Radio Map Construction and Non-cooperative Radiation Source Localization Based on Agents Interaction

ZHOU Zou; DENG Tianrong; QIU Chen; QIU Hongbing

doi:10.12263/DZXB.20251269

您当前的位置：

首页 >

文章列表页 >

Radio Map Construction and Non-cooperative Radiation Source Localization Based on Agents Interaction

更新时间：2026-06-15

- Radio Map Construction and Non-cooperative Radiation Source Localization Based on Agents Interaction
- ACTA ELECTRONICA SINICA Pages: 1-14(2026)
- 作者机构：
  
  1.桂林电子科技大学认知无线电与信息处理省部共建教育部重点实验室，广西桂林 541004
  2.广西人工智能学院，广西南宁 530201
  3.鹏城实验室宽带通信部，广东深圳 518055
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62101293);Guangxi Natural Science Foundation of China(2023GXNSFAA026058);The Director Fund project of the Key Laboratory of Cognitive Radio and Information Processing of Ministry of Education(CRKL220110)
- DOI：10.12263/DZXB.20251269
  CLC： TN92;TP18
- Received：19 February 2026，
  
  Accepted：19 March 2026，
  
  Online First：15 June 2026，
- 稿件说明：
移动端阅览
ZHOU Zou, DENG Tianrong, QIU Chen, et al. Radio Map Construction and Non-cooperative Radiation Source Localization Based on Agents Interaction[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-14.
DOI：

ZHOU Zou, DENG Tianrong, QIU Chen, et al. Radio Map Construction and Non-cooperative Radiation Source Localization Based on Agents Interaction[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-14. DOI： 10.12263/DZXB.20251269.

摘要

无线电地图构建与非合作辐射源定位是电磁环境精确认知与动态管控的核心任务，二者高度耦合、相互制约。本文借鉴认知学习与具身智能理论，提出基于智能体协同交互、智能内生的无线电地图构建与辐射源定位双任务统一架构，实现感知-认知-行为的反馈闭环。首先利用众包概率共识思想，结合高斯回归过程与二维位置编码，将多智能体的离散稀疏采样数据转换为包含连续信号场的预测分布、几何拓扑及辐射源目标空间位置存在概率估计的空间注意力图，建立多智能体关于辐射源目标的共识感知先验；在此基础上，构建多智能体统一语义空间中的辐射源目标一致性联合表征，利用多头自注意力机制设计任务驱动和目标驱动的智能体交互策略，以同时完成无线电地图构建和非合作辐射源定位双任务；基于近端策略优化强化学习方法，设计双任务信息交互反馈策略，实现自组织与自学习，以形成感知、认知与交互决策的具身行为闭环。仿真结果验证了所提方案的可行性：在5%稀疏采样条件下，本系统对无线电地图构建与辐射源定位双任务进行协同优化，相较于独立执行单任务，无线电地图构建与辐射源定位的精度分别提升18.2%和43.5%。其中，无线电地图构建精度（RMSE）相比克里金算法和全卷积深度补全自动编码器分别提升了60.95%和32.55%；辐射源定位精度相较于传统的RSS定位基准算法，定位误差降低了65.7%，扩展到10 km × 10 km的典型定位场景时，辐射源定位任务仍能稳定维持在1.2%以内的相对精度。

Abstract

Radio map construction and non-cooperative emitter localization are pivotal tasks for accurate perception and dynamic control of the electromagnetic environment

characterized by high coupling and mutual constraints. Drawing on cognitive learning and embodied intelligence theories

this paper proposes a unified dual-task framework for radio map construction and emitter localization featuring multi-agent collaborative interaction and endogenous intelligence

thereby establishing a "perception-cognition-action" feedback loop. First

leveraging the concept of crowdsourced probabilistic consensus

we integrate Gaussian Process Regression (GPR) with 2D-positional encoding to transform discrete sparse sampling data from multiple agent into spatial attention maps. These maps encompass continuous signal field predictive distributions

geometric topologies

and probability estimates of emitter spatial presence

establishing a consensus perceptual prior regarding the target emitters. Building upon this

a consistent joint representation for emitters is constructed within a unified multi-agent semantic space. A multi-head self-attention mechanism is then utilized to design task-driven and target-driven agent interaction strategies

