| 79 | 0 | 310 |
| 下载次数 | 被引频次 | 阅读次数 |
全球导航卫星系统(Global Navigation Satellite System, GNSS)拒止环境下的精准定位是保障无人机在复杂空间内安全作业的关键。然而，受环境封闭、多径效应严重及电磁干扰等多重因素影响，高精度无人机位置获取难度较大。基于信道状态信息(Channel State Information, CSI)的无线电指纹定位技术因具有抗多径干扰能力而成为重要解决方案。然而，该技术高度依赖高密度的无线电地图，在实际部署中面临现场采集工作量大、参考点稀疏导致定位精度急剧下降的难题。针对这一难题，提出了基于条件生成对抗网络(Location-to-CSI Generative Adversarial Network, L2C-GAN)的指纹增强模型，通过学习粗粒度无线电地图的空间位置与无线电指纹间的非线性映射关系生成虚拟无线电指纹，从而重构细粒度无线电地图。其中，条件是指无人机坐标；网络输入是由高维信道状态信息分段获取的单通道指纹图及对应坐标；生成器与判别器分别对坐标进行高维编码，并引入自注意力机制提升全局上下文学习能力。结果表明，在仅有2%参考点的极端稀疏情况下，平均定位误差可由2.01 m降低至1.67 m,精度提升了16.92%。
Abstract：To tackle the significant decline in positioning accuracy caused by sparse reference points in Channel State Information(CSI) fingerprinting, this paper presents a fingerprint augmentation model called L2C-GAN(Location-to-CSI Generative Adversarial Network). The proposed method reconstructs fine-grained radio maps by generating virtual fingerprints based on the learned non-linear mapping between spatial locations and Radio Frequency(RF) features. The methodology consists of three key stages. First, a Density-Based Spatial Clustering of Applications with Noise(DBSCAN) is employed to preprocess the raw CSI amplitude data. This approach adaptively identifies and retains dominant signal clusters while eliminating outliers arising from environmental noise and hardware instability, thereby ensuring the purity and spatial consistency of the training data. Second, to accommodate convolutional operations, high-dimensional CSI matrices are segmented along subcarrier indices and reshaped into single-channel 2D feature maps. Third, the L2C-GAN architecture is constructed using a conditional generation mechanism. To address the low dimensionality of spatial coordinates, a Fourier-feature-based Positional Encoding mechanism is designed to map 2D coordinates into high-dimensional embedding vectors. Both the generator and discriminator integrate Self-Attention modules to capture long-range dependencies among subcarriers, enabling the model to learn global context. Experimental validation is conducted using the OpenCSI dataset in an extremely sparse setting with only 2%(88) real reference points. The results demonstrate that L2C-GAN effectively enhances radio map reconstruction. The average positioning error decreases from 2.01 m to 1.67 m, representing a 16.92% improvement over the baseline without augmentation. Furthermore, experiments with varying parameter settings show that augmenting with 400 virtual reference points yields the optimal positioning accuracy of 1.67 m. Comparative results also indicate that the proposed method significantly outperforms state-of-the-art augmentation techniques, such as SSIM-Aug(Structural Similarity-based Augmentation), AF-DCGAN(Amplitude Feature Deep Convolutional GAN), and LESS(Adaptive Fingerprint-based Localization with Less Site Survey). Notably, the model exhibits robust performance even under limited hardware configurations, achieving a positioning error of 1.92 m with only two receiving antennas, which surpasses the unaugmented four-antenna baseline.
[1] Amarasingam N,Salgadoe A S A,Powell K,et al.A review of UAV platforms,sensors,and applications for monitoring of sugarcane crops[J].Remote Sensing Applications:Society and Environment,2022,26:100712.
[2] Cheng Nan,Wu Shen,Wang Xiucheng,et al.AI for UAV-assisted IoT applications:a comprehensive review[J].IEEE Internet of Things Journal,2023,10(16):14438-14461.
[3] 中共中央国务院印发《国家综合立体交通网规划纲要》[J].中华人民共和国国务院公报，2021(8):25-37.The CPC Central Committee and the State Council issued the “Outline of the National Comprehensive Three-dimensional Transportation Network Planning”[J].State Council of the People's Republic of China,2021(8):25-37.
