UWB TDoA Error Correction using Transformers: Patching and Positional Encoding Strategies

2025-07-04

AI Summary

In industrial environments, UWB TDoA localization suffers from multipath propagation and non-line-of-sight (NLOS) effects, while conventional NLOS link removal strategies exacerbate geometric dilution of precision (GDOP). To address this, we propose a Transformer-based end-to-end TDoA error correction method. Instead of discarding NLOS links, our approach directly processes raw channel impulse response (CIR) sequences from all anchor nodes, leveraging customized patching, multi-order sequence rearrangement, and positional encoding to comprehensively model signal delay characteristics under full-NLOS conditions—thereby preserving critical information. Experiments in highly NLOS-dominant industrial settings demonstrate a positioning accuracy of 0.39 m, representing a 73.6% improvement over the standard TDoA baseline. Our method effectively mitigates GDOP degradation and establishes a new paradigm for robust localization in heavily occluded environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Despite their high accuracy, UWB-based localization systems suffer inaccuracies when deployed in industrial locations with many obstacles due to multipath effects and non-line-of-sight (NLOS) conditions. In such environments, current error mitigation approaches for time difference of arrival (TDoA) localization typically exclude NLOS links. However, this exclusion approach leads to geometric dilution of precision problems and this approach is infeasible when the majority of links are NLOS. To address these limitations, we propose a transformer-based TDoA position correction method that uses raw channel impulse responses (CIRs) from all available anchor nodes to compute position corrections. We introduce different CIR ordering, patching and positional encoding strategies for the transformer, and analyze each proposed technique's scalability and performance gains. Based on experiments on real-world UWB measurements, our approach can provide accuracies of up to 0.39 m in a complex environment consisting of (almost) only NLOS signals, which is an improvement of 73.6 % compared to the TDoA baseline.

Problem

• Mitigating UWB localization errors in multipath and NLOS environments
• Improving TDoA accuracy using transformer-based correction with raw CIRs
• Enhancing scalability and performance in complex industrial settings

Innovation

• Transformer-based TDoA error correction method
• Uses raw CIRs from all anchor nodes
• Introduces CIR patching and positional encoding