Geometry-Aware Infrastructure-Anchored Denoiser for UWB Sensing and Work-Zone Reconstruction

2026-07-05

AI Summary

Outdoor ultra-wideband (UWB) ranging is highly susceptible to non-line-of-sight propagation, impulsive noise, and long-tailed error distributions, often leading to geometric reconstruction distortions. This work proposes GAIA, a novel framework that, for the first time, integrates geometric awareness into UWB denoising. By jointly optimizing infrastructure anchor positions and spatial constraints through temporal modeling, implicit anchor layout estimation, and deterministic distance projection, GAIA enables end-to-end learning tailored for reconstruction consistency. The method fuses multi-source data from UWB, GNSS, and IMU, embedding geometric projection constraints directly into the supervised denoising task. Evaluated on real-world outdoor datasets, GAIA reduces ranging mean squared error by 18.4% and improves polygon IoU by 15.5% compared to PoseMLP, significantly outperforming existing filtering and learning-based baselines.

Abstract

Accurate work-zone geometry perception is critical for intelligent transportation systems, and ultra-wideband sensing offers a low-cost approach for infrastructure-aided reconstruction. However, outdoor UWB ranging is often degraded by non-line-of-sight propagation, burst noise, and long-tail errors, which can distort downstream spatial reconstruction. We present GAIA, a geometry-aware, infrastructure-anchored learning framework that couples temporal range modeling with latent anchor-layout estimation and deterministic distance projection. GAIA preserves range denoising as the supervised task while orienting the learned distances toward boundary-consistent reconstruction. We evaluate GAIA on a real-world outdoor UWB dataset with synchronized UWB, GNSS, and IMU measurements, and further test robustness using a real-data-calibrated stress-test simulator. GAIA achieves the lowest overall range MSE and highest polygon IoU among evaluated filtering-based and learning-based baselines, reducing MSE by 18.4% and improving polygon IoU by 15.5% over PoseMLP. These results show that geometry-aware range denoising provides an effective path toward spatially coherent work-zone reconstruction.

Problem

• UWB sensing
• work-zone reconstruction
• range denoising
• non-line-of-sight
• geometry perception

Innovation

• geometry-aware denoising
• infrastructure-anchored learning
• UWB sensing
• spatial reconstruction
• anchor-layout estimation