Digital Twin-Guided Wireless Localization via Probabilistic Inverse Learning
Abstract
This work investigates how site-specific digital twins (DTs) can support wireless localization using simplified distributed infrastructure. We propose PRISM (Probabilistic Refinement using Inverse learning and a Site-specific Model), a DT-guided probabilistic localization scheme with single-antenna access points (APs). Localization is formulated as a probabilistic inverse problem in which a conditional proposal distribution over UE locations is learned from multi-node channel impulse responses (CIRs). The proposal generates candidate locations, with its spread regularized during training and DT consistency used to reweight candidates and refine the estimate at inference. The DT serves as an approximate forward-consistency model, avoiding assumptions of exact channel fidelity or differentiability with respect to user position. Numerical experiments demonstrate gains over data-driven and classical fingerprinting benchmarks, while achieving a median error of approximately $0.7$ m using 10 single-antenna APs. Without retraining, PRISM remains effective under degraded inference-time DT features. PRISM also yields uncertainty estimates from its proposal covariance, with empirical χ2 calibration approaching ideal behavior as APs increase.
Related
- Learning in Inverse Games: Tractable Training with Probabilistic Guarantees
- Task-Aware Beamforming for Semantic Wireless Localization
- Agentic Wireless Digital Twin Construction and Calibration Using Real-World Measurements
- Large Language Models Meet Bayesian Optimization: Towards Self-evolving Wireless Digital Twins
- Tri-Band Channel Measurement-Enabled Multi-Layer Digital Twin for Terahertz Wireless Data Centers
BibTeX
@misc{abouamer2026digital,
title = {{Digital Twin-Guided Wireless Localization via Probabilistic Inverse Learning}},
author = {Mahmoud Saad Abouamer and Henrik C. M. Frederiksen and Robin J. Williams and Shashi Raj Pandey and Petar Popovski},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.36905},
eprint = {2610.36905},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.36905},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Digital Twin-Guided Wireless Localization via Probabilistic Inverse Learning
AU - Mahmoud Saad Abouamer
AU - Henrik C. M. Frederiksen
AU - Robin J. Williams
AU - Shashi Raj Pandey
AU - Petar Popovski
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.36905
UR - https://arxiv.org/abs/2610.36905
AB - This work investigates how site-specific digital twins (DTs) can support wireless localization using simplified distributed infrastructure. We propose PRISM (Probabilistic Refinement using Inverse learning and a Site-specific Model), a DT-guided probabilistic localization scheme with single-antenna access points (APs). Localization is formulated as a probabilistic inverse problem in which a conditional proposal distribution over UE locations is learned from multi-node channel impulse responses (CIRs). The proposal generates candidate locations, with its spread regularized during training and DT consistency used to reweight candidates and refine the estimate at inference. The DT serves as an approximate forward-consistency model, avoiding assumptions of exact channel fidelity or differentiability with respect to user position. Numerical experiments demonstrate gains over data-driven and classical fingerprinting benchmarks, while achieving a median error of approximately $0.7$ m using 10 single-antenna APs. Without retraining, PRISM remains effective under degraded inference-time DT features. PRISM also yields uncertainty estimates from its proposal covariance, with empirical χ^2 calibration approaching ideal behavior as APs increase.
ER -