带输入噪声的高斯过程扩展目标跟踪算法  

Gaussian process extended target tracking with input noise

作　　者：任磊 郭云飞[1] REN Lei;GUO Yunfei(School of Automation,Hangzhou Dianzi University,Hangzhou Zhejiang 310018,China)

机构地区：[1]杭州电子科技大学自动化学院,杭州310018

出　　处：《杭州电子科技大学学报（自然科学版）》2022年第2期41-48,95,共9页Journal of Hangzhou Dianzi University：Natural Sciences

基　　金：浙江省自然科学基金重点资助项目(LZ20F010002)。

摘　　要：传统的基于高斯过程的扩展目标跟踪(Gaussian Process Extended Target Tracking,GP-ETT)算法通常将高斯过程的输入视为精确值,输入不确定性不可忽略时,引起跟踪性能的降低。针对这一问题,定量推导了GP-ETT算法中GP输入噪声的前二阶矩,提出基于泰勒级数与数值近似的3种带输入噪声的GP-ETT算法,并求得理想环境下带输入噪声的GP-ETT最优理论性能界。仿真结果表明,改进算法的马氏距离更小,得到的性能界更合理。In the traditional Extended target tracking(ETT)based on Gaussian Process,the GP input is assumed to be known accurately,that will degrade the tracking performance when the input uncertainty occurs.In order to address this problem,the first two moments of the GP input in the GP-ETT is derived in this paper.Then,based on the Taylor series expansion and the numerical approximation,three modified GP-ETT methods are proposed.Finally,the optimal theorical performance bound of GP-ETT with input noise is derived under the ideal conditions.Simulation results show that the proposed GP-ETT method achieves a smaller Mahalanobis distance and the derived performance bound is more reasonable.

关 键 词：扩展目标跟踪 高斯过程 输入噪声 克拉美罗下界 误差传递 

分 类 号：TN953[电子电信—信号与信息处理]