enabling the simultaneous execution of both tasks. Furthermore

a dual-task information interaction feedback strategy based on Proximal Policy Optimization (PPO) is designed to achieve self-organization and self-learning

forming an embodied behavioral loop of perception

cognition

and interactive decision-making. Simulation results validate the feasibility and superiority of the proposed scheme. Under a 5% sparse sampling condition

the synergistic optimization of both tasks achieves accuracy improvements of 18.2% and 43.5% for radio map construction and emitter localization

respectively

compared to independent task execution. Specifically

the RMSE of radio map construction improves by 60.95% and 32.55% over Kriging and Full Convolutional Auto-Encoder

respectively. Meanwhile

the localization error is reduced by 65.7% compared to the RSS-based baseline

maintaining a stable relative accuracy within 1.2% even when extended to a 10 km×10 km large-scale scenario.

关键词

Keywords

references

Zhang Shoubin , Li Zhimeng , Li Haojin , et al . Novel radio environment map construction scheme for 3-D and full band for modern internet of things applications [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 9 ): 12419 - 12432 . DOI: 10.1109/jiot.2024.3520611 http://dx.doi.org/10.1109/jiot.2024.3520611

Zhang Shoubin , Wang Hongjun , Shen Zhexian , et al . Multiple radiation source localization in IoT: A radio-map-assisted scheme [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 20 ): 42484 - 42500 . DOI: 10.1109/jiot.2025.3592781 http://dx.doi.org/10.1109/jiot.2025.3592781

Tsoulos G , Athanasiadou G , Zarbouti D , et al . Empirical analysis of 5G deployments: A comparative assessment of network performance with 4G [J ] . AEU-International Journal of Electronics and Communications , 2024 , 186 : 155479 . DOI: 10.1016/j.aeue.2024.155479 http://dx.doi.org/10.1016/j.aeue.2024.155479

Jaiswal R K , Elnourani M , Deshmukh S , et al . Leveraging transfer learning for radio map estimation via mixture of experts [J ] . IEEE Transactions on Cognitive Communications and Networking , 2026 , 12 : 846 - 863 . DOI: 10.1109/tccn.2025.3570469 http://dx.doi.org/10.1109/tccn.2025.3570469

Yu Weijia , Du Jianhe , Chen Yuanzhi , et al . Vehicle localization based on Bayesian tensor decomposition in intelligent transportation systems [J ] . IEEE Transactions on Intelligent Transportation Systems , 2025 , 26 ( 10 ): 16204 - 16221 . DOI: 10.1109/tits.2025.3582038 http://dx.doi.org/10.1109/tits.2025.3582038

Kiouvrekis Y , Panagiotakopoulos T , Nousi E , et al . Explainable machine learning for radio environment mapping: An intelligent system for electric field strength monitoring [J ] . IEEE Access , 2025 , 13 : 75104 - 75122 . DOI: 10.1109/access.2025.3564650 http://dx.doi.org/10.1109/access.2025.3564650

Xhafa A , Fabra F , Egea-Roca D , et al . Experimental investigation of AoA estimation and antenna calibration with 5G NR signals using USRP devices [J ] . IEEE Transactions on Instrumentation and Measurement , 2025 , 74 : 5504515 . DOI: 10.1109/tim.2025.3569347 http://dx.doi.org/10.1109/tim.2025.3569347

Zhang Chengjie , Han Xinyang , Kong He , et al . Optimal sensor placement for full-set TDOA localization accounting for sensor location errors [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2025 , 61 ( 4 ): 10944 - 10950 . DOI: 10.1109/taes.2025.3563140 http://dx.doi.org/10.1109/taes.2025.3563140

Kim J . Source localization based on FDOA and TDOA with bounded sensor location errors and changing carrier frequency [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 12 ): 22478 - 22488 . DOI: 10.1109/jiot.2025.3552540 http://dx.doi.org/10.1109/jiot.2025.3552540

Fabris A , Rayel O K , Rebelatto J L , et al . AoA and RSSI-based BLE indoor positioning system with Kalman filter and data fusion [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 11 ): 15348 - 15359 . DOI: 10.1109/jiot.2025.3530866 http://dx.doi.org/10.1109/jiot.2025.3530866

Ko C H , Wu S H . A framework for proactive indoor positioning in densely deployed WiFi networks [J ] . IEEE Transactions on Mobile Computing , 2020 , 21 ( 1 ): 1 - 15 .

