信息工程大学学报2026，Vol.27Issue(3)：259-266,274,9.DOI:10.3969/j.issn.1671-0673.2026.03.002
基于注意力增强DDPG的短波协同测向与定位方法
A Cooperative Direction-Finding and Localization Method for Shortwave Based on Attention-Enhanced DDPG
冯祺玥 1唐涛 1张昀普 1赵排航 1陈晓云1
作者信息
摘要
Abstract
Shortwave localization in complex scenarios plays a crucial role in battlefield communica-tions.Existing deep-learning-based intelligent shortwave direction-finding methods mainly rely on manual annotation,and there is a scarcity of high-quality shortwave signal samples.To address the aforementioned challenges,a shortwave autonomous direction-finding and localization method is pro-posed,based on a space-time high-resolution time-frequency representation of shortwave signals and an attention-enhanced deep deterministic policy gradient(DDPG)algorithm.A reinforcement learning environment is first designed based on space-time high-resolution time-frequency representation,along with an agent possessing a hybrid action space.Then,a reward function is designed based on the esti-mated localization results,thereby establishing an observable Markov decision process.Subsequently,by enhancing deep reinforcement learning with an attention mechanism for multi-level non-fine evalua-tion,automatic direction finding and positioning are achieved.This design reduces the need for manual labeling and enables autonomous evolution through simultaneous work and learning,gradually improv-ing the intelligent direction-finding and localization capabilities for shortwave signals.Experimental results show that,comparable localization accuracy and parameter estimation performance are main-tained,while the direction-finding and localization time is improved by approximately 77.7%.关键词
测向定位/马尔可夫决策过程/空时高分辨/混合动作空间/深度确定性策略梯度算法Key words
direction finding/Markov decision process/space-time high-resolution/hybrid action space/deep deterministic policy gradient algorithm分类
信息技术与安全科学引用本文复制引用
冯祺玥,唐涛,张昀普,赵排航,陈晓云..基于注意力增强DDPG的短波协同测向与定位方法[J].信息工程大学学报,2026,27(3):259-266,274,9.
