An adaptive robustizing approach to kalman filtering

Tsai, Chee; Kurz, L.

doi:10.1016/0005-1098(83)90104-8

Cited by 61 publications

(18 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the performance of error compensation depends on the selection of appropriate parameters that correctly represent practical model deviations at each time point. Tsai and Kurz reported an error compensation method using polynomial fitting [37]. The use of a high-order polynomial may lead to the difficulty in solving state parameters, while the use of a low-order polynomial may result in the low compensation accuracy.…”

Section: Related Workmentioning

confidence: 98%

Windowing-based random weighting fitting of systematic model errors for dynamic vehicle navigation

Gao

Zhong

Wei

et al. 2014

Information Sciences

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 98%

Windowing-based random weighting fitting of systematic model errors for dynamic vehicle navigation

Gao

Zhong

Wei

et al. 2014

Information Sciences

View full text Add to dashboard Cite

“…Though KF is the optimal linear filter, when dealing with non-Gaussian type noise large variances may occur by applying a linear filter, as shown in [16,17,30]. The authors address this problem by using a score function which is dependent both on the probability density function and the realization.…”

Section: Problem Formulation and Bayesian Filteringmentioning

confidence: 99%

A semi-definite programming approach for robust tracking

Shtern

Ben‐Tal

2015

Math. Program.

View full text Add to dashboard Cite

Tracking problems are prevalent in the present day GPS and video systems. The problem of target tracking is a specific case of dynamic linear system estimation with additive noise. The most widely used filter for these systems is the Kalman filter (KF). The optimality of the KF and similar Bayesian filters is guaranteed under particular probabilistic assumptions. However, in practice, and specifically in applications such as tracking, these probabilistic assumptions are not realistic; indeed, the system noise is typically bounded and in fact might be adversarial. For such cases, robust estimation approaches, such as H ∞ filtering and set-value estimation, were introduced with the aim of providing filters with guaranteed worst case performance. In this paper we present an innovative approximated set-value estimator (SVE) which is obtained through a semi-definite programming problem. We demonstrate that our problem is practically tractable even for long time horizons. The framework is extended to include the case of partially statistical noise, thus combining the KF and SVE frameworks. A variation of this filter which applies a rolling window approach is developed, achieving fixed computational cost per-iteration and coinciding with the classical SVE when window size is one. Finally, we present numerical results that show the advantages of this filter when dealing with adversarial noise and compare the performance of the various robust filters with the KF. B Shimrit Shtern

show abstract

“…Under the statistical assumptions described in Tsai and Kurz (1983) and Cross (1990), the prediction and filtering equations of the Kalman Filter can be summarized as follows.…”

Section: Kalman Filtermentioning

confidence: 99%

Real-time deformation monitoring with GPS and Kalman Filter

İnce

Şahin

2014

Earth Planet Sp

View full text Add to dashboard Cite

The main purpose of this research is to develop a real-time GPS monitoring system with the aid of a Kalman Filter for use in an active tectonic region near Istanbul, and its surrounding region. Currently, an ongoing project exists, funded by the World Bank, that monitors deformation in Istanbul and the Marmara Region. Istanbul is one of the largest cities in the world, and is under possible earthquake threat. In order to set up a powerful control system, a surveying and estimation method was designed and the necessary software, called RT-MODS2 (Real-Time Monitoring Of Dynamic Systems 2), was developed. The software reads real-time input data from GPS receivers and performs deformation analyses with the help of the Kalman Filter. Some studies of filtering and deformation analysis were performed in order to detect failures and outliers, and to increase the reliability of the deformation analysis.

show abstract

An adaptive robustizing approach to kalman filtering

Cited by 61 publications

References 19 publications

Windowing-based random weighting fitting of systematic model errors for dynamic vehicle navigation

Windowing-based random weighting fitting of systematic model errors for dynamic vehicle navigation

A semi-definite programming approach for robust tracking

Real-time deformation monitoring with GPS and Kalman Filter

Contact Info

Product

Resources

About