LOCUS-DT: Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins

2026-07-31

AI Summary

This work addresses the challenge of accurate indoor localization in complex environments, where occlusion and multipath effects hinder conventional single-point methods from properly modeling multimodal posterior position distributions. Treating snapshot-based localization as a posterior inference problem over emitter location, the authors propose a framework integrating digital twins and ray tracing (Sionna) to generate synthetic multipath signatures from candidate positions. A learnable scoring function is designed to match dominant specular paths between measured and simulated channels. The approach innovatively incorporates an observation-conditioned uncertainty scoring mechanism and a cross-environment training strategy, enabling—for the first time within a digital twin framework—an effective characterization of sharp, multimodal posterior structures. This yields substantially improved localization accuracy and robustness compared to Gaussian or Gaussian mixture baseline methods.

Abstract

Accurate indoor localization is essential for emerging applications in robotic navigation and search and rescue. While classical methods typically focus on single-point estimates, complex indoor environments with heavy blockage and multipath propagation often lead to multimodal likelihood surfaces where a single estimate is insufficient. This paper proposes LOCUS-DT (Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins), a framework that treats snapshot localization as posterior inference over the transmitter location. By leveraging a ray-tracing-based digital twin (DT) of the known environment, LOCUS-DT generates synthetic multipath profiles for candidate locations and compares them against the measured channel profile. Central to our approach is a novel learned scoring function designed to compare a fixed number of dominant specular paths, providing robustness against errors in both the DT environment model and the physical channel estimation. Importantly, LOCUS-DT is trained over an ensemble of environments to ensure generalization to unseen layouts. We evaluate the system using a Sionna-based ray-tracing backend, demonstrating that LOCUS-DT captures the sharp, multimodal posterior structures inherent in indoor settings more accurately than standard Gaussian or Gaussian-mixture benchmarks.

Problem

• indoor localization
• multipath propagation
• multimodal likelihood
• digital twins
• posterior inference

Innovation

• Digital Twin
• Uncertainty Scoring
• Multipath Localization
• Posterior Inference
• Ray Tracing