Uncertainty-Driven UAV Active Sensing for Radio Map Construction in Dense Urban Environments

ZHANG Han; HAN Yu; MENG Lingxin; YAO Mengchen; CHEN Hanhui

doi:10.12263/DZXB.20260052

您当前的位置：

首页 >

文章列表页 >

Uncertainty-Driven UAV Active Sensing for Radio Map Construction in Dense Urban Environments

更新时间：2026-06-08

- Uncertainty-Driven UAV Active Sensing for Radio Map Construction in Dense Urban Environments
- ACTA ELECTRONICA SINICA Pages: 1-12(2026)
- 作者机构：
  
  哈尔滨工程大学信息与通信工程学院，黑龙江哈尔滨 150001
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62201172);Fundamental Research Funds for the Central Universities(3072025YY0801)
- DOI：10.12263/DZXB.20260052
  CLC： TN929.5;
- Received：20 February 2026，
  
  Accepted：12 March 2026，
  
  Online First：08 June 2026，
- 稿件说明：
移动端阅览
ZHANG Han, HAN Yu, MENG Lingxin, et al. Uncertainty-Driven UAV Active Sensing for Radio Map Construction in Dense Urban Environments[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-12.
DOI：

ZHANG Han, HAN Yu, MENG Lingxin, et al. Uncertainty-Driven UAV Active Sensing for Radio Map Construction in Dense Urban Environments[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-12. DOI： 10.12263/DZXB.20260052.

摘要

在城市密集环境中，高层建筑遮挡、多系统并发辐射及多源干扰叠加使电磁环境呈现显著时变性和空间异质性，传统离线构建并低频更新的频谱地图难以及时反映真实信道状态，难以满足动态频谱管理、无线资源调度及低空通信保障对精度与时效性的要求，尤其是在复杂任务场景下对在线感知与快速决策能力提出了更高要求。针对上述问题，本文提出一种基于不确定度驱动的无人机频谱地图主动感知方法。首先，将无人机在线频谱地图更新与路径规划联合建模为马尔可夫决策过程，在状态中显式引入地图不确定度统计量、无人机位姿、飞行时间、目标距离和任务进度等信息，以增强策略对环境变化和任务阶段的综合表征能力。其次，利用预训练U-Net实现SINR频谱地图在线重构，并输出像素级不确定度估计，以不确定度下降表征信息增益，引导无人机优先感知高价值未知区域。进一步，设计基于特征线性调制的FiLM-D3QN决策网络，利用不确定度与任务进程条件动态调制中间特征和价值估计，实现信息获取与航迹效率之间的自适应权衡。仿真结果表明，在多干扰城市场景下，所提方法在到达率保持90%以上的同时，可有效降低地图重构误差，RMSE较经典IPP方法下降约7.1%，较原始D3QN下降约9.8%，并具有更短的平均回合长度，验证了该方法在复杂城市电磁环境中开展在线频谱地图更新与主动感知任务的有效性。

Abstract

In dense urban environments

blockage by high-rise buildings

concurrent radiation from multiple wireless systems

and the superposition of multi-source interference make the electromagnetic environment highly time-varying and spatially heterogeneous. Traditional radio maps

which are constructed offline and updated at a low frequency

cannot reflect the real channel state in time. As a result

they are unable to meet the requirements of dynamic spectrum management

wireless resource scheduling

and low-altitude communication support in terms of both accuracy and timeliness. This challenge is more pronounced in complex mission scenarios

where online sensing and rapid decision-making are especially important. To address this issue

this paper proposes an uncertainty-driven active sensing method for UAV-based spectrum mapping. First

the online radio map updating and path planning processes are jointly modeled as a Markov decision process. The state explicitly includes statistical measures of map uncertainty

UAV position

flight time

target distance

and mission progress

so as to improve the policy's ability to represent environmental changes and mission stages. Second

a pre-trained U-Net is employed to reconstruct the SINR radio map online and to output pixel-level uncertainty estimates. The reduction in uncertainty is used to characterize information gain

which guides the UAV to sense high-value unknown regions with priority. Furthermore

a FiLM-D3QN decision network based on Feature-wise Linear Modulation is designed. It uses uncertainty and mission-progress conditions to dynamically modulate intermediate features and value estimation

thereby achieving an adaptive balance between information acquisition and trajectory efficiency. Simulation results show that

in urban scenarios with dense interference

the proposed method effectively reduces map reconstruction error while maintaining an arrival rate above 90%. The RMSE is reduced by about 7.1% compared with the classical IPP method and by about 9.8% compared with the original D3QN. The proposed method also achieves a shorter average episode length. These results verify its effectiveness for online radio map updating and active sensing in complex urban electromagnetic environments.

