EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds

Mohammed S Alharbi iD, Shinkyu Park iD

Sensors · 18.03.2026 · 26 (6) · 1904

DOI: 10.3390/s26061904 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.03.2026. Verfasst von Mohammed S Alharbi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Electrical and Computer Engineering Department, King Abdullah University of Science and Technology (KAUST), Thuwal 23955, Saudi Arabia. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Abdullah University of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Inertial localization is particularly valuable in GPS-denied environments such as indoors. However, localization using only Inertial Measurement Units (IMUs) suffers from drift caused by motion-process noise and sensor biases. This paper introduces Uncertainty-aware Map-constrained Inertial Localization (UMLoc), an end-to-end framework that jointly models IMU uncertainty and map constraints to achieve drift-resilient positioning. UMLoc integrates two coupled modules: (1) a Long Short-Term Memory (LSTM) quantile regressor, which estimates the specific quantiles needed to define 68%, 90% and 95% prediction intervals serving as a measure of localization uncertainty and (2) a Conditioned Generative Adversarial Network (CGAN) with cross-attention that fuses IMU dynamic data with distance-based floor-plan maps to generate geometrically feasible trajectories. The modules are trained jointly, allowing uncertainty estimates to propagate through the CGAN during trajectory generation. UMLoc was evaluated on three datasets, including a newly collected 2-h indoor benchmark with time-aligned IMU data, ground-truth poses and floor-plan maps. Results show that the method achieves a mean drift ratio of 5.9% over a 70m travel distance and an average Absolute Trajectory Error (ATE) of 1.36m, while maintaining calibrated prediction bounds.

Schlagwörter

Stichwörter der Autor:innen

Generative Adversarial Networks (GAN)Map-Aided LocalizationNeural Networksinertial localizationquantile regressionuncertainty estimation

Autor:innen und Institutionen

  • Electrical and Computer Engineering Department, King Abdullah University of Science and Technology (KAUST), Thuwal 23955, Saudi Arabia.

ORCID-Profile: Mohammed S Alharbi, Shinkyu Park

Förderung

  • King Abdullah University of Science and Technology

Zitieren

APA

Alharbi, M. S., & Park, S. (2026). UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds. Sensors, 26(6), 1904. https://doi.org/10.3390/s26061904

Vancouver

Alharbi MS, Park S. UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds. Sensors. 2026;26(6):1904. doi:10.3390/s26061904

BibTeX
@article{Alharbi2026,
  author = {Alharbi, Mohammed S and Park, Shinkyu},
  title = {UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1904},
  doi = {10.3390/s26061904}
}
Kostenlos starten →