Yoo J . Multiple fingerprinting localization by an artificial neural network [J ] . Sensors , 2022 , 22 ( 19 ): 7505 . DOI: 10.3390/s22197505 http://dx.doi.org/10.3390/s22197505

Alrabaee S , Debbabi M , Wang Lingyu . A survey of binary code fingerprinting approaches: Taxonomy, methodologies, and features [J ] . ACM Computing Surveys (CSUR) , 2023 , 55 ( 1 ): 19.1 - 19.41 . DOI: 10.1145/3486860 http://dx.doi.org/10.1145/3486860

Chen Qidong , Liu Rui , Yan Qiuzhen , et al . Localization of multiple GNSS interference sources based on target det ection in C/N 0 distribution maps [J ] . Remote Sensing , 2025 , 17 ( 15 ): 2627 . DOI: 10.3390/rs17152627 http://dx.doi.org/10.3390/rs17152627

Liu Jiayu , Liu Xiaodong , Liang Hongtao , et al . A data-and-semantic dual-driven intelligent inference framework for simultaneously spectrum map construction and signal source localization [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 12 ): 18750 - 18764 . DOI: 10.1109/jiot.2025.3556727 http://dx.doi.org/10.1109/jiot.2025.3556727

Zhang Songyang , Yu Tianhang , Choi B , et al . Radiomap inpainting for restricted areas based on propagation priority and depth map [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 8 ): 9330 - 9344 . DOI: 10.1109/twc.2024.3360872 http://dx.doi.org/10.1109/twc.2024.3360872

Feng Bin , Zheng Meng , Liang Wei , et al . A recent survey on radio map estimation methods for wireless networks [J ] . Electronics , 2025 , 14 ( 8 ): 1564 . DOI: 10.3390/electronics14081564 http://dx.doi.org/10.3390/electronics14081564

Zhao Jianli , Feng Xingzhao , Fang Sheng , et al . Tensor completion via nonlocal tensor wheel decomposition for hyperspectral image recovery [J ] . IEEE Geoscience and Remote Sensing Letters , 2025 , 22 : 5504905 . DOI: 10.1109/lgrs.2025.3569305 http://dx.doi.org/10.1109/lgrs.2025.3569305

Chen Guokai , Liu Yongxiang , Zhang Jianzhao , et al . GPRT: A Gaussian process regression-based radio map construction method for rugged terrain [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 13 ): 23905 - 23920 . DOI: 10.1109/jiot.2025.3554507 http://dx.doi.org/10.1109/jiot.2025.3554507

Ma Yilin , Zhang Chiya , He Chunlong , et al . Radio map estimation using a CycleGAN-based learning framework for 6G wireless communication [J ] . Digital Communications and Networks , 2025 , 11 ( 6 ): 1822 - 1830 . DOI: 10.1016/j.dcan.2025.08.001 http://dx.doi.org/10.1016/j.dcan.2025.08.001

Maiti P , Mitra D . Ordinary kriging interpolation for indoor 3D REM [J ] . Journal of Ambient Intelligence and Humanized Computing , 2023 , 14 ( 10 ): 13285 - 13299 . DOI: 10.1007/s12652-022-03784-2 http://dx.doi.org/10.1007/s12652-022-03784-2

Teganya Y , Romero D . Deep completion autoencoders for radio map estimation [J ] . IEEE Transactions on Wireless Communications , 2022 , 21 ( 3 ): 1710 - 1724 . DOI: 10.1109/twc.2021.3106154 http://dx.doi.org/10.1109/twc.2021.3106154

Wang Jie , Zhu Qiuming , Lin Zhipeng , et al . Sparse Bayesian learning-based 3-D radio environment map construction: Sampling optimization, scenario-dependent dictionary construction, and sparse recovery [J ] . IEEE Transactions on Cognitive Communications and Networking , 2024 , 10 ( 1 ): 80 - 93 . DOI: 10.1109/tccn.2023.3319539 http://dx.doi.org/10.1109/tccn.2023.3319539

Chen Qi , Huang Ming , Yang Jingjing . REM-Net+: Quantified 3D radio environment map construction guided by radio propagation model [J ] . IEEE Transactions on Vehicular Technology , 2026 , 75 ( 4 ): 6351 - 6362 . DOI: 10.1109/tvt.2025.3623917 http://dx.doi.org/10.1109/tvt.2025.3623917

Čolaković A . IoT systems modeling and performance evaluation [J ] . Computer Science Review , 2023 , 50 : 100598 . DOI: 10.1016/j.cosrev.2023.100598 http://dx.doi.org/10.1016/j.cosrev.2023.100598

陈兆 , 王玫 , 周陬 , 等 . 基于多参数融合的超宽带基站布设优化方法 [J ] . 电子学报 , 2023 , 51 ( 10 ): 2855 - 2865 .

Chen Zhao , Wang Mei , Zhou Zou , et al . Optimization method for ultra-wideband base station configuration based on multi-parameter fusion [J ] . Acta Electronica Sinica , 2023 , 51 ( 10 ): 2855 - 2865 . (in Chinese)

周陬 , 王若楠 , 纪冰辉 , 等 . 一种基于感知阵型的无人机蜂群动态侦察任务调度系统及方法 : CN202110700086.9 [P ] . 2024-01-09 .

Zhou Zou , Wang Ruonan , Ji Binghui , et al . Unmanned aerial vehicle swarm dynamic reconnaissance task scheduling system and method based on perceptual formation : CN202110700086.9 [P ] . 2024-01-09 . (in Chinese)

Zhao Yue , Cheng Nan , Li Zan , et al . An efficient sensor selection algorithm for TDOA localization with estimated source position [C ] // ICC 2022-IEEE International Conference on Communications . Piscataway : IEEE , 2022 : 871 - 876 . DOI: 10.1109/icc45855.2022.9838504 http://dx.doi.org/10.1109/icc45855.2022.9838504

Li Xianliang , Xu Sheng , Ho K C . Time-of-arrival simultaneous sensor and target localization with dynamic optimal sensor placements [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2025 , 61 ( 5 ): 12663 - 12677 . DOI: 10.1109/taes.2025.3574055 http://dx.doi.org/10.1109/taes.2025.3574055

Liu Wenjie , Chen Junting . UAV-aided radio map construction exploiting environment semantics [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 9 ): 6341 - 6355 . DOI: 10.1109/twc.2023.3241845 http://dx.doi.org/10.1109/twc.2023.3241845

Wang Xuegang , Wang Fanggang , He Boxiang . Radio environment map reconstruction via tensor completion: Bayesian and semantic approaches [J ] . IEEE Transactions on Vehicular Technology , 2025 , 74 ( 5 ): 7897 - 7913 . DOI: 10.1109/tvt.2025.3531124 http://dx.doi.org/10.1109/tvt.2025.3531124

Gao Qianhao , Zhu Qiuming , Lin Zhipeng , et al . Time-variant radio map reconstruction with optimized distributed sensors in dynamic spectrum environments [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 12 ): 20927 - 20941 . DOI: 10.1109/jiot.2025.3545542 http://dx.doi.org/10.1109/jiot.2025.3545542

Wu Wei , Chen Yu , Zhou Fuhui , et al . Semantic communications for efficient spectrum maps construction and signal source location [J ] . IEEE Wireless Communications Letters , 2024 , 13 ( 12 ): 3266 - 3270 . DOI: 10.1109/lwc.2024.3398025 http://dx.doi.org/10.1109/lwc.2024.3398025

Juang J C , Tsai Y F . Analysis of GNSS interference events based on TRITON GNSS-R measurements [J ] . NAVIGATION: Journal of the Institute of Navigation , 2025 , 72 ( 4 ): navi. 720 . DOI: 10.33012/navi.720 http://dx.doi.org/10.33012/navi.720

Ramchandra A R , Skurdal A , Ranganathan P , et al . Detecting GPS interference using automatic dependent surveillance-broadcast data [J ] . Electronics , 2024 , 13 ( 16 ): 3145 . DOI: 10.3390/electronics13163145 http://dx.doi.org/10.3390/electronics13163145

