Digital twin enhances wireless user location with probabilistic modeling
Digital Twin-Guided Wireless Localization via Probabilistic Inverse Learning
Information Theory
Summary
Locating wireless devices indoors is hard and often requires a lot of hardware. The authors show how a digital twin, a virtual model of the site, can help estimate where a device is with fewer antennas. Their method learns to propose possible device locations based on signal data and uses the digital twin to check and improve these guesses. This approach reduces error and can measure its own uncertainty, even when the digital twin model isn’t perfect.
What this means in practice
- •For wireless network engineers: Use simplified single-antenna setups with digital twins to improve indoor device localization accuracy without complex hardware upgrades.
- •For smart building system integrators: Implement precise indoor location tracking using site models to enable location-based services while minimizing infrastructure costs.
Authors
Mahmoud Saad Abouamer, Henrik C. M. Frederiksen, Robin J. Williams, Shashi Raj Pandey, Petar Popovski
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 $χ^2$ calibration approaching ideal behavior as APs increase.