一种室内伪卫星混合指纹定位方法

doi:10.19665/j.issn1001-2400.20221102

摘要/Abstract

摘要：

目前,复杂的室内环境与伪卫星信号的交互机制尚未得到根本解决,室内定位的稳定性、连续性和准确性仍是技术瓶颈,现有室内指纹定位方法面临指纹采集量与定位精度和定位范围成正比的限制,同时也有非实际采集不能完成定位的弊端。针对现有方法的不足,结合实际测量、数学仿真和人工神经网络的优点,提出了一种基于实际采集指纹、建模仿真指纹和人工神经网络的室内伪卫星混合指纹定位方法。首先对实际环境和信号收发端进行模型构建,其次将利用射线追踪仿真生成的模拟指纹转换后联合实测指纹共同添加到神经网络的输入中,扩展了原来单一实测指纹输入数据集的样本特征,最后利用混合指纹共同训练人工神经网络定位模型,用于在线定位。以某机场环境为例,实验证明混合指纹定位方法可以提高稀疏采集指纹区域的定位精度,均方根定位误差约为0.485 0 m,与传统指纹定位方法相比,定位误差降低了约54.7%;在没有采集指纹的区域也可以粗略完成初步定位,均方根定位误差约为1.123 7 m,突破了传统指纹定位方法的局限。

关键词: 指纹定位, 人工神经网络, 伪卫星, 射线追踪, 室内定位

Abstract:

At present,the interaction mechanism between the complex indoor environment and pseudolite signals has not been fundamentally resolved,and the stability,continuity,and accuracy of indoor positioning are still technical bottlenecks.Existing fingerprint positioning methods face the limitation that the collection workload is proportional to the positioning accuracy and positioning range,and have the disadvantage that the positioning cannot be completed without actual collection.In order to solve the above shortcomings of the existing methods,by combining the advantages of actual measurement,mathematical simulation and the artificial neural network,an indoor pseudolite hybrid fingerprint location method based on actual fingerprints,simulation fingerprints and the artificial neural network is proposed.First,the actual environment and signal transceiver are modeled.Second,both the simulated fingerprints generated by ray tracing simulation after conversion and the measured fingerprints are added to the input of the neural network,which expands the sample characteristics of the input data set of the original single measured fingerprints.Finally,the artificial neural network positioning model is jointly trained by the mixed fingerprints and then used for online positioning.By taking an airport environment as an example,it is proved that the hybrid method can improve the positioning accuracy of the sparsely collected fingerprint region,and that the root mean square error is 0.485 0 m,which is 54.7% lower than that of the traditional fingerprint positioning method.Preliminary positioning can also be completed in areas where no fingerprints are collected,and the root mean square positioning error is 1.123 7 m,which breaks through the limitations of traditional fingerprint location methods.

Key words: fingerprint positioning, ANN, pseudolite, ray tracing, indoor positioning

中图分类号:

TN967.1

李雅宁,李宏生,蔚保国. 一种室内伪卫星混合指纹定位方法[J]. 西安电子科技大学学报, 2023, 50(5): 21-31.

LI Yaning,LI Hongsheng,YU Baoguo. Indoor pseudolite hybrid fingerprint positioning method[J]. Journal of Xidian University, 2023, 50(5): 21-31.

图/表 11

图1

图2

表1

图3

图4

图5

图6

图7

图8

表2

图9

参考文献 16

[1]	GAN X L, YU B G, WANG X P. A New Array Pseudolites Technology for High Precision Indoor Positioning[J]. IEEE Access, 2019, 7:153269-153277. doi: 10.1109/ACCESS.2019.2948034
[2]	POULOSE A, KIM J, HAN D. A Sensor Fusion Framework for Indoor Localization Using Smartphone Sensors and Wi-Fi RSSI Measurements[J]. Applied Sciences, 2019, 9(20):4379. doi: 10.3390/app9204379
[3]	YUAN Z W, ZHANG X J, ZHOU P, et al. Research on Indoor Position Fingerprint Location Based on Machine Learning Combined Particle Filter[C]//Proceedings of the 2nd International Conference on Safety Produce Informatization(IICSPI 2019).Piscataway:IEEE, 2019:456-459.
[4]	LIN C H, CHEN L H, WU H K, et al. An Indoor Positioning Algorithm Based on Fingerprint and Mobility Prediction in RSS Fluctuation-Prone WLANs[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems, 2021, 51(5):2926-2936. doi: 10.1109/TSMC.2019.2917955
[5]	毕京学. 智能手机Wi-Fi/PDR室内混合定位优化问题研究[D]. 徐州: 中国矿业大学, 2019.
[6]	秦宁宁, 张臣臣. 模糊聚类下的接入点选择匹配定位算法[J]. 西安电子科技大学学报, 2022, 49(4):71-81.
	QIN Ningning, ZHANG Chenchen. Access Point Selection Matching Localization Algorithm Based on Fuzzy Clustering[J]. Journal of Xidian University, 2022, 49(4):71-81.
[7]	孙顺远, 朱红洲, 秦宁宁. 一种动态校正的信号双尺度近邻定位方法[J]. 西安电子科技大学学报, 2022, 49(3):93-100.
	SUN Shunyuan, ZHU Hongzhou, QIN Ningning. Signal Two-Scale Nearest Neighbor Positioning Method under Dynamic Correction[J]. Journal of Xidian University, 2022, 49(3):93-100.
[8]	HUANG L, GAN X L, YU B G. An Innovative Fingerprint Location Algorithm for Indoor Positioning Based on Array Pseudolite[J]. Sensors, 2019, 19(20):4420. doi: 10.3390/s19204420
[9]	ZHOU C Y, LIU J Y, SHENG M, et al. Exploiting Fingerprint Correlation for Fingerprint-Based Indoor Localization:A Deep Learning Based Approach[J]. IEEE Transactions on Vehicular Technology, 2021, 70(6):5762-5774. doi: 10.1109/TVT.2021.3075539
[10]	, RENAUDINO, ZEMENT, BURGESST. Ray-Tracing Based Fingerprinting for Indoor Localization[C]//Proceedings of the 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Piscataway:IEEE, 2018:1-5.
[11]	TSENGP H, CHAN Y C, LIN Y J, et al. Ray-Tracing-Assisted Fingerprinting Based on Channel Impulse Response Measurement for Indoor Positioning[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(5):1032-1045. doi: 10.1109/TIM.2016.2622799
[12]	ILINA O, ZIYADINOV V, KLENOV N, et al. A Survey on Symmetrical Neural Network Architectures and Applications[J]. Symmetry, 2022, 14:1391. doi: 10.3390/sym14071391
[13]	WU L N, HE D P, AI B, et al. Artificial Neural Network Based Path Loss Prediction for Wireless Communication Network[J]. IEEE Access 2020, 8:199523-199538. doi: 10.1109/Access.6287639
[14]	MANUEL E M, MARTIN M, WANSU L. Breaking Wireless Propagation Environmental Uncertainty with Deep Learning[J]. IEEE Transactions on Wireless Communications, 2020, 19(8):5075-5087. doi: 10.1109/TWC.7693
[15]	YANG Y W, GAO FF, ZHONG Z M, et al. Deep Transfer Learning-Based Downlink Channel Prediction for FDD Massive MIMO Systems[J]. IEEE Transactions on Communications, 2020, 68(12):7485-7497. doi: 10.1109/TCOMM.26
[16]	孙晨晨, 逯贵祯. 基于射线追踪法的室内走廊环境电波传播研究[J]. 中国传媒大学学报(自然科学版), 2019, 26(5):54-59.
	SUN Chenchen, LU Guizhen. Research on Environmental Radio Wave Propagation in Indoor Corridor Based on Ray Tracing Method[J]. Journal of Communication University of China(Science and Technology), 2019, 26(5):54-59.

参数	值
房间模型尺寸/m³	100×20×4.5
承重柱模型尺寸/m³	0.5×0.5×4.5
墙壁材质/介电常数/电导率	混凝土/5/0.001 5
地面材质/介电常数/电导率	瓷砖大理石/6/10^-8
信号频率/MHz	1 575.42
天线类型	右旋圆极化全向天线
仿真测试接收区域尺寸/m²	5×5
仿真测试接收点间隔/m	1
发射功率/dBm	-70
最大反射/透射/绕射次数	3
射线间隔/(°)	0.25

算法	K最邻近法	支持向量法	文献[3]方法	文献[9]方法	文中方法
RMS误差/m	1.182 1	1.069 6	0.771 4	0.925 3	0.485 0
95%误差/m	2.272 7	1.842 4	1.619 4	1.472 7	1.026 0
平均绝对误差/m	0.351 5	0.333 3	0.260 7	0.305 2	0.145 5