Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach

Indoor localization and navigation have become an increasingly important problem in both industry and academia with the widespread use of mobile smart devices and the development of network techniques. The Wi-Fi-based technology shows great potential for applications due to the ubiquitous Wi-Fi infr...

Full description

Bibliographic Details
Main Authors: Xuxin Lin, Jianwen Gan, Chaohao Jiang, Shuai Xue, Yanyan Liang
Format: Article
Language:English
Published: MDPI AG 2023-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/23/14/6320
_version_ 1797587500331433984
author Xuxin Lin
Jianwen Gan
Chaohao Jiang
Shuai Xue
Yanyan Liang
author_facet Xuxin Lin
Jianwen Gan
Chaohao Jiang
Shuai Xue
Yanyan Liang
author_sort Xuxin Lin
collection DOAJ
description Indoor localization and navigation have become an increasingly important problem in both industry and academia with the widespread use of mobile smart devices and the development of network techniques. The Wi-Fi-based technology shows great potential for applications due to the ubiquitous Wi-Fi infrastructure in public indoor environments. Most existing approaches use trilateration or machine learning methods to predict locations from a set of annotated Wi-Fi observations. However, annotated data are not always readily available. In this paper, we propose a robot-aided data collection strategy to obtain the limited but high-quality labeled data and a large amount of unlabeled data. Furthermore, we design two deep learning models based on a variational autoencoder for the localization and navigation tasks, respectively. To make full use of the collected data, a hybrid learning approach is developed to train the models by combining supervised, unsupervised and semi-supervised learning strategies. Extensive experiments suggest that our approach enables the models to learn effective knowledge from unlabeled data with incremental improvements, and it can achieve promising localization and navigation performance in a complex indoor environment with obstacles.
first_indexed 2024-03-11T00:40:49Z
format Article
id doaj.art-32c3f624306d4b9c8f82a143fc0d3b19
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-11T00:40:49Z
publishDate 2023-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-32c3f624306d4b9c8f82a143fc0d3b192023-11-18T21:16:05ZengMDPI AGSensors1424-82202023-07-012314632010.3390/s23146320Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning ApproachXuxin Lin0Jianwen Gan1Chaohao Jiang2Shuai Xue3Yanyan Liang4Faculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaFaculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaFaculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaFaculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaFaculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaIndoor localization and navigation have become an increasingly important problem in both industry and academia with the widespread use of mobile smart devices and the development of network techniques. The Wi-Fi-based technology shows great potential for applications due to the ubiquitous Wi-Fi infrastructure in public indoor environments. Most existing approaches use trilateration or machine learning methods to predict locations from a set of annotated Wi-Fi observations. However, annotated data are not always readily available. In this paper, we propose a robot-aided data collection strategy to obtain the limited but high-quality labeled data and a large amount of unlabeled data. Furthermore, we design two deep learning models based on a variational autoencoder for the localization and navigation tasks, respectively. To make full use of the collected data, a hybrid learning approach is developed to train the models by combining supervised, unsupervised and semi-supervised learning strategies. Extensive experiments suggest that our approach enables the models to learn effective knowledge from unlabeled data with incremental improvements, and it can achieve promising localization and navigation performance in a complex indoor environment with obstacles.https://www.mdpi.com/1424-8220/23/14/6320Wi-Fi-based indoor localization and navigationdeep reinforcement learningsemi-supervised learningunsupervised learning
spellingShingle Xuxin Lin
Jianwen Gan
Chaohao Jiang
Shuai Xue
Yanyan Liang
Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach
Sensors
Wi-Fi-based indoor localization and navigation
deep reinforcement learning
semi-supervised learning
unsupervised learning
title Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach
title_full Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach
title_fullStr Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach
title_full_unstemmed Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach
title_short Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach
title_sort wi fi based indoor localization and navigation a robot aided hybrid deep learning approach
topic Wi-Fi-based indoor localization and navigation
deep reinforcement learning
semi-supervised learning
unsupervised learning
url https://www.mdpi.com/1424-8220/23/14/6320
work_keys_str_mv AT xuxinlin wifibasedindoorlocalizationandnavigationarobotaidedhybriddeeplearningapproach
AT jianwengan wifibasedindoorlocalizationandnavigationarobotaidedhybriddeeplearningapproach
AT chaohaojiang wifibasedindoorlocalizationandnavigationarobotaidedhybriddeeplearningapproach
AT shuaixue wifibasedindoorlocalizationandnavigationarobotaidedhybriddeeplearningapproach
AT yanyanliang wifibasedindoorlocalizationandnavigationarobotaidedhybriddeeplearningapproach