1 Fingerprint Based mmWave Positioning System Aided by Reconﬁgurable Intelligent Surface

2025-04-30 1 0 1.03MB 5 页 10玖币

侵权投诉

Fingerprint Based mmWave Positioning System

Aided by Reconﬁgurable Intelligent Surface

Tuo Wu, Cunhua Pan, Yijin Pan, Hong Ren, Maged Elkashlan, and Cheng-Xiang Wang, Fellow IEEE

Abstract—Reconﬁgurable intelligent surface (RIS) is a promis-

ing technique for millimeter wave (mmWave) positioning systems.

In this paper, we consider multiple mobile users (MUs) position-

ing problem in the multiple-input multiple-output (MIMO) time-

division duplex (TDD) mmWave systems aided by the RIS. We

derive the expression for the space-time channel response vector

(STCRV) as a novel type of ﬁngerprint. The STCRV consists of

the multipath channel characteristics, e.g., time delay and angle of

arrival (AOA), which is related to the position of the MU. By using

the STCRV as input, we propose a novel residual convolution

network regression (RCNR) learning algorithm to output the

estimated three-dimensional (3D) position of the MU. Speciﬁcally,

the RCNR learninng algorithm includes a data processing block

to process the input STCRV, a normal convolution block to

extract the features of STCRV, four residual convolution blocks

to further extract the features and protect the integrity of the

features, and a regression block to estimate the 3D position.

Extensive simulation results are also presented to demonstrate

that the proposed RCNR learning algorithm outperforms the

traditional convolution neural network (CNN).

Index Terms—Reconﬁgurable intelligent surface (RIS), intelli-

gent reﬂecting surface, positioning, radio localization.

I. INTRODUCTION

Localization-related industries demand high levels of local-

ization accuracy [1], e.g., mobile user sensing [2]. It is worth

pointing out that prevalent global positioning system (GPS)

localization accuracy, even in ideal conditions, is approxi-

mately 5 meters, which falls short of meeting the stringent re-

quirements of location-sensitive applications. Hence, wireless

positioning systems in the millimeter wave (mmWave) band

were advocated by some researchers as a way to improve the

positioning performance [3]. However, due to the sensitivity

of mmWave signals to blockages, high-precision positioning

is difﬁcult to maintain [4].

Reconﬁgurable intelligent surface (RIS) is an emerging

technique for mmWave positioning systems with several ad-

vantages [5]–[10]. First, the RIS can reconstruct a new line-of-

sight (LoS) communication link if the direct link was blocked

by obstacles [7]. Second, the RIS provides reliable and high-

precision estimation with low energy consumption [9]. Finally,

the RIS saves hardware costs when deploying a wireless

positioning reference compared with the access point (AP)

(Corresponding author: Cunhua Pan).

T. Wu and M.Elkashlan are with the School of Electronic Engineering and

Computer Science at Queen Mary University of London, London E1 4NS,

U.K. (Email:{tuo.wu, maged.elkashlan}@qmul.ac.uk). C. Pan, Y. Pan and

H. Ren are with the National Mobile Communications Research Laboratory,

Southeast University, Nanjing 210096, China. C.-X. Wang is with the National

Mobile Communications Research Laboratory, Southeast University, Nanjing

210096, China, and also with the Purple Mountain Laboratories, Nanjing,

211111, China. (Email: {cpan, panyj, hren, chxwang}@seu.edu.cn).

[8]. Thus, wireless positioning algorithms aided by the RIS is

a promising enabler for sixth-generation (6G) wireless systems

[10].

Currently, wireless positioning algorithms aided by the RIS

have been studied by some researchers, including two-step

positioning algorithms and ﬁngerprint based algorithms [11],

[12]. For two-step positioning algorithms, the channel parame-

ters, e.g., time delay and angle of arrival (AOA), are estimated

at the ﬁrst step. At the second step, the channel parameters

can be used to derive the three-dimensional (3D) position of

the mobile user (MU) by using the geometry relationship. For

instance, a near-ﬁeld joint channel estimation and localiza-

tion algorithm was proposed in [11]. However, the two-step

positioning algorithms depend on the channel parameters esti-

mation, which require line-of-sight (LoS) measurement. These

algorithms may not be suitable for indoor localization as the

LoS links may be blocked by obstacles. Without estimating the

channel parameters, ﬁngerprint based positioning algorithms

directly predict the position by using the ﬁngerprint (e.g.,

received signal strength information (RSSI)). For example,

[12] regarded RSSI as a type of ﬁngerprint to predict the

MUs aided by the RIS. However, RSSI-based ﬁngerprint

localization algorithms can be unstable due to the fast fading

ﬂuctuation. Recently, some researchers proposed the channel

state information (CSI) as the ﬁngerprint, due to its potential

to enhance the positioning accuracy compared with RSSI [13].

Against the above background, the main contributions of

this paper are summarized as follows:

1) For the ﬁngerprint based mmWave positioning system,

we propose a new type of ﬁngerprint, space-time channel

response vector (STCRV), which consists of multipath

channel characteristics. The proposed STCRV ﬁngerprint

is closely related to the position of the MU.

2) Utilizing the STCRV as the wireless positioning ﬁnger-

print, we propose a novel residual convolution network

regression (RCNR) learning algorithm to estimate the 3D

positions of the MUs. Speciﬁcally, STCRV is processed

by a data processing block at ﬁrst. Then, a normal

convolution block is then used to extract the features of

the output from the data processing block. Consequently,

four residual convolution blocks are utilized to further

extract the features and protect the integrity. Finally, the

3D position is estimated through a regression block.

3) Simulation results are provided to evaluate the perfor-

mance of the proposed RCNR learning algorithm. The

proposed algorithm outperforms the CNN in terms of root

mean square error (RMSE).

arXiv:2210.11998v1 [eess.SP] 21 Oct 2022

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

1FingerprintBasedmmWavePositioningSystemAidedbyRecongurableIntelligentSurfaceTuoWu,CunhuaPan,YijinPan,HongRen,MagedElkashlan,andCheng-XiangWang,FellowIEEEAbstractRecongurableintelligentsurface(RIS)isapromis-ingtechniqueformillimeterwave(mmWave)positioningsystems.Inthispaper,weconsidermultiplemobi...

展开>> 收起<<

1 Fingerprint Based mmWave Positioning System Aided by Reconﬁgurable Intelligent Surface.pdf

共5页,预览1页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

1 Fingerprint Based mmWave Positioning System Aided by Reconﬁgurable Intelligent Surface

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: