Robust Kalman tracking and smoothing with propagating and non-propagating outliers

DOI10.48550/ARXIV.1204.3358MaRDI QIDQ123767zbMATH OpenOpenAlexFDO

Authors Peter Ruckdeschel, Bernhard Spangl, Daria Pupashenko, P. Ruckdeschel, Bernhard Spangl, Daria Pupashenko

Publication date 16 April 2012

Published in Statistical Papers (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1204.3358

zbMATH Keywords

robustnessextended Kalman filterKalman filteringKalman smootherpropagating outliers

Mathematics Subject Classification ID

Filtering in stochastic control theory (93E11) Robustness and adaptive procedures (parametric inference) (62F35)

Abstract: A common situation in filtering where classical Kalman filtering does not perform particularly well is tracking in the presence of propagating outliers. This calls for robustness understood in a distributional sense, i.e.; we enlarge the distribution assumptions made in the ideal model by suitable neighborhoods. Based on optimality results for distributional-robust Kalman filtering from Ruckdeschel[01,10], we propose new robust recursive filters and smoothers designed for this purpose as well as specialized versions for non-propagating outliers. We apply these procedures in the context of a GPS problem arising in the car industry. To better understand these filters, we study their behavior at stylized outlier patterns (for which they are not designed) and compare them to other approaches for the tracking problem. Finally, in a simulation study we discuss efficiency of our procedures in comparison to competitors.

Recommendations

• Approaches for the robustification of Kalman filters
• Robust Kalman filter for rank deficient observation models
• scientific article; zbMATH DE number 1036036
• Robust and Trend-Following Student's t Kalman Smoothers
• Outlier-robust Kalman filters with mixture correntropy

Cites work

• scientific article; zbMATH DE number 3909587 (Why is no real title available?)
• scientific article; zbMATH DE number 3954047 (Why is no real title available?)
• scientific article; zbMATH DE number 4064318 (Why is no real title available?)
• scientific article; zbMATH DE number 53439 (Why is no real title available?)
• scientific article; zbMATH DE number 61455 (Why is no real title available?)
• scientific article; zbMATH DE number 502963 (Why is no real title available?)
• scientific article; zbMATH DE number 718724 (Why is no real title available?)
• scientific article; zbMATH DE number 3437452 (Why is no real title available?)
• scientific article; zbMATH DE number 3395249 (Why is no real title available?)
• AN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHM
• An extension of the SRIF Kalman filter
• Approaches for the robustification of Kalman filters
• Exponential smoothing for time series with outliers
• Ideal spatial adaptation by wavelet shrinkage
• Influence functionals for time series (with discussion)
• Minimax-robust prediction of discrete time series
• Rejection of Outliers
• Repeated median and hybrid filters
• Robust Estimation of a Location Parameter
• Robust Kalman filter in discrete time
• Robust bayesian estimation for the linear model and robustifying the Kalman filter
• Robust forecasting with exponential and Holt-Winters smoothing
• Robust recursive estimation in the presence of heavy-tailed observation noise
• Robust techniques for signal processing: A survey
• State space and hidden Markov models
• Statistical Analysis of Financial Data in S-Plus
• The cost of not knowing the radius

Cited in

(10)

• A semi-definite programming approach for robust tracking
• scientific article; zbMATH DE number 2045484 (Why is no real title available?)
• Conditionally Gaussian random sequences for an integrated variance estimator with correlation between noise and returns
• Outlier-robust Kalman filtering framework based on statistical similarity measure
• RobKF
• Output outlier robust state estimation
• Real Time Anomaly Detection And Categorisation
• Robust estimation of linear state space models
• Robust Two-Step Wavelet-Based Inference for Time Series Models
• Jump-diffusion risk-sensitive benchmarked asset management with traditional and alternative data

Describes a project that uses

Uses Software

• robfilter
• MASS (R)
• mvtnorm
• CRAN
• S-PLUS
• R

This page was built for publication: Robust Kalman tracking and smoothing with propagating and non-propagating outliers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q123767)