Toward Large-Scale and Robust Indoor Positioning: Deep Learning-Augmented VLP/INS Fusion With Efficient Anchor Calibration
IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 14000-14016
DOI: 10.1109/tmc.2026.3676727 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Xiaoxiang Cao und 6 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Gefördert von: China Postdoctoral Science Foundation, National Natural Science Foundation of China, Natural Science Foundation of Hubei Province.
Abstract (Originalsprache)
Visible Light Positioning (VLP) has emerged as a promising indoor localization technology owing to its high accuracy, low power consumption, and lighting compatibility. The Received Signal Strength (RSS)-based multi-anchor VLP preserves these advantages while having drawn considerable research attention due to its simple implementation and high reliability. However, its large-scale deployment encounters challenges at every stage: inefficient anchor calibration, limited model-based ranging performance, and robustness reduction from undetected gross errors. To address these issues, we propose a VLP and inertial navigation system fusion framework comprising an anchor position estimation module, a distance estimation module, and a fusion positioning module. For anchor calibration, a LiDAR-inertial odometry-based calibration scheme enhanced by a two-layer optimization strategy is introduced, which provides prior knowledge of anchor positions for the whole system. To improve the performance of the RSS-based ranging method, a hybrid Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-Bidirectional Long Short-Term Memory (Bi-LSTM) network with an embedded distance quality assessor is developed, achieving over 50% higher accuracy than model-based baselines. It delivers precise distance estimates and their validity labels for measurement updates in subsequent fusion positioning. Additionally, a two-stage error detection mechanism filters low-quality observations by combining network-generated usability labels with prior-state estimates. The system consistently attains decimeter-level positioning across various trajectories, meeting the needs of diverse Internet of Things applications.
Förderung
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
- Natural Science Foundation of Hubei Province
- Postdoctoral Fellowship Program of CPSF
- Postdoctoral Project of Hubei Province
- Open Fund of State Key Laboratory for Safe Mining of Deep Coal Resources and Environment Protection
Zitieren
APA
Cao, X., Wang, X., Yu, T., Zhang, Z., Bi, J., Yu, Y., & Hu, Y. (2026). Toward Large-Scale and Robust Indoor Positioning: Deep Learning-Augmented VLP/INS Fusion With Efficient Anchor Calibration. IEEE Transactions on Mobile Computing, 25(9), 14000-14016. https://doi.org/10.1109/tmc.2026.3676727
Vancouver
Cao X, Wang X, Yu T, Zhang Z, Bi J, Yu Y, et al. Toward Large-Scale and Robust Indoor Positioning: Deep Learning-Augmented VLP/INS Fusion With Efficient Anchor Calibration. IEEE Transactions on Mobile Computing. 2026;25(9):14000-14016. doi:10.1109/tmc.2026.3676727
BibTeX
@article{Cao2026,
author = {Cao, Xiaoxiang and Wang, Xuan and Yu, Tengfei and Zhang, Zhenghua and Bi, Jingxue and Yu, Yue and Hu, Yulin},
title = {Toward Large-Scale and Robust Indoor Positioning: Deep Learning-Augmented VLP/INS Fusion With Efficient Anchor Calibration},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {9},
pages = {14000--14016},
doi = {10.1109/tmc.2026.3676727}
}
EUVIMED