| 一种基于神经网络和UKF的自适应目标误差配准方法 |
| |
| 引用本文： | 刘宇,陈昕,王运锋,刘洪.一种基于神经网络和UKF的自适应目标误差配准方法[J].四川大学学报(工程科学版),2012,44(3):101-105. |
| |
| 作者姓名： | 刘宇 陈昕 王运锋 刘洪 |
| |
| 作者单位： | 1. 四川大学计算机学院,四川成都,610064
2. 海军空管办,北京,100071 |
| |
| 摘 要： | 针对多传感器数据融合的误差配准问题,提出了一种自适应的误差配准方法。该方法使用无迹卡尔曼滤波方法训练神经网络,在偏差先验模型未知的条件下,通过学习待配准目标量测与配准目标之间的误差变化,实时估计配准误差并同时将其应用于目标状态估计。仿真实验表明,该方法能够实时有效地估计目标配准误差和目标状态。
|
| 关 键 词： | 误差配准 神经网络 无迹卡尔曼滤波 |
| 收稿时间： | 2011/10/13 0:00:00 |
| 修稿时间： | 3/26/2012 7:10:11 PM |
An Adaptive Target Error Registration Based on Neural Networks and UKF |
| |
| Liu Yu,Chen Xin,Wang Yunfeng and Liu Hong.An Adaptive Target Error Registration Based on Neural Networks and UKF[J].Journal of Sichuan University (Engineering Science Edition),2012,44(3):101-105. |
| |
| Authors: | Liu Yu Chen Xin Wang Yunfeng and Liu Hong |
| |
| Affiliation: | School of Computer Sci.,Sichuan Univ.;ATC System Office of Navy;School of Computer Sci.,Sichuan Univ.;School of Computer Sci.,Sichuan Univ. |
| |
| Abstract: | In this paper, an adaptive target error registration method based on Neural Networks(NN) and Unscented Kalman Filter(UKF) is proposed. The method applied UKF training neural Networks. In case of prior model of bias unknown, the method learned the difference between unregistered target measurements and registered track and estimated the registered error and target state real time. The simulation results showed that the effectiveness of the method. |
| |
| Keywords: | error registration Neural Networks Unscented Kalman Filter(UKF) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《四川大学学报(工程科学版)》浏览原始摘要信息 |
|
点击此处可从《四川大学学报(工程科学版)》下载全文 |
