TGPP: Trajectory-Guided Plug-and-Play Priors for Sparse Radio Map Reconstruction

2026-05-07

AI Summary

Wireless signal map reconstruction under sparse trajectory sampling is highly susceptible to spatially heterogeneous uncertainty, particularly suffering from insufficient observations in regions distant from trajectories or occluded by obstacles, which degrades accuracy. To address this challenge, this work proposes Trajectory-Guided Plug-and-Play Prior (TGPP), which for the first time jointly incorporates an interpretable input-space risk prior with implicit guidance features. TGPP can be seamlessly integrated into diverse reconstruction architectures—including deterministic, adversarial, graph neural networks, and the latent-variable generative model RadioFlow-LDM—without modifying their backbone structures. Evaluated on the RadioMapSeer dataset, TGPP consistently enhances performance across five sampling rates, achieving up to a 43.1% reduction in normalized mean squared error (NMSE) compared to baseline methods.

Abstract

Radio map (RM) reconstruction is essential for environment-aware wireless networks, but practical measurements are often collected along mobility trajectories rather than randomly scattered over the target region. Such trajectory-sampled observations induce spatially heterogeneous uncertainty: near-trajectory regions are directly constrained, whereas distant or occluded regions remain weakly observed, leading to degraded reconstruction accuracy in under-constrained areas. To address this problem, we propose Trajectory-Guided Plug-and-Play Priors (TGPP), a general guidance module for sparse RM reconstruction. TGPP learns an explicit guidance map as an interpretable input-space risk prior, and an implicit guide feature that is projected and fused with backbone hidden representations. TGPP can be attached to different reconstruction backbones without changing their original task formulation. We further introduce RadioFlow-LDM, a latent flow-based generative backbone, and apply TGPP to deterministic, adversarial, graph-based, and latent generative reconstruction models. Experiments on RadioMapSeer with five trajectory sampling rates show that trajectory-sampled reconstruction differs substantially from random sparse interpolation. TGPP improves most reconstruction metrics across backbones, achieving up to 43.1% NMSE reduction relative to the corresponding base backbone without trajectory-guided priors.

Problem

• radio map reconstruction
• trajectory-sampled data
• spatial uncertainty
• sparse interpolation
• under-constrained regions

Innovation

• Trajectory-Guided Priors
• Plug-and-Play
• Radio Map Reconstruction
• Spatial Uncertainty Modeling
• Latent Flow Generative Model