Open AccessDerivation of Modified Input Estimation Filter Using Bayesian Framework
Author(s) -
Zhichao Bao,
Qiuxi Jiang,
Qi Ao,
Qiuju Chen
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/677/2/022138
Subject(s) - kalman filter , invariant extended kalman filter , state vector , acceleration , ensemble kalman filter , extended kalman filter , recursive bayesian estimation , fast kalman filter , bayesian probability , filter (signal processing) , computer science , alpha beta filter , tracking (education) , control theory (sociology) , algorithm , filtering problem , mathematics , moving horizon estimation , artificial intelligence , computer vision , physics , psychology , pedagogy , control (management) , classical mechanics
A new approach to derive the modified input estimation is proposed using Bayesian framework. Tracking manoeuvring targets is a tough problem and many algorithms are proposed to deal with it. Among these algorithms, modified input estimation (MIE) technique has been proved to be an effective method. MIE technique treats acceleration as additive input term in the state vector and estimates the original state and acceleration vectors simultaneously with a standard Kalman filter. Analogous to standard Kalman filter, however, the MIE filter equations which have a modification on Kalman gain is given without a cohesive derivation. Using a Bayesian framework, we will present a conceptually cohesive roadmap that starts at first principles and leads directly to derivation of MIE filter equations.