WiCo-PG: Wireless Channel Foundation Model for Pathloss Map Generation via Synesthesia of Machines

TL;DR

This paper introduces WiCo-PG, a novel wireless channel foundation model using multi-modal data and advanced neural network architectures to generate accurate pathloss maps for 6G UAV-to-ground scenarios, outperforming existing methods.

Contribution

The paper presents the first wireless channel foundation model for pathloss map generation utilizing Synesthesia of Machines, with a new dataset, a dual VQGAN-Transformer architecture, and a frequency-guided MoE, advancing cross-modal wireless modeling.

Findings

Achieves NMSE of 0.012 in pathloss map generation.

Outperforms LLM4PG and conventional schemes by over 6.98 dB.

Demonstrates strong few-shot generalization with 2.7% samples.

Abstract

A wireless channel foundation model for pathloss map generation (WiCo-PG) via Synesthesia of Machines (SoM) is developed for the first time. Considering sixth-generation (6G) uncrewed aerial vehicle (UAV)-to-ground (U2G) scenarios, a new multi-modal sensing-communication dataset is constructed for WiCo-PG pre-training, including multiple U2G scenarios, diverse flight altitudes, and diverse frequency bands. Based on the constructed dataset, the proposed WiCo-PG enables cross-modal pathloss map generation by leveraging RGB images from different scenarios and flight altitudes. In WiCo-PG, a novel network architecture designed for cross-modal pathloss map generation based on dual vector quantized generative adversarial networks (VQGANs) and Transformer is proposed. Furthermore, a novel frequency-guided shared-routed mixture of experts (S-R MoE) architecture is designed for cross-modal pathloss map generation. Simulation results demonstrate that the proposed WiCo-PG achieves improved pathloss map generation accuracy through pre-training with a normalized mean squared error (NMSE) of 0.012, outperforming the large language model (LLM)-based scheme, i.e., LLM4PG, and the conventional deep learning-based scheme by more than 6.98 dB. The enhanced generality of the proposed WiCo-PG can further outperform the LLM4PