基於無線區域網路之手持式室內定位系統

Abstract

在本論文中提出一個以無線區域網路(Wireless Local Area Network, WLAN)接收訊號強度值(Received Signal Strength Indication, RSSI)為基礎的手持式室內定位(Localization)系統，鑒於近年來無線區域網路以及定位服務蓬勃發展，室內環境普遍皆有架設無線網路基地台(Access Point, AP)，所形成的無線區域網路可方便使用者利用移動式裝置，接收無線區域網路之無線訊號並使用上網功能，本文中針對無線區域網路中的訊號強度，以內差法(Interpolation)、曲線擬合法(Curve Fitting)及適應性網路模糊推論系統(Adaptive Neural Fuzzy Inference System, ANFIS)，建立起室內環境下之無線傳播衰減模型(Radio propagation model)，利用該訊號模型可將接收訊號強度映射至相對應實際空間中的距離，透過擴展式卡爾曼濾波器(Extended Kalman Filter, EKF)估測出所在之位置。本論文所提出的手持式室內定位系統，不但可用於估測移動裝置使用者位置資訊，還能提供網路基地台自動偵測訊號強度並切換的機制，而所有定位的資訊亦可讓遠端的另一位使用者透過網路查詢。實驗結果皆成功地驗證了所提出的出之功能，並提供精確且穩定的位置估測。

In this study, a handheld indoor localization system based on the Received Signal Strength Indication (RSSI) from Wireless Local Area Network (WLAN) is proposed. Booming wireless LAN and location-based service, the wireless networks have become a critical part of the networking infrastructure, and capable for mobile devices equipped with WLAN to receive the radio signal for networking. We propose to utilize WLAN received signal strength recorded by a handheld device to develop the radio propagation channel model with interpolation, curve fitting and Adaptive Neural Fuzzy Inference System (ANFIS) respectively. Thus the strength of the received radio signal can be converted to a physical distance approximately. The available distances from the positions localized in the test bed are estimated by using an Extended Kalman Filter (EKF). In addition, the presented handheld system can provide not only user location service but also the client remote inquiry and AP roaming. Consequently, the experimental results show that the presented specific functions are verified and our approach can provide an accurate localization.