关键词

Keywords

references

Ding Guoru , Jiao Yutao , Wang Jinlong , et al . Spectrum inference in cognitive radio networks: Algorithms and applications [J ] . IEEE Communications Surveys & Tutorials , 2018 , 20 ( 1 ): 150 - 182 . DOI: 10.1109/comst.2017.2751058 http://dx.doi.org/10.1109/comst.2017.2751058

Zeng Yong , Xu Xiaoli , Jin Shi , et al . Simultaneous navigation and radio mapping for cellular-connected UAV with deep reinforcement learning [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 7 ): 4205 - 4220 . DOI: 10.1109/twc.2021.3056573 http://dx.doi.org/10.1109/twc.2021.3056573

Shi Zhiguo , Chang Xianyu , Yang Chaoqun , et al . An acoustic-based surveillance system for amateur drones detection and localization [J ] . IEEE Transactions on Vehicular Technology , 2020 , 69 ( 3 ): 2731 - 2739 . DOI: 10.1109/tvt.2020.2964110 http://dx.doi.org/10.1109/tvt.2020.2964110

饶凌风 , 耿娜 , 张勇 , 等 . 不确定环境下无人机任务分配的种群交互式粒子群算法 [J ] . 电子学报 , 2025 , 53 ( 8 ): 2678 - 2690 .

Rao Lingfeng , Geng Na , Zhang Yong , et al . Population interactive particle swarm optimization algorithm for UAV task allocation in uncertain environments [J ] . Acta Electronica Sinica , 2025 , 53 ( 8 ): 2678 - 2690 . (in Chinese)

Sun Lu , Wang Jiashuai , Wan Liangtian , et al . Human-UAV interaction assisted heterogeneous UAV swarm scheduling for target searching in communication denial environment [J ] . IEEE Transactions on Automation Science and Engineering , 2025 , 22 : 4457 - 4472 . DOI: 10.1109/tase.2024.3412005 http://dx.doi.org/10.1109/tase.2024.3412005

Li Jiapeng , Zhang Qixun , Ma Dingyou , et al . UAV target reconstruction and imaging algorithm design and performance evaluation using CSI of ISAC signal [J ] . IEEE Transactions on Wireless Communications , 2025 , 24 ( 11 ): 9422 - 9434 . DOI: 10.1109/twc.2025.3573290 http://dx.doi.org/10.1109/twc.2025.3573290

陈进朝 , 王洋 , 张营 , 等 . 基于时空密度聚类的异构无人机集群覆盖路径规划方法 [J ] . 电子学报 , 2025 , 53 ( 3 ): 705 - 715 .

Chen Jinchao , Wang Yang , Zhang Ying , et al . Coverage path planning for heterogeneous UAVs based on temporal-spatial density clustering [J ] . Acta Electronica Sinica , 2025 , 53 ( 3 ): 705 - 715 . (in Chinese)

沈锋 , 丁国如 , 李婕 , 等 . 电磁频谱多维态势压缩测绘技术研究进展 [J ] . 通信学报 , 2023 , 44 ( 11 ): 25 - 42 .

Shen Feng , Ding Guoru , Li Jie , et al . Research progress on electromagnetic spectrum multidimensional situation compressed mapping technology [J ] . Journal on Communications , 2023 , 44 ( 11 ): 25 - 42 . (in Chinese)

Lin Yun , Tu Ya , Dou Zheng . An improved neural network pruning technology for automatic modulation classification in edge devices [J ] . IEEE Transactions on Vehicular Technology , 2020 , 69 ( 5 ): 5703 - 5706 . DOI: 10.1109/tvt.2020.2983143 http://dx.doi.org/10.1109/tvt.2020.2983143

Kang Jiawen , Zhong Yue , Xu Minrui , et al . Tiny multiagent DRL for twins migration in UAV metaverses: A multileader multifollower Stackelberg game approach [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 12 ): 21021 - 21036 . DOI: 10.1109/jiot.2024.3360183 http://dx.doi.org/10.1109/jiot.2024.3360183

Gao Qian , Zhong Ruikang , Hyundong Shin , et al . MARL-based UAV trajectory and beamforming optimization for ISAC system [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 24 ): 40492 - 40505 . DOI: 10.1109/jiot.2024.3453195 http://dx.doi.org/10.1109/jiot.2024.3453195

Zhou Yifan , Zhou Fuhui , Zhou Huilin , et al . Robust trajectory and transmit power optimization for secure UAV-enabled cognitive radio networks [J ] . IEEE Transactions on Communications , 2020 , 68 ( 7 ): 4022 - 4034 . DOI: 10.1109/tcomm.2020.2979977 http://dx.doi.org/10.1109/tcomm.2020.2979977

王红军 , 徐浩然 , 赵文元 . 电磁频谱地图构建中的空间插值方法综述 [J ] . 电讯技术 , 2025 , 65 ( 1 ): 141 - 151 .