[4] 魏志强，王晶.大型固定翼无人机跟随民航机的尾流安全评估方法[J].安全与环境学报，2024,24(12):4533-4541.Wei Zhiqiang,Wang Jing.Calculation method for required wake turbulence separation integrating UAVs into civil aviation airspace[J].Journal of Safety and Environment,2024,24(12):4533-4541.
[5] 张静，张科，王靖宇，等.低空反无人机技术现状与发展趋势[J].航空工程进展，2018,9(1):1-8,34.Zhang Jing,Zhang Ke,Wang Jingyu,et al.A survey on anti-UAV technology and its future trend[J].Advances in Aeronautical Science and Engineering,2018,9(1):1-8,34.
[6] Zekavat S,Buehrer R M,Durgin G D,et al.An overview on position location:Past,present,future[J].International Journal of Wireless Information Networks,2021,28:45-76.
[7] Liu Zheng,Fu Zhe,Li Tongyun,et al.A phase and RSSI-based method for indoor localization using passive RFID system with mobile platform[J].IEEE Journal of Radio Frequency Identification,2022,6:544-551.
[8] 杨海龙，祁小凤，王瑞元，等.高噪声环境下声发射损伤源定位技术研究[J].工程与试验，2024,64(2):23-27.Yang Hailong,Qi Xiaofeng,Wang Ruiyuan,et al.Research on damage source localization by acoustic emission in high noise environments[J].Engineering and Test,2024,64(2):23-27.
[9] 秦杰，邓平，罗锐，等.一种基于鲸鱼优化的TOA/AOA最优化定位算法[J].导航定位学报，2023,11(6):93-101.Qin Jie,Deng Ping,Luo Rui,et al.A TOA/AOA optimization localization algorithm based on whale optimization[J].Journal of Navigation and Positioning,2023,11(6):93-101.
[10] Lee H,Kang T,Jeong S,et al.Evaluation of RF fingerprinting-aided RSS-based target localization for emergency response[C]//Proceedings of the 2022 IEEE 95th Vehicular Technology Conference (VTC2022-Spring).Piscataway,NJ,USA:Institute of Electrical and Electronics Engineers,2022:1-7.
[11] Kong Ruiqi,Chen He.CSI-RFF:leveraging micro-signals on CSI for RF fingerprinting of commodity WiFi[J].IEEE Transactions on Information Forensics and Security,2024,19:5301-5315.
[12] Bianchi V,Paolo C,Ilaria D M.RSSI-based indoor localization and identification for ZigBee wireless sensor networks in smart homes[J].IEEE Transactions on Instrumentation and Measurement,2018,68:566-575.
[13] Bottigliero S,Milanesio D,Saccani M,et al.A low-cost indoor real-time locating system based on TDOA estimation of UWB pulse sequences[J].IEEE Transactions on Instrumentation and Measurement,2021,70:5502211.
[14] Tong Xinyu,Wan Yang,Li Qianru,et al.CSI fingerprinting localization with low human efforts[J].IEEE/ACM Transactions on Networking,2020,29(1):372-385.
[15] Amiri R,Yerramalli S,Yoo T,et al.Indoor environment learning via RF-mapping[J].IEEE Journal on Selected Areas in Communications,2023,41(6):1859-1872.
[16] Wu Chenshu,Yang Zheng,Xiao Chaowei.Automatic radio map adaptation for indoor localization using smartphones[J].IEEE Transactions on Mobile Computing,2017,17(3):517-528.
[17] Yin Jie,Yang Qiang,Ni L M.Learning adaptive temporal radio maps for signal-strength-based location estimation[J].IEEE Transactions on Mobile Computing,2008,7(7):869-883.
[18] Xiang Chenlu,Zhang Shunqing,Xu Shugong,et al.Crowdsourcing-based indoor localization with knowledge-aided fingerprint transfer[J].IEEE Sensors Journal,2022,22(5):4281-4293.
