Indoor navigation incorporating multiple localisation sources and pedestrian dead reckoning

Navigation systems have become an integral part of our daily lives. The Global Positioning System (GPS) is widely used to determine outdoor positions and is capable of achieving high accuracy and reliability due to extensive research over the years. However, it is unable to replicate such results f...

Full description

Saved in:
Bibliographic Details
Main Author: Lim, Bo Zhi
Other Authors: Oh Hong Lye
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/148055
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Navigation systems have become an integral part of our daily lives. The Global Positioning System (GPS) is widely used to determine outdoor positions and is capable of achieving high accuracy and reliability due to extensive research over the years. However, it is unable to replicate such results for indoor localisation. Indoor localisation instead utilises other technologies developed over the past couple of years such as Wi-Fi fingerprinting and Bluetooth Low Energy (BLE) beacons. These technologies achieve decent results alone, but their accuracy and efficiency improves when utilised in combination. This project explores the possibilities of combining various localisation technologies, such as GPS, Wi-Fi fingerprinting and BLE beacons, with methodologies such as Pedestrian Dead Reckoning (PDR), to obtain accurate location estimations in short intervals. This project also involved the participation in an Indoor Positioning and Indoor Navigation (IPIN) Indoor Localisation Competition to gain insights on the localisation technologies and methodologies. Experimental results show a slight improvement over Wi-Fi fingerprinting and GPS, with possible rooms for improvement, while a feasibility study is scheduled to be conducted to evaluate the feasibility of the algorithm in an actual use-case scenario.