Improved Strong Tracking Cubature Kalman Filter for Target Tracking

DOI

10.2991/caai-17.2017.35How to use a DOI?

Keywords

cubature Kalman filter; strong tracking filter; fault detection and isolation; numerical stability

Abstract

Cubature Kalman filter (CKF) is a very popular non-linear filter algorithm recently. CKF obtains better numerical stability and accuracy in high dimensional situation compared to UKF. However, in case of process model uncertainty, the performance of CKF will greatly degrade or even provoke divergence. An improved strong tracking CKF (ISTCKF) is proposed to keep the numerical stability and improve the robustness. First, the theoretical framework of strong tracking filter (STF) is combined with CKF. Then, an enhanced fault detection and isolation technique is established to overcome the drawback in STCKF. ISTCKF only performs correction phase when the process model uncertainty is detected and isolated. The ISTCKF is tested and validated via a target tracking model.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shuida Bao
AU  - An Zhang
PY  - 2017/06
DA  - 2017/06
TI  - Improved Strong Tracking Cubature Kalman Filter for Target Tracking
BT  - Proceedings of the 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017)
PB  - Atlantis Press
SP  - 164
EP  - 168
SN  - 1951-6851
UR  - https://doi.org/10.2991/caai-17.2017.35
DO  - 10.2991/caai-17.2017.35
ID  - Bao2017/06
ER  -