[19] Chen Lüdong,Zhao Caidan,Zheng Yicheng,et al.Radio frequency fingerprint identification based on transfer learning[C]//Proceedings of the 2021 IEEE/CIC International Conference on Communications in China (ICCC).Piscataway,NJ,USA:Institute of Electrical and Electronics Engineers,2021:81-85.
[20] 唐文胜，李姗，匡旺秋.RF室内定位指纹库空间相关生成算法[J].计算机工程与应用，2008,44(23):226-229,232.Tang Wensheng,Li Shan,Kuang Wangqiu.New algorithm based-on spatial correlation for yielding fingerprints database of RF indoor localization[J].Computer Engineering and Applications,2008,44(23):226-229,232.
[21] Ng P C,Spachos P,She J,et al.A kernel method to nonlinear location estimation with RSS-based fingerprint[J].IEEE Transactions on Mobile Computing,2022,22(8):4388-4404.
[22] Muta O,Takata K,Noguchi K,et al.Device-free WLAN based indoor localization scheme with spatially concatenated CSI and distributed antennas[J].IEEE Transactions on Vehicular Technology,2022,72(1):852-865.
[23] Wei Wu,Yan Jun,Wu Xiaofu,et al.CSI fingerprinting for device-free localization:Phase calibration and SSIM-based augmentation[J].IEEE Wireless Communications Letters,2022,11(6):1137-1141.
[24] Li Qiyue,Qu Heng,Liu Zhi,et al.AF-DCGAN:amplitude feature deep convolutional GAN for fingerprint construction in indoor localization systems[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2019,5(3):468-480.
[25] Zhang Lingyan,Wu Shaohua,Zhang Tingting,et al.Learning to locate:Adaptive fingerprint-based localization with few-shot relation learning in dynamic indoor environments[J].IEEE Transactions on Wireless Communications,2023,22(8):5253-5264.
[26] Lü Zhongyuan,Chan T T L,Leung G C M,et al.High-dimensional radio frequency fingerprint synthesis for indoor positioning[J].IEEE Transactions on Instrumentation and Measurement,2025,74:2517416.
[27] Yuan Yazhou,Liu Xun,Liu Zhixin,et al.Indoor localization with wireless heterogeneous devices by composite fingerprint sets and hybrid classification[J].IEEE Transactions on Vehicular Technology,2022,71(11):12117-12127.
[28] 李楠，强懿耕，樊瑞，等.基于异常因子的航空器飞行轨迹异常检测研究[J].安全与环境学报，2021,21(2):643-648.Li Nan,Qiang Yigeng,Fan Rui,et al.On the abnormal detection of the aircraft flight trajectory based on the abnormal factor statistics[J].Journal of Safety and Environment,2021,21(2):643-648.
[29] 艾矫燕，郑剑武，刘高煊.基于GF-LSTM和GAN网络的小样本集人工水体溶解氧浓度预测[J].安全与环境学报，2021,21(1):426-434.Ai Jiaoyan,Zheng Jianwu,Liu Gaoxuan.Forecast for dissolved oxygen concentration in artificial water body based on GF-LSTM and GAN network[J].Journal of Safety and Environment,2021,21(1):426-434.
[30] Martin A,Soumith C,Leon B.Wasserstein generative adversarial networks[C]//Proceedings of the 34th International Conference on Machine Learning (ICML 2017).Sydney,NSW,Australia:Journal of Machine Learning Research,2017:214-223.
[31] Gassner A,Musat C,Rusu A,et al.OpenCSI:an open-source dataset for indoor localization using CSI-based fingerprinting[PP/OL].(2021-04-16)[2025-05-06].https://arxiv.org/abs/2104.07963.
基本信息:
DOI：10.13637/j.issn.1009-6094.2025.0755
中图分类号:V279;V249.3;TN96
引用信息:
[1]陈乃馨,朱春丽,陈磊,等.面向GNSS拒止环境的极少参考点无线电指纹定位方法[J].安全与环境学报,2026,26(07):2527-2538.DOI:10.13637/j.issn.1009-6094.2025.0755.
基金信息:
国家自然科学基金项目(52302426)
2026-05-15
2026-05-15
2026-05-15