Probabilistic Condition-Aware Dual-Branch Model for Multipath-Resilient Wireless Localization
IEEE Communications Letters · 2026 · 30 · 2565-2569
DOI: 10.1109/lcomm.2026.3711349 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Yaping Zhu und 3 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Science and Technology Innovation Action Plan Project.
Abstract (Originalsprache)
Wireless localization in complex propagation environments remains challenging due to the heterogeneous channel-location relationships induced by varying propagation conditions. Conventional unified localization models often fail to adequately capture such condition-dependent characteristics, leading to degraded positioning accuracy and limited robustness. To address this issue, this letter proposes a probabilistic condition-aware dual-branch localization framework that explicitly incorporates propagation uncertainty into the localization process. By modeling the location posterior as a mixture of LOS- and NLOS-conditioned predictors and adaptively fusing their outputs via a learned probabilistic router, the proposed approach enables propagation-aware localization without requiring explicit state observation at inference. A two-stage training strategy ensures stable learning of state-specialized representations and routing weights. Experiments demonstrate that the proposed method consistently outperforms both unified regression and hard-decision baselines, particularly in challenging NLOS scenarios. Source code is available at https://github.com/jzengust/Res-SR.
Förderung
- National Natural Science Foundation of China
- Shanghai Science and Technology Innovation Action Plan Project
Zitieren
APA
Zhu, Y., Chen, Y., Zeng, J., & Wang, J. (2026). Probabilistic Condition-Aware Dual-Branch Model for Multipath-Resilient Wireless Localization. IEEE Communications Letters, 30, 2565-2569. https://doi.org/10.1109/lcomm.2026.3711349
Vancouver
Zhu Y, Chen Y, Zeng J, Wang J. Probabilistic Condition-Aware Dual-Branch Model for Multipath-Resilient Wireless Localization. IEEE Communications Letters. 2026;30:2565-2569. doi:10.1109/lcomm.2026.3711349
BibTeX
@article{Zhu2026,
author = {Zhu, Yaping and Chen, Yilong and Zeng, Jin and Wang, Junyuan},
title = {Probabilistic Condition-Aware Dual-Branch Model for Multipath-Resilient Wireless Localization},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {2565--2569},
doi = {10.1109/lcomm.2026.3711349}
}
EUVIMED