The First Indoor Pathloss Radio Map Prediction Challenge

2025-01-23

AI Summary

This work addresses the challenge of path loss prediction for indoor directional wireless signal propagation. Methodologically, it introduces the first deep learning–driven radio map prediction benchmark—comprising a standardized dataset, a well-defined task formulation, and a fair evaluation framework—to fill a critical gap in this specialized domain. The proposed approach integrates ray-tracing priors with deep learning, featuring a multi-scale feature extraction architecture and an end-to-end regression model trained jointly on both real-world measurements and synthetic channel data. As a key contribution, the benchmark was deployed as the ICASSP 2025 International Challenge, attracting over ten international teams. The top-performing solution achieved a mean absolute path loss prediction error of under 1.8 dB, substantially improving accuracy and reproducibility in indoor channel modeling.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

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.

Problem

• Wireless Signal
• Indoor Environment
• Attenuation Prediction

Innovation

• Indoor Environment
• Signal Attenuation Prediction
• Competition-driven Research