A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based Sensor
Accurate localization is crucial for numerous applications. While several methods exist for outdoor localization, typically relying on GPS signals, these approaches become unreliable in environments subject to a weak GPS signal or GPS outage. Many researchers have attempted to address this limitatio...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/522 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587488413089792 |
|---|---|
| author | Kévin Cédric Guyard Jonathan Bertolaccini Stéphane Montavon Michel Deriaz |
| author_facet | Kévin Cédric Guyard Jonathan Bertolaccini Stéphane Montavon Michel Deriaz |
| author_sort | Kévin Cédric Guyard |
| collection | DOAJ |
| description | Accurate localization is crucial for numerous applications. While several methods exist for outdoor localization, typically relying on GPS signals, these approaches become unreliable in environments subject to a weak GPS signal or GPS outage. Many researchers have attempted to address this limitation, primarily focusing on real-time solutions. However, for applications that do not require real-time localization, these methods remain suboptimal. This paper presents a novel Transformer-based bidirectional encoder approach to address, in postprocessing, the localization challenges during GPS weak signal phases or GPS outages. Our method predicts the velocity during periods of weak or lost GPS signals and calculates the position through bidirectional velocity integration. Additionally, it incorporates position interpolation to ensure smooth transitions between active GPS and GPS outage phases. Applied to a dataset tracking horse positions—which features velocities up to 10 times those of pedestrians and higher acceleration—our approach achieved an average trajectory error below 3 m, while maintaining stable relative distance errors regardless of the GPS outage duration. |
| format | Article |
| id | doaj-art-3a557ff723754c3ebc1f5f9577406900 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-3a557ff723754c3ebc1f5f95774069002025-01-24T13:49:14ZengMDPI AGSensors1424-82202025-01-0125252210.3390/s25020522A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based SensorKévin Cédric Guyard0Jonathan Bertolaccini1Stéphane Montavon2Michel Deriaz3Information Science Institute, GSEM/CUI, University of Geneva, 1227 Carouge, SwitzerlandInformation Science Institute, GSEM/CUI, University of Geneva, 1227 Carouge, SwitzerlandVeterinary Department of the Swiss Armed Force, 3003 Berne, SwitzerlandHaute Ecole de Gestion Genève, HES-SO, 1227 Carouge, SwitzerlandAccurate localization is crucial for numerous applications. While several methods exist for outdoor localization, typically relying on GPS signals, these approaches become unreliable in environments subject to a weak GPS signal or GPS outage. Many researchers have attempted to address this limitation, primarily focusing on real-time solutions. However, for applications that do not require real-time localization, these methods remain suboptimal. This paper presents a novel Transformer-based bidirectional encoder approach to address, in postprocessing, the localization challenges during GPS weak signal phases or GPS outages. Our method predicts the velocity during periods of weak or lost GPS signals and calculates the position through bidirectional velocity integration. Additionally, it incorporates position interpolation to ensure smooth transitions between active GPS and GPS outage phases. Applied to a dataset tracking horse positions—which features velocities up to 10 times those of pedestrians and higher acceleration—our approach achieved an average trajectory error below 3 m, while maintaining stable relative distance errors regardless of the GPS outage duration.https://www.mdpi.com/1424-8220/25/2/522localization reconstruction during GPS outagesTransformerbidirectional encoderdeep learningtime series |
| spellingShingle | Kévin Cédric Guyard Jonathan Bertolaccini Stéphane Montavon Michel Deriaz A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based Sensor Sensors localization reconstruction during GPS outages Transformer bidirectional encoder deep learning time series |
| title | A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based Sensor |
| title_full | A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based Sensor |
| title_fullStr | A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based Sensor |
| title_full_unstemmed | A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based Sensor |
| title_short | A Transformer Encoder Approach for Localization Reconstruction During GPS Outages from an IMU and GPS-Based Sensor |
| title_sort | transformer encoder approach for localization reconstruction during gps outages from an imu and gps based sensor |
| topic | localization reconstruction during GPS outages Transformer bidirectional encoder deep learning time series |
| url | https://www.mdpi.com/1424-8220/25/2/522 |
| work_keys_str_mv | AT kevincedricguyard atransformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor AT jonathanbertolaccini atransformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor AT stephanemontavon atransformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor AT michelderiaz atransformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor AT kevincedricguyard transformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor AT jonathanbertolaccini transformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor AT stephanemontavon transformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor AT michelderiaz transformerencoderapproachforlocalizationreconstructionduringgpsoutagesfromanimuandgpsbasedsensor |