A UWB/IMU-Assisted Fingerprinting Localization Framework with Low Human Efforts  

作　　者：Pan Hao Chen Yu Qi Xiaogang Liu Meili 

机构地区：[1]School of Mathematics and Statistics,Xidian University,Xi’an 710126,China [2]Science and Technology on Near-Surface Detection Laboratory,Wuxi 214035,China [3]School of Software,Nanchang Hangkong University,Nanchang 330063,China

出　　处：《China Communications》2024年第6期40-52,共13页中国通信（英文版）

摘　　要：With the rapid development of smart phone,the location-based services(LBS)have received great attention in the past decades.Owing to the widespread use of WiFi and Bluetooth devices,Received Signal Strength Indication(RSSI)fingerprintbased localization method has obtained much development in both academia and industries.In this work,we introduce an efficient way to reduce the labor-intensive site survey process,which uses an UWB/IMU-assisted fingerprint construction(UAFC)and localization framework based on the principle of Automatic radio map generation scheme(ARMGS)is proposed to replace the traditional manual measurement.To be specific,UWB devices are employed to estimate the coordinates when the collector is moved in a reference point(RP).An anchor self-localization method is investigated to further reduce manual measurement work in a wide and complex environment,which is also a grueling,time-consuming process that is lead to artificial errors.Moreover,the measurements of IMU are incorporated into the UWB localization algorithm and improve the label accuracy in fingerprint.In addition,the weighted k-nearest neighbor(WKNN)algorithm is applied to online localization phase.Finally,filed experiments are carried out and the results confirm the effectiveness of the proposed approach.

关 键 词：indoor localization machine learning ultra wideband WiFi fingerprint 

分 类 号：TN92[电子电信—通信与信息系统]