一种Wi-Fi RTT/数据驱动惯性导航行人室内定位方法  

A Wi-Fi RTT/data-driven inertial navigation pedestrian indoor positioning method

作　　者：周宝定[1] 胡超 孙超 刘旭 吴鹏[1] 杨钧富 ZHOU Baoding;HU Chao;SUN Chao;LIU Xu;WU Peng;YANG Junfu(School of Civil and Transportation Engineering,Shenzhen University,Shenzhen 518060,China;School of Architecture and Urban Planning,Shenzhen University,Shenzhen 518060,China;Sinopec Petroleum Engineering Geophysical Company Limited Beidou Operation Service Center,Nanjing 210000,China)

机构地区：[1]深圳大学土木与交通工程学院,广东深圳518060 [2]深圳大学建筑与城市规划学院,广东深圳518060 [3]中石化石油工程地球物理有限公司北斗运营服务中心,江苏南京210000

出　　处：《测绘通报》2024年第4期76-82,共7页Bulletin of Surveying and Mapping

摘　　要：为了研究基于智能手机的行人室内定位方法,并提高其精度,本文提出了一种基于Wi-Fi往返时间(RTT)、惯性测量单元(IMU)的定位系统。该方法主要包括3部分:(1)使用扩展卡尔曼滤波融合测距信息的Wi-Fi RTT室内定位方法;(2)适用于多手机使用模式的航位推算方法,该方法基于长短时记忆模型(LSTM)建立神经网络模型,预测行人运动速度及航向;(3)基于误差状态卡尔曼滤波的Wi-Fi RTT/数据驱动惯性导航融合定位方法,进一步提高定位精度。试验结果表明,与单一的基于Wi-Fi RTT方法和数据驱动惯性导航方法相比,本文方法的平均定位精度提升了10%~20%。In pursuit of investigating pedestrian indoor positioning methods based on smartphones and enhancing the precision of indoor pedestrian localization,this paper proposes a localization system utilizing Wi-Fi RTT and IMU for the indoor positioning of pedestrians using smartphones.The method comprises three key components:①The introduction of a Wi-Fi RTT indoor positioning method that employs extended Kalman filtering to integrate distance measurement information.②The proposition of a dead reckoning method suitable for multi-phone usage,utilizing LSTM to establish a neural network model for predicting pedestrian movement speed and heading.③The development of a fusion positioning method based on ESKF that combines Wi-Fi RTT and data-driven inertial navigation to further elevate positioning accuracy.Experimental findings illustrate that,in comparison to individual Wi-Fi RTT and data-driven inertial navigation methods,the proposed approach achieves an average improvement of 10%to 20%in positioning accuracy.

关 键 词：智能手机 数据驱动惯性导航 Wi-Fi RTT 行人航迹推算 融合定位 

分 类 号：P228[天文地球—大地测量学与测量工程]