This paper proposes a two-dimensonal positioning method based on a hidden Markov model map-matching scheme. The states of the hidden Markov model are generated by dividing the area of interest into a grid. At each time instant, the method considers two types of measurements: the platform's heading and the two-dimensional distance between the platform and the single-anchor. A recursive Bayesian estimator exploits these measurements to estimate the platform's position. The platform's heading measurement is used to calculate the prior probability distribution. Following this, observation likelihood is computed by considering the two-dimensional distance measurement as the observation of the hidden Markov model. Finally, the most probable projection of these measurements on the states of the hidden Markov model is estimated as the platform's position. The proposed method can be efficiently used, especially in constrained indoor and outdoor environments. Moreover, the method provides a two-dimensional positioning solution with an increased robustness thanks to the bounded error on the distance measurements. Simulation studies are provided to demonstrate the effectiveness of the proposed method.
Keyword: hidden Markov model; map-matching; recursive Bayesian estimation; single-anchor positioning
Publication Name (dc.title) | 2D-HASAP: Two-Dimensional Heading-Aided Single-Anchor Positioning via Hidden Markov Model Map-Matching |
Author/s (dc.contributor.yazarlar) | Serkan Zobar, Mehmet Çiydem, Özgül Salor, Charles K. Toth, Alper Yilmaz |
Publication type (dc.type) | Konferans Bildirisi |
Language (dc.language) | İngilizce |
Publication year (dc.date.issued) | 2023 |
National/International (dc.identifier.ulusaluluslararasi) | Uluslararası |
Source (dc.relation.journal) | IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems |
Additional source name / Conference information (dc.identifier.kaynakadiekbilgi) | 2023 IEEE Symposium Sensor Data Fusion and International Conference on Multisensor Fusion and Integration, SDF-MFI 2023.- Bonn, Germany.- 27-29 November 2023.- Kod 195797 |
ISSN/ISBN (dc.identifier.issn) | ISBN: 979-8-3503-8258-7 |
Publisher (dc.publisher) | IEEE Xplore Digital Librar, USA |
Databases (dc.contributor.veritaban) | IEEE Xplore |
Databases (dc.contributor.veritaban) | Scopus |
Index Type (dc.identifier.index) | Scopus |
Abstract (dc.description.abstract) | This paper proposes a two-dimensonal positioning method based on a hidden Markov model map-matching scheme. The states of the hidden Markov model are generated by dividing the area of interest into a grid. At each time instant, the method considers two types of measurements: the platform's heading and the two-dimensional distance between the platform and the single-anchor. A recursive Bayesian estimator exploits these measurements to estimate the platform's position. The platform's heading measurement is used to calculate the prior probability distribution. Following this, observation likelihood is computed by considering the two-dimensional distance measurement as the observation of the hidden Markov model. Finally, the most probable projection of these measurements on the states of the hidden Markov model is estimated as the platform's position. The proposed method can be efficiently used, especially in constrained indoor and outdoor environments. Moreover, the method provides a two-dimensional positioning solution with an increased robustness thanks to the bounded error on the distance measurements. Simulation studies are provided to demonstrate the effectiveness of the proposed method. |
Abstract (dc.description.abstract) | Keyword: hidden Markov model; map-matching; recursive Bayesian estimation; single-anchor positioning |
URL (dc.rights) | https://ieeexplore.ieee.org/document/10361293 |
DOI (dc.identifier.doi) | 10.1109/SDF-MFI59545.2023.10361293 |
Faculty / Institute (dc.identifier.fakulte) | Mühendislik Fakültesi |
Department (dc.identifier.bolum) | Elektrik-Elektronik Mühendisliği Bölümü |
Author(s) in the Institution (dc.contributor.author) | Özgül SALOR-DURNA |
Kayıt No (dc.identifier.kayitno) | BL60B0377E |
Record Add Date (dc.date.available) | 2024-01-25 |
Notes (Publication year) (dc.identifier.notyayinyili) | 2023 |
Subject Headings (dc.subject) | hidden Markov model |
Subject Headings (dc.subject) | map-matching |
Subject Headings (dc.subject) | recursive Bayesian estimation |
Subject Headings (dc.subject) | single-anchor positioning |