Seamless indoor outdoor navigation

Nowadays, autonomous robotic applications that operated indoor and outdoor are gaining popularity in the delivery, cleaning, and disinfection field due to the Coronavirus pandemic. Ideally, whenever there is a mobile robot applied in the real world, the robot should be capable to perform seamless in...

Full description

Saved in:
Bibliographic Details
Main Author: Liew, Wan Seng
Other Authors: Ang Wei Tech
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/154671
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-154671
record_format dspace
spelling sg-ntu-dr.10356-1546712022-01-04T07:34:19Z Seamless indoor outdoor navigation Liew, Wan Seng Ang Wei Tech School of Mechanical and Aerospace Engineering WTAng@ntu.edu.sg Engineering::Mechanical engineering Nowadays, autonomous robotic applications that operated indoor and outdoor are gaining popularity in the delivery, cleaning, and disinfection field due to the Coronavirus pandemic. Ideally, whenever there is a mobile robot applied in the real world, the robot should be capable to perform seamless indoor-outdoor navigation so that their functionalities could be more diversified. Compared to indoor navigation, which is a mostly solved topic and widely used nowadays, there is still no definite way in performing outdoor navigation, let alone travel from indoor to outdoor and vice versa. This is because the cost of applying the state-of-the-art Simultaneous Localization and Mapping (SLAM) on outdoor navigation is high and not realistic. Hence, there is a need to develop an indoor-outdoor navigation system for mobile robots to travel indoor and outdoor reliably at a reasonable cost. In this report, the navigation framework developed aims to integrate the map data extracted from the Google Maps Platform and a civil-standard GPS sensor with the conventional navigation stack of the mobile robot without utilising any SLAM element. The benefits of this framework include it eliminates the need of doing the tedious pre-mapping process and does not require any LIDAR sensor, which is commonly used in SLAM. The mobile robot platform used in this report is a wheelchair that aims to facilitate the movement of a patient with acute mobility impairment. Apart from that, this report will explore the other key components that are necessary for indoor-outdoor navigation such as the computer vision in identifying travelable outdoor paths and indoor localization sensor, Ultra-Wideband (UWB). The computer vision model utilizes the techniques of OpenCV and the performance is compared with the Nvidia Free Space Segmentation. The localization of the mobile robot is dependent on the GPS sensor outdoor while UWB at indoor, this report will also evaluate the effectiveness of both localization sensors in the navigation system. Bachelor of Engineering (Mechanical Engineering) 2022-01-04T07:34:18Z 2022-01-04T07:34:18Z 2021 Final Year Project (FYP) Liew, W. S. (2021). Seamless indoor outdoor navigation. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/154671 https://hdl.handle.net/10356/154671 en A268 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Mechanical engineering
spellingShingle Engineering::Mechanical engineering
Liew, Wan Seng
Seamless indoor outdoor navigation
description Nowadays, autonomous robotic applications that operated indoor and outdoor are gaining popularity in the delivery, cleaning, and disinfection field due to the Coronavirus pandemic. Ideally, whenever there is a mobile robot applied in the real world, the robot should be capable to perform seamless indoor-outdoor navigation so that their functionalities could be more diversified. Compared to indoor navigation, which is a mostly solved topic and widely used nowadays, there is still no definite way in performing outdoor navigation, let alone travel from indoor to outdoor and vice versa. This is because the cost of applying the state-of-the-art Simultaneous Localization and Mapping (SLAM) on outdoor navigation is high and not realistic. Hence, there is a need to develop an indoor-outdoor navigation system for mobile robots to travel indoor and outdoor reliably at a reasonable cost. In this report, the navigation framework developed aims to integrate the map data extracted from the Google Maps Platform and a civil-standard GPS sensor with the conventional navigation stack of the mobile robot without utilising any SLAM element. The benefits of this framework include it eliminates the need of doing the tedious pre-mapping process and does not require any LIDAR sensor, which is commonly used in SLAM. The mobile robot platform used in this report is a wheelchair that aims to facilitate the movement of a patient with acute mobility impairment. Apart from that, this report will explore the other key components that are necessary for indoor-outdoor navigation such as the computer vision in identifying travelable outdoor paths and indoor localization sensor, Ultra-Wideband (UWB). The computer vision model utilizes the techniques of OpenCV and the performance is compared with the Nvidia Free Space Segmentation. The localization of the mobile robot is dependent on the GPS sensor outdoor while UWB at indoor, this report will also evaluate the effectiveness of both localization sensors in the navigation system.
author2 Ang Wei Tech
author_facet Ang Wei Tech
Liew, Wan Seng
format Final Year Project
author Liew, Wan Seng
author_sort Liew, Wan Seng
title Seamless indoor outdoor navigation
title_short Seamless indoor outdoor navigation
title_full Seamless indoor outdoor navigation
title_fullStr Seamless indoor outdoor navigation
title_full_unstemmed Seamless indoor outdoor navigation
title_sort seamless indoor outdoor navigation
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/154671
_version_ 1722355306842816512