Collaborative SLAM Based on WiFi Fingerprint Similarity and Motion Information

Simultaneous localization and mapping (SLAM) has been extensively researched in past years particularly with regard to range-based or visual-based sensors. Instead of deploying dedicated devices that use visual features, it is more pragmatic to exploit the radio features to achieve this task, due to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE internet of things journal 2020-03, Vol.7 (3), p.1826-1840
Hauptverfasser: Liu, Ran, Marakkalage, Sumudu Hasala, Padmal, Madhushanka, Shaganan, Thiruketheeswaran, Yuen, Chau, Guan, Yong Liang, Tan, U-Xuan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Simultaneous localization and mapping (SLAM) has been extensively researched in past years particularly with regard to range-based or visual-based sensors. Instead of deploying dedicated devices that use visual features, it is more pragmatic to exploit the radio features to achieve this task, due to their ubiquitous nature and the widespread deployment of the Wi-Fi wireless network. This article presents a novel approach for collaborative simultaneous localization and radio fingerprint mapping (C-SLAM-RF) in large unknown indoor environments. The proposed system uses received signal strengths (RSS) from Wi-Fi access points (APs) in the existing infrastructure and pedestrian dead reckoning (PDR) from a smartphone, without a prior knowledge about map or distribution of AP in the environment. We claim a loop closure based on the similarity of the two radio fingerprints. To further improve the performance, we incorporate the turning motion and assign a small uncertainty value to a loop closure if a matched turning is identified. The experiment was done in an area of 130 m by 70 m and the results show that our proposed system is capable of estimating the tracks of four users with an accuracy of 0.6 m with Tango-based PDR and 4.76 m with a step counter-based PDR.
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2019.2957293