Methoden vergleichen

	Robuster Kalman-Filter	Partikelfilter (Sequentieller Monte-Carlo-Algorithmus)
Fachgebiet	Bayes-Statistik	Bayes-Statistik
Familie	Bayesian methods	Bayesian methods
Entstehungsjahr	1977	1993
Urheber	Derived from Kalman (1960); robust extensions developed by Masreliez, Martin, and others from the 1970s onward	Gordon, Salmond & Smith
Typ	Sequential Bayesian state estimator with robustified update step	Sequential Monte Carlo estimator
Wegweisende Quelle	Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 82(1), 35-45.	Gordon, N. J., Salmond, D. J., & Smith, A. F. M. (1993). Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proceedings F (Radar and Signal Processing), 140(2), 107–113.
Aliasnamen	RKF, heavy-tailed Kalman filter, outlier-robust Kalman filter, robust state estimation	SMC, sequential Monte Carlo, bootstrap filter, condensation algorithm
Verwandt	5	4
Zusammenfassung	The Robust Kalman Filter is an extension of the classical Kalman filter designed to maintain reliable state estimation when observations or process noise depart from the Gaussian assumption — particularly when data contain outliers, heavy-tailed distributions, or gross errors. By replacing or downweighting the standard least-squares update with influence-limited or M-estimation-based corrections, it prevents a single anomalous measurement from distorting the entire state estimate.	The particle filter, introduced by Gordon, Salmond, and Smith in 1993, is a sequential Monte Carlo algorithm that approximates the Bayesian filtering distribution for nonlinear and non-Gaussian state-space models. Rather than tracking a single best estimate, it maintains a cloud of N weighted random samples — particles — that collectively represent the full posterior distribution of a hidden state at each point in time as new observations arrive.