基于卡尔曼一致性滤波的最优平滑

Optimal smoothers based on Kalman Consensus Filters

文章提出一种运用于无线传感网络中目标跟踪的平滑算法,并讨论了在3种平滑框架下本算法的具体运用。该算法以无迹卡尔曼一致性滤波算法交换节点间滤波估计值,使节点信息趋于一致,以此优化后的滤波估计值作为RauchTung-Striebel(RTS)平滑方法的初始值。针对高斯最优平滑的3种框架具有不同的应用场合,分别阐述3种框架下的基于一致性滤波的无迹RTS平滑算法。仿真实验结果表明,该算法提高了整个跟踪过程的精度。

In this paper,a smoothing algorithm which is applied to target tracking in wireless sensor network was presented,then,we discussed the application area of the three smoothing algorithm forms.The algorithm uses a neighbor＇s information with the Unscented Kalman consensus filters to reach a consensus,and then the obtained Kalman consensus filters＇ value will be the initial value of the Rauch-Tung-Striebel smoother.Because the three optimal smoothing forms was suitable for different applications,we elaborated three optimal smoothing forms of the Unscented Rauch-Tung-Striebel Smoother based on Kalman consensus filter.Simulation results were provided to demonstrate the algorithm which improves the accuracy of the whole tracking.