Wang Hongjun , Xu Haoran , Zhao Wenyuan . Survey on spatial interpolation methods for electromagnetic spectrum map construction [J ] . Telecommunication Engineering , 2025 , 65 ( 1 ): 141 - 151 . (in Chinese)

Tu Ya , Lin Yun , Zha Haoran , et al . Large-scale real-world radio signal recognition with deep learning [J ] . Chinese Journal of Aeronautics , 2022 , 35 ( 9 ): 35 - 48 . DOI: 10.1016/j.cja.2021.08.016 http://dx.doi.org/10.1016/j.cja.2021.08.016

Romero D , Kim S J . Radio map estimation: A data-driven approach to spectrum cartography [J ] . IEEE Signal Processing Magazine , 2022 , 39 ( 6 ): 53 - 72 . DOI: 10.1109/msp.2022.3200175 http://dx.doi.org/10.1109/msp.2022.3200175

Levie R , Yapar Ç , Kutyniok G , et al . RadioUNet: Fast radio map estimation with convolutional neural networks [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 6 ): 4001 - 4015 . DOI: 10.1109/twc.2021.3054977 http://dx.doi.org/10.1109/twc.2021.3054977

Zhang Songyang , Wijesinghe A , Ding Zhi . RME-GAN: A learning framework for radio map estimation based on conditional generative adversarial network [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 20 ): 18016 - 18027 . DOI: 10.1109/jiot.2023.3278235 http://dx.doi.org/10.1109/jiot.2023.3278235

Zhang Han , Han Yu , Meng Lingxin , et al . MFFGCN: Multimodal feature fusion graph convolution network for radio map estimation with uneven spatial sampling [J ] . IEEE Transactions on Mobile Computing , 2025 , 24 ( 12 ): 13366 - 13382 . DOI: 10.1109/tmc.2025.3590335 http://dx.doi.org/10.1109/tmc.2025.3590335

谭海东 , 杨晶晶 , 黄铭 . 基于卷积神经网络和注意力机制的无线电地图构建方法研究 [J ] . 电波科学学报 , 2025 , 40 ( 6 ): 1069 - 1077 .

Tan Haidong , Yang Jingjing , Huang Ming . A study on the methodology for constructing radio maps utilizing convolutional neural network and attention mechanisms [J ] . Chinese Journal of Radio Science , 2025 , 40 ( 6 ): 1069 - 1077 . (in Chinese)

Paonessa F , Virone G , Bolli P , et al . UAV-based antenna measurements: Scan strategies [C ] // Proceedings of 2017 11th European Conference on Antennas and Propagation (EUCAP) . Piscataway : IEEE , 2017 : 1303 - 1305 . DOI: 10.23919/eucap.2017.7928721 http://dx.doi.org/10.23919/eucap.2017.7928721

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 Jie , Zhu Qiuming , Lin Zhipeng , et al . Sparse Bayesian learning-based hierarchical construction for 3D radio environment maps incorporating channel shadowing [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 10 ): 14560 - 14574 . DOI: 10.1109/twc.2024.3416447 http://dx.doi.org/10.1109/twc.2024.3416447

Shrestha R , Romero D , Chepuri S P . Spectrum surveying: Active radio map estimation with autonomous UAVs [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 1 ): 627 - 641 . DOI: 10.1109/twc.2022.3197087 http://dx.doi.org/10.1109/twc.2022.3197087

Du Xiaofu , Zhu Qiuming , Ding Guoru , et al . UAV-assisted three-dimensional spectrum mapping driven by spectrum data and channel model [J ] . Symmetry , 2021 , 13 ( 12 ): 2308 . DOI: 10.3390/sym13122308 http://dx.doi.org/10.3390/sym13122308

Wu Qihui , Shen Feng , Wang Zheng , et al . 3D spectrum mapping based on ROI-driven UAV deployment [J ] . IEEE Network , 2020 , 34 ( 5 ): 24 - 31 . DOI: 10.1109/mnet.011.2000076 http://dx.doi.org/10.1109/mnet.011.2000076

