TDoA-Based Self-Supervised Channel Charting with NLoS Mitigation

2025-10-09

AI Summary

Existing channel charting (CC) methods suffer from poor global scalability and inadequate robustness against non-line-of-sight (NLoS)-induced localization errors. To address these limitations, this paper proposes a globally scalable, self-supervised wireless localization framework. It leverages enhanced channel impulse response (CIR) data, jointly fusing time-difference-of-arrival (TDoA) measurements with transmitter–receiver position priors, while enforcing localization continuity via short-term user displacement modeling. A novel NLoS noise identification and dynamic masking mechanism is introduced to significantly improve NLoS robustness. The framework is end-to-end validated on the 5G OpenAirInterface platform within an O-RAN architecture. Experiments in real-world 5G deployments demonstrate sub-4-meter accuracy in 90% of scenarios—outperforming state-of-the-art semi-supervised and self-supervised approaches. Additionally, we publicly release the first large-scale CIR dataset annotated with ground-truth localization labels.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Local Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Channel Charting (CC) has emerged as a promising framework for data-driven radio localization, yet existing approaches often struggle to scale globally and to handle the distortions introduced by non-line-of-sight (NLoS) conditions. In this work, we propose a novel CC method that leverages Channel Impulse Response (CIR) data enriched with practical features such as Time Difference of Arrival (TDoA) and Transmission Reception Point (TRP) locations, enabling a self-supervised localization function on a global scale. The proposed framework is further enhanced with short-interval User Equipment (UE) displacement measurements, which improve the continuity and robustness of the learned positioning function. Our algorithm incorporates a mechanism to identify and mask NLoS-induced noisy measurements, leading to significant performance gains. We present the evaluations of our proposed models in a real 5G testbed and benchmarked against centimeter-accurate Real-Time Kinematic (RTK) positioning, in an O-RAN--based 5G network by OpenAirInterface (OAI) software at EURECOM. It demonstrated outperforming results against the state-of-the-art semi-supervised and self-supervised CC approaches in a real-world scenario. The results show localization accuracies of 2-4 meters in 90% of cases, across a range of NLoS ratios. Furthermore, we provide public datasets of CIR recordings, along with the true position labels used in this paper's evaluation.

Problem

• Improving radio localization accuracy in non-line-of-sight conditions
• Developing scalable self-supervised positioning using TDoA features
• Mitigating NLoS distortions in channel charting for global applications

Innovation

• Uses TDoA and TRP data for self-supervised localization
• Integrates UE displacement to enhance positioning robustness
• Identifies and masks NLoS measurements to improve accuracy