipline/Department 0133
Degree Level thesis
University/Publisher University of Illinois – Urbana-Champaign
Abstract In a recent work it is shown that importance sampling can be avoided in the particle filter through an innovation structure inspired by traditional nonlinear filtering combined with optimal control formalisms. The resulting algorithm is referred to as feedback particle filter. The purpose of this thesis is to provide a comparative study of the feedback particle filter (FPF). Two types of comparisons are discussed: i) with the extended Kalman filter, and ii) with the conventional resampling-based particle filters. The comparison with Kalman filter is used to highlight the feedback structure of the FPF. Also computational cost estimates are discussed, in terms of number of op- erations relative to EKF. Comparison with the conventional particle filtering ap- proaches is based on a numerical example taken from the survey article on the topic of nonlinear filtering. Comparisons are provided for both computational cost and accuracy.
Subjects/Keywords Filtering; state estimation; particle filtering; Kalman filter; feedback particle filter
Contributors Mehta, Prashant G. (advisor)
Language en
Rights Copyright 2014 Shane Ghiotto
Country of Publication us
Record ID handle:2142/49437
Repository uiuc
Date Indexed 2018-11-19
Grantor University of Illinois at Urbana-Champaign
Issued Date 2014-05-30 16:44:03

Sample Search Hits | Sample Images

…similarities and differences between the methods. The other case evaluated is a comparison of the resampling based particle filtering techniques with the feedback particle filter. The remainder of the thesis is organized as follows: chapter 2 provides…

…comparing these filtering methods. Chapter 5 ends with conclusions and directions for future work. 3 CHAPTER 2 COMPARISON OF FEEDBACK BASED FILTERING APPROACHES This chapter provides an introduction to the algorithms used for the feedback particle filter…

…filter is introduced, section 2.2 provides an introduction to the extended Kalman filter, and section 2.3 then draws comparisons between the two filtering methods, particularly highlighting the feedback structure present in both. 2.1 Feedback Particle

…the EKF though, the FPF is applicable to a general class of nonlinear filtering problems with non-Gaussian posterior distributions. The EKF, as such, is unable to handle these non-Gaussian distributions. 2.1.1 Feedback Particle Filter Algorithm…

…Feedback Structure In recent decades, there have been many important advances in importance sampling based approaches for particle filtering; cf., [4, 2, 10]. A crucial distinction in the feedback particle filter algorithm is that there is no…

…SPDE) of nonlinear filtering, it is conspicuous by its absence in a conventional particle filter. Arguably, the structural aspects of the Kalman filter have been as important as the algorithm itself in design, integration, testing and operation of…

…regularization are discussed. 3.1 Conventional Particle Filters A conventional particle filter is a simulation-based algorithm to approximate the filtering task. At time t, the state of the filter is {(Xti , wti ) : 1 ≤ i ≤ N}: The value Xti…

…CHAPTER 1 INTRODUCTION Filtering and state estimation from noisy measurements is a concept that feeds into many fields such as signal processing, navigation, and control. From global positioning systems (GPS) and target tracking to…

.