Chen Yiran , Zhu Qiuming , Wang Jie , et al . UAV-aided efficient informative path planning for autonomous 3D spectrum mapping [J ] . IEEE Transactions on Cognitive Communications and Networking , 2026 , 12 : 1664 - 1677 . DOI: 10.1109/tccn.2025.3603736 http://dx.doi.org/10.1109/tccn.2025.3603736

Dutta S , Wilde N , Smith S L . Informative path planning for active regression with Gaussian processes via sparse optimization [J ] . IEEE Transactions on Robotics , 2025 , 41 : 2184 - 2199 . DOI: 10.1109/tro.2025.3548865 http://dx.doi.org/10.1109/tro.2025.3548865

Zhu Hai , Chung J J , Lawrance N R J , et al . Online informative path planning for active information gathering of a 3D surface [C ] // Proceedings of 2021 IEEE International Conference on Robotics and Automation (ICRA) . Piscataway : IEEE , 2021 : 1488 - 1494 . DOI: 10.1109/icra48506.2021.9561963 http://dx.doi.org/10.1109/icra48506.2021.9561963

Jakkala K , Akella S . Multi-robot informative path planning from regression with sparse Gaussian processes [C ] // Proceedings of 2024 IEEE International Conference on Robotics and Automation (ICRA) . Piscataway : IEEE , 2024 : 12382 - 12388 . DOI: 10.1109/icra57147.2024.10610484 http://dx.doi.org/10.1109/icra57147.2024.10610484

Rückin J , Magistri F , Stachniss C , et al . An informative path planning framework for active learning in UAV-based semantic mapping [J ] . IEEE Transactions on Robotics , 2023 , 39 ( 6 ): 4279 - 4296 . DOI: 10.1109/tro.2023.3313811 http://dx.doi.org/10.1109/tro.2023.3313811

Schlotfeldt B , Tzoumas V , Pappas G J . Resilient active information acquisition with teams of robots [J ] . IEEE Transactions on Robotics , 2021 , 38 ( 1 ): 244 - 261 . DOI: 10.1109/tro.2021.3082212 http://dx.doi.org/10.1109/tro.2021.3082212

Wei Yongyong , Zheng Rong . Informative path planning for mobile sensing with reinforcement learning [C ] // Proceedings of IEEE INFOCOM 2020-IEEE Conference on Computer Communications . Piscataway : IEEE , 2020 : 864 - 873 . DOI: 10.1109/infocom41043.2020.9155528 http://dx.doi.org/10.1109/infocom41043.2020.9155528

Zhao Haitao , Hao Qing , Huang Hao , et al . Online trajectory optimization for energy-efficient cellular-connected UAVs with map reconstruction [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 3 ): 3445 - 3456 . DOI: 10.1109/tvt.2023.3323349 http://dx.doi.org/10.1109/tvt.2023.3323349

Deng Tan , Wang Yanping , Li Jin , et al . Entropy normalization sac-based task offloading for UAV-assisted mobile-edge computing [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 15 ): 26220 - 26233 . DOI: 10.1109/jiot.2024.3395276 http://dx.doi.org/10.1109/jiot.2024.3395276

Zhang Lijuan , Peng Jiabin , Yi Weiguo , et al . A state-decomposition DDPG algorithm for UAV autonomous navigation in 3-D complex environments [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 6 ): 10778 - 10790 . DOI: 10.1109/jiot.2023.3327753 http://dx.doi.org/10.1109/jiot.2023.3327753

Guan Yue , Zou Sai , Peng Haixia , et al . Cooperative UAV trajectory design for disaster area emergency communications: A multiagent PPO method [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 5 ): 8848 - 8859 . DOI: 10.1109/jiot.2023.3320796 http://dx.doi.org/10.1109/jiot.2023.3320796

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fine-Grained Inference Task Offloading for Large Language Model in Industrial Edge-Cloud Collaborative Scenarios

A Causal Tree-of-Thought-Based Model for Battery State-of-Charge Prediction in Electric Vehicles

Efficient Task Offloading Based on Traffic Prediction in IoV-Enabled Edge Computing

Research on UAV Path Planning Algorithm for Fairness Data Collection and Energy Supplement

A Novel SAR Super-Resolution Method via Signal Extrapolation and Hierarchical Learning

Related Author

LI Zhongyang

CAO Xiaoke

CAI Yichen

SUN Guibin

LIU Kexin

LIAO Ling-ling

TAO Ming

XIE Ren-ping

Related Institution

Shenyuan Honors College, Beihang University

School of Automation Science and Electrical Engineering, Beihang University

School of Artificial Intelligence, Beihang University

School of Computer Science and Technology (School of Cyberspace Security), Dongguan University of Technology

School of Information and Communication Engineering, University of Electronics Science and Technology of China

⁰