Li Deyi . Cognitive physics: The enlightenment by Schrödinger, Turing, and Wiener and beyond [J ] . Intelligent Computing , 2023 , 2 : 0009 . DOI: 10.34133/icomputing.0009 http://dx.doi.org/10.34133/icomputing.0009

An Zhulin , Yu Xinqing , Wang Chu , et al . Embodied intelligence: Recent advances and future perspectives [J ] . The Innovation Informatics , 2025 , 1 ( 1 ): 100008 . DOI: 10.59717/j.xinn-inform.2025.100008 http://dx.doi.org/10.59717/j.xinn-inform.2025.100008

Ma Nan , Pan Jia , Liu Yongjin , et al . Embodied interactive intelligence towards autonomous driving [J ] . Engineering , 2026 , 59 : 337 - 351 . DOI: 10.1016/j.eng.2025.09.032 http://dx.doi.org/10.1016/j.eng.2025.09.032

阮天宸 , 吴启晖 , 赵世瑾 , 等 . 认知学习: 电磁频谱空间机器学习新范式 [J ] . 电子学报 , 2023 , 51 ( 6 ): 1430 - 1442 .

Ruan Tianchen , Wu Qihui , Zhao Shijin , et al . Cognitive learning: A new paradigm for machine learning in electromagnetic spectrum environment [J ] . Acta Electronica Sinica , 2023 , 51 ( 6 ): 1430 - 1442 . (in Chinese)

Obayashi N , Abdulali A , Iida F , et al . Embodied intelligence paradigm for human-robot communication [J ] . Science Robotics , 2025 , 10 ( 105 ): eads8528 . DOI: 10.1126/scirobotics.ads8528 http://dx.doi.org/10.1126/scirobotics.ads8528

Wan Zishen , Qian Jiayi , Du Yuhang , et al . Generative AI in embodied systems: System-level analysis of performance, efficiency and scalability [C ] // 2025 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) . Piscataway : IEEE , 2025 : 26 - 37 . DOI: 10.1109/ispass64960.2025.00013 http://dx.doi.org/10.1109/ispass64960.2025.00013

Palar P S , Shimoyama K . Efficient global optimization with ensemble and selection of kernel functions for engineering design [J ] . Structural and Multidisciplinary Optimization , 2019 , 59 ( 1 ): 93 - 116 . DOI: 10.1007/s00158-018-2053-9 http://dx.doi.org/10.1007/s00158-018-2053-9

Roh B , Shin W , Kim I , et al . Spatially consistent representation learning [C ] // Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 1144 - 1153 . DOI: 10.1109/cvpr46437.2021.00120 http://dx.doi.org/10.1109/cvpr46437.2021.00120

Gudmundson M . Correlation model for shadow fading in mobile radio systems [J ] . Electronics Letters , 1991 , 27 ( 23 ): 2145 - 2146 . DOI: 10.1049/el:19911328 http://dx.doi.org/10.1049/el:19911328

Mao Guoqiang , Fidan B , Anderson B D O . Wireless sensor network localization techniques [J ] . Computer Networks , 2007 , 51 ( 10 ): 2529 - 2553 . DOI: 10.1016/j.comnet.2006.11.018 http://dx.doi.org/10.1016/j.comnet.2006.11.018

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An Embodied Intelligence-Based Method for Single-UAV Tracking of Maneuvering Radiation Sources in Unknown Environments

Embodied-Intelligence-Driven Electromagnetic Spectrum Resource Allocation for Low-Altitude UAV Data Offloading and Beam Tracking

Image Classification Network with Attenuation Disentangling Mechanism

A Human-Body Local Specific Absorption Rate Evaluation Algorithm in Indoor Complex Electromagnetic Environments

The Inevitability of Side-Channel Leakage in Encrypted Traffic

Related Author

LIANG Hongtao

FU Yangmeizi

WAN Yiyao

LIU Xiaodong

WU Qihui

ZHAO Zhongling

HE Hao

SONG Tian

Related Institution

College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics

School of Information Engineering, Nanchang University

School of Cyberspace Science and Technology, Beijing Institute of Technology of China

The State Key Laboratory of Integrated Service Networks, Xidian University

⁰