To address the limited real-time performance of existing radio map construction methods in measurement-free scenarios, this work proposes an air-ground collaborative method for shared radio map generation. A diffusion model is introduced to formulate a conditional generation task, thereby meeting the requirement for real-time radio map generation among large-scale distributed user nodes. First, an edge computing architecture enabling shared denoising between unmanned aerial vehicles (UAVs) and ground base stations is constructed. The radio map generation task is formulated as a mixed-integer nonlinear programming problem with the objective of minimizing the total generation latency for all users. Subsequently, the original problem is decomposed into two subproblems: the joint optimization of user-server service policies and shared denoising steps, and UAV trajectory planning. These two subproblems are efficiently solved via the branch-and-bound method and the model-based reinforcement learning algorithm RGCN-DRL, respectively. In particular, a prediction module based on relational graph convolutional networks is designed to effectively capture user mobility intentions, which assists in UAV flight decision-making. Simulation results demonstrate that compared with the baseline method of local radio map generation, the proposed method reduces radio map generation latency by 53.08% while guaranteeing the quality of radio map generation.
[1]ZENG Y, et al.A Tutorial on Environment-Aware Communications via Channel Knowledge Map for 6G[J].IEEE Communications Surveys & Tutorials, 2024, 26(3):1478-1518
[2]查浩然, 孙露, 尚佳颖, 等.动态电磁环境中具身频谱感知技术研究[J].通信学报, 2026, online(online):o-n
[3]金立民, 王海超, 谷江春, 等.低空具身智能频谱管控技术研究[J].数据采集与处理, 2025, 40(1):45-55
[4]张寿彬, 王红军.电磁频谱地图构建：稀疏高斯过程回归方法[J].小型微型计算机系统, 2025, online(online):o-n
[5]RON L, ?AGKAN Y, GITTA K, et al.RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks[J].IEEE Transactions on Wireless Communications, 2021, 20(6):4001-4015
[6]BALLOTTA L, FABBRO N D, et al.VREM-FL: Mobility-Aware Computation-Scheduling Co-Design for Vehicular Federated Learning[J].IEEE Transactions on Vehicular Technology, 2025, 74(2):3311-3326
[7]TIMOTEO R D, CUNHA D, et al.A proposal for path loss prediction in urban environments using support vector regression[C]//Advanced International Conference on Telecommunications (AICT), 2014: 119-124.
[8]DANIEL S, RENATO L, SLAWOMIR S.Tensor Completion for Radio Map Reconstruction using Low Rank and Smoothness[C]//2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2019.
[9]ZHANG H, HAN Y, et al.MFFGCN: Multimodal Feature Fusion Graph Convolution Network for Radio Map Estimation with Uneven Spatial Sampling[J].IEEE Transactions on Mobile Computing, 2025, online(online):online-online
[10]WANG S Y, XU X L, ZENG Y.Deep Learning-Based CKM Construction with Image Super-Resolution[C]//2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring), 2025.
[11]SHAO S, CHENG L, et al.CollaboRadio: a Hybrid Device-Edge-Cloud Collaboration Paradigm for Fine-Grained Radio Map Construction[J].IEEE Transactions on Mobile Computing, 2025, online(online):online-online
[12]TOMAS S, LUKAS V, MAREK N.Graphical Heatmap-Based Approach to Indoor Radio Signal Propagation: Adapting Advanced Ray Tracing and Global Illumination Algorithms[J].IEEE Transactions on Antennas and Propagation, 2024, 72(7):6045-6059
[13]WANG X C, TAO K D, CHENG N, et al.RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction[J].IEEE Transactions on Cognitive Communications and Networking, 2025, 11(2):738-750
[14]WANG X C, ZHANG Q M, CHENG N, et al.RadioDiff-3D: A 3D×3D Radio Map Dataset and Generative Diffusion Based Benchmark for 6G Environment-Aware Communication[J].IEEE Transactions on Network Science and Engineering, 2025, online(online):online-online
[15]LUO X H, LI Z Z, et al.Denoising Diffusion Probabilistic Model for Radio Map Estimation in Generative Wireless Networks[J].IEEE Transactions on Cognitive Communications and Networking, 2025, online(online):online-online
[16]XU M R, DU H Y, NIYATO D, et al.Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services[J].IEEE Communications Surveys and Tutorials, 2024, 26(2):1127-1170
[17]MA X, WANG Y H, et al.Latte: Latent Diffusion Transformer for Video Generation[J].arXiv, 2024, 无(无):无-无
[18]BLATTMANN A, DOCKHORN T, et al.Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets[J].arXiv, 2023, 无(无):无-无
[19]ZHUANG X Y, WU J Q, WU H J, et al.Joint Optimization of Model Inferencing and Task Offloading for MEC-Empowered Large Vision Model Services[C]//IEEE INFOCOM 2025 - IEEE Conference on Computer Communications, 2025.
[20]DU H Y, ZHANG R C, NIYATO D, et al.Exploring Collaborative Distributed Diffusion-Based AI-Generated Content (AIGC) in Wireless Networks[J].IEEE Network, 2024, 38(3):178-186
[21]XIE G C, XIE R C, et al.Enhancing Vehicular Edge Intelligence through Distributed Collaborative Generative AI Inference[C]//ICC 2024 - IEEE International Conference on Communications, 2024.
[22]WU T, LI M M, et al.Joint UAV Deployment and Edge Association for Energy-Efficient Federated Learning[J].IEEE Transactions on Cognitive Communications and Networking, 2025, online(online):online-online
[23]屈毓锛, 秦蓁, 马靖豪, 等.面向空地协同移动边缘计算的服务布置策略[J].计算机学报, 2022, 45(4):781-797
[24]LI S C, ALE S, et al.Joint Computation Offloading and Multi-Dimensional Resource Allocation in Air-Ground Integrated Vehicular Edge Computing Network[J].IEEE Internet of Things Journal, 2024, 11(20):1981-1981
[25]LIU Y J, JIANG L, et al.Energy-Efficient Space-Air-Ground Integrated Edge Computing for Internet of Remote Things: A Federated DRL Approach[J].IEEE Internet of Things Journal, 2023, 10(6):4845-4856
[26]LI S C, HUANG Q R, CHEN H B, et al.DRL-Based Joint Task Offloading and Resource Allocation in Air-Ground Integrated Vehicular Edge Computing Network With Energy Harvesting[J].IEEE Transactions on Vehicular Technology, 2025, online(online):online-online
[27]HEVESLI M, SEID A M, ERBAD A, et al.Multi-Agent DRL for Queue-Aware Task Offloading in Hierarchical MEC-Enabled Air-Ground Networks[J].IEEE Transactions on Cognitive Communications and Networking, 2025, online(online):online-online
[28]DAI Z P, LIU C H, et al.AoI-minimal UAV Crowdsensing by Model-based Graph Convolutional Reinforcement Learning[C]//IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, London, United Kingdom, 2022: 1029-1038.
[29]RICHARD S S.Dyna,an integrated architecture for learning,planning,and reacting[J].ACM SIGART Bulletin, 1991, 2(4):160-163
[30]LI C, TIAN M Q, et al.On-Demand Environment Perception and Resource Allocation for Task Offloading in Vehicular Networks[J].IEEE Transactions on Wireless Communications, 2024, 23(11):16001-16016
[31]ZENG Y, et al.Energy Minimization for Wireless Communication With Rotary-Wing UAV[J].IEEE Transactions on Wireless Communications, 2019, 18(4):2329-2345
[32]ZHANG H, et al.CrowdBind: Fairness Enhanced Late Binding Task Scheduling in Mobile Crowdsensing[C]//EWSN ' 20: Proceedings of the 2020 International Conference on Embedded Wireless Systems and Networks, 2020.
[33]RHEE I J, SHIN M S, et al.CRAWDAD ncsu/mobilitymodels[J].IEEE Dataport, 2022, 无(November 2):无-无
CJA