多层神经网络在跟踪式卡尔曼滤波器中的应用

本文将多层神经网络引入跟踪式卡尔曼滤波器，提高了估计的精确度。以前的跟踪式卡尔曼滤波器的估计精度与目标的运动状态有关，当目标的运动不能够用线性状态空间模型描述时，其估计精度将要下降。而多层网络的引入，改善了这一不足。多层神经网络经过训练以后，能够对卡尔曼滤波器的结果进行修正。仿真结果表明，多层神经网络的应用，使估计精度显著提高。

A Improved Tracking Karlman Filter Using a Multilayed Neural network

This paper present a method toimprove the estimation accuracy of a trackingKarlman filter (TKF) by using a multilayed neural network (MNN). Estimation accuracyof the TKF is degraded due to the uncertainties which cannot be expressed by the linearstate-space model given priori.. The MNN capable of leaning an arbltrary so that realized amapping from measurement to the corrections of estimation of TKF. Simullation resultsshow that the estimation accuracy is much improved by using MNN.