The First Indoor Pathloss Radio Map Prediction Challenge

TL;DR

This paper introduces the ICASSP 2025 Indoor Pathloss Radio Map Prediction Challenge, aiming to advance deep learning models for indoor radio signal propagation and provide a benchmark for future research.

Contribution

It presents the first challenge focused on indoor directional radio pathloss prediction, including datasets, tasks, evaluation methods, and analysis of submitted solutions.

Findings

Multiple methods evaluated with varying accuracy

Deep learning approaches show promising results

Benchmark established for future research

Abstract

To encourage further research and to facilitate fair comparisons in the development of deep learning-based radio propagation models, in the less explored case of directional radio signal emissions in indoor propagation environments, we have launched the ICASSP 2025 First Indoor Pathloss Radio Map Prediction Challenge. This overview paper describes the indoor path loss prediction problem, the datasets used, the Challenge tasks, and the evaluation methodology. Finally, the results of the Challenge and a summary of the submitted methods are presented.