基于轴向注意力的UUV非合作目标状态估计方法  

An Axial Attention-Based UUV Non-Cooperative Target State Estimation Method

作　　者：林常见 程玉虎 王雪松 刘玉豪 LIN Changjian;CHENG Yuhu;WANG Xuesong;LIU Yuhao(School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116)

机构地区：[1]中国矿业大学信息与控制工程学院,徐州221116

出　　处：《系统科学与数学》2024年第12期3477-3490,共14页Journal of Systems Science and Mathematical Sciences

基　　金：国家自然科学基金(62303467);江苏省自然科学基金(BK20231061)资助课题。

摘　　要：为提高无人水下航行器(unmanned underwater vehicle,UUV)对非合作目标状态估计的准确性,文章提出了一种基于轴向注意力的目标状态估计方法,分析基于声呐观测的UUV非合作目标状态估计机理,将该问题的非马尔可夫状态空间模型转换为带有记忆的一阶马尔可夫状态空间模型,从而构建递归滤波模型.针对前视声呐观测的不可靠性、目标运动的不可预测性,提出一种基于轴向注意力Transformer的非合作目标状态多步预测网络,描述非线性观测下,非合作目标相对声呐的复杂运动过程.针对观测的不稳定性及后验分布的未知性,基于Monte Carlo近似推断原理,利用该多步预测网络将目标观测状态空间中的采样粒子映射到目标预测状态空间,构建基于轴向注意力的目标状态估计方法.仿真结果表明了所提方法对不确定输入的适应性和鲁棒性.To improve the accuracy of unmanned underwater vehicle(UUV)state estimation of non-cooperative targets,an axial attention-based target state estimation method is proposed in this paper.The state estimation mechanism of the UUV non-cooperative target based on sonar observation is analyzed.The non-Markov state-space model of the problem is transformed into a first-order Markov state-space model with memory,and a recursive filtering model is constructed.Aiming at the unreliability of forward-looking sonar observation and the unpredictability of target motion,a multi-step prediction network based on transformer is proposed to describe the complex motion process of non-cooperative target relative to sonar under nonlinear observation.Aiming at the instability of observation and the unpredictability of posterior distribution,based on the Monte Carlo approximate inference principle,the multi-step prediction network is used to map the particles in the target measurement state space to the target prediction state space,and a non-cooperative target state estimation algorithm based on the axial attention is constructed.The simulation results show that the adaptability and robustness of the proposed method to uncertain inputs.

关 键 词：目标状态估计 轴向注意力 无人水下航行器 前视声呐 非合作目标 

分 类 号：U674.941[交通运输工程—船舶及航道工程] U666.7[交通运输工程—船舶与海洋工程]