Sensing Image Data Based Unmanned Aerial Vehicle Channel Path Loss Prediction
SUN Mingran1, HUANG Ziwei1, BAI Lu2,3, CHENG Xiang1, ZHANG Hongguang4, FENG Tao4
1. School of Electronics, Peking University, Beijing 100871; 2. Shandong Research Institute of Industrial Technology, Jinan 250100; 3. Joint SDU-NTU Centre for Artificial Intelligence Research, Shandong University, Jinan 250101; 4. Institute of System Engineering, Academy of Military Sciences PLA, Beijing 100039
Abstract:To facilitate the application and development of 6G unmanned aerial vehicle(UAV)-to-ground wireless communications, improve the theory foundation of UAV-to-ground communication system and meet the safety and efficiency requirements of 6G communications, sensing image data based UAV channel path loss prediction in 6G UAV-to-ground communication scenario is studied. Firstly, based on AirSim and Wireless InSite, sensing data simulation platform and channel data simulation platform, a mixed sensing and communication integration dataset for a dynamic UAV-to-ground communication scenario, is established to explore the mapping relationship between physical space and electromagnetic space. Secondly, based on the established dataset, the mapping relationship between sensing image in physical space and channel path loss in electromagnetic space is built and the 6G UAV-to-ground real-time path loss prediction is achieved. Finally, the prediction result of the proposed model is compared with the test set through the simulation test and the results verify the accuracy of the proposed model.
[1] CHENG X, DUAN D L, GAO S J, et al. Integrated Sensing and Communications(ISAC) for Vehicular Communication Networks(VCN). IEEE Internet of Things Journal, 2022, 9(23): 23441-23451. [2] CHENG X, ZHANG H T, ZHANG J N, et al. Intelligent Multi-modal Sensing-Communication Integration: Synesthesia of Machines. IEEE Communications Surveys and Tutorials, 2023. DOI: 10.1109/COMST.2023.3336917. [3] CHENG X, HUANG Z W, BAI L.Channel Nonstationarity and Con-sistency for Beyond 5G and 6G: A Survey. IEEE Communications Surveys and Tutorials, 2022, 24(3): 1634-1669. [4] SUMAN S, KUMAR S, DE S.Path Loss Model for UAV-Assisted RFET. IEEE Communications Letters, 2018, 22(10): 2048-2051. [5] CUI Z Z, BRISO C, GUAN K, et al. Low-Altitude UAV Air-Ground Propagation Channel Measurement and Analysis in a Suburban Environment at 3.9 GHz. IET Microwaves, Antennas and Propagation, 2019, 13(9): 1503-1508. [6] MASARACCHIA A, LI Y J, NGUYEN K K, et al. UAV-Enabled Ultra-Reliable Low-Latency Communications for 6G: A Comprehensive Survey. IEEE Access, 2021, 9: 137338-137352. [7] GUPTA A, DU J F, CHIZHIK D, et al. Machine Learning-Based Urban Canyon Path Loss Prediction Using 28 GHz Manhattan Mea-surements. IEEE Transactions on Antennas and Propagation, 2022, 70(6): 4096-4111. [8] ATES H F, HASHIR S M, BAYKAS T, et al. Path Loss Exponent and Shadowing Factor Prediction from Satellite Images Using Deep Learning. IEEE Access, 2019, 7: 101366-101375. [9] AHMADIEN O, ATES H F, BAYKAS T, et al. Predicting Path Loss Distribution of an Area from Satellite Images Using Deep Lear-ning. IEEE Access, 2020, 8: 64982-64991. [10] LEVIE R, YAPAR Ç, KUTYNIOK G, et al. RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks. IEEE Transactions on Wireless Communications, 2021, 20(6): 4001-4015. [11] QIU K H, BAKIRTZIS S, SONG H, et al. Pseudo Ray-Tracing: Deep Leaning Assisted Outdoor mm-Wave Path Loss Prediction. IEEE Wireless Communications Letters, 2022, 11(8): 1699-1702. [12] CHENG X, HUANG Z W, BAI L, et al. M3SC: A Generic Dataset for Mixed Multi-modal(MMM) Sensing and Communication Integration. China Communications, 2023, 20(11): 13-29. [13] SHAH S, DEY D, LOVETT C, et al. AirSim: High-Fidelity Vi-sual and Physical Simulation for Autonomous Vehicles // HUTTER M, SIEGWART R, eds. Field and Service Robotics. Berlin, Germany: Springer, 2018: 621-635. [14] 杨晖,曲秀杰.图像分割方法综述.电脑开发与应用, 2005, 18(3): 21-23. (YANG H, QU X J.Survey of Image Segmentation Method. Computer Development and Applications, 2005, 18(3): 21-23.) [15] GARDNER M W, DORLING S R. Artificial Neural Networks(The Multilayer Perceptron)-A Review of Applications in the Atmospheric Sciences. Atmospheric environment, 1998, 32(14/15): 2627-2636. [16] HE J C, LI L, XU J C, et al. ReLU Deep Neural Networks and Linear Finite Elements[C/OL].[2023-09-24]. https://arxiv.org/pdf/1807.03973v2.pdf. [17] YOU K C, LONG M S, WANG J M, et al. How Does Learning Rate Decay Help Modern Neural Networks?[C/OL]. [2023-09-24]. https://arxiv.org/pdf/1908.01878.pdf.