Scholarlink

<p>In aerospace target tracking, the use of inaccurate prior information and external environmental disturbances can degrade tracking accuracy and even lead to filter divergence. To address this issue, this paper proposes a novel adaptive cubature Kalman filter (CKF) incorporating multiple fading factors (VBRCKF-MF). The proposed method first models the measurement noise using the inverse gamma distribution and applies the variational Bayesian (VB) approach to iteratively estimate the measurement noise covariance matrix and the target state. The estimated measurement noise covariance is then incorporated into the computation of multiple fading factors, which are used to adjust the predicted state covariance matrix online. Finally, the local optimal target state is obtained by performing state augmentation based on the updated predicted state covariance and measurement noise covariance matrices.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel adaptive cubature Kalman filter based on multiple fading factors

  • 期刊论文

  • 发表日期：

    2026年7月22日

查看全文
  • Peng Gu,
  • Zhongliang Jing

摘要

In aerospace target tracking, the use of inaccurate prior information and external environmental disturbances can degrade tracking accuracy and even lead to filter divergence. To address this issue, this paper proposes a novel adaptive cubature Kalman filter (CKF) incorporating multiple fading factors (VBRCKF-MF). The proposed method first models the measurement noise using the inverse gamma distribution and applies the variational Bayesian (VB) approach to iteratively estimate the measurement noise covariance matrix and the target state. The estimated measurement noise covariance is then incorporated into the computation of multiple fading factors, which are used to adjust the predicted state covariance matrix online. Finally, the local optimal target state is obtained by performing state augmentation based on the updated predicted state covariance and measurement noise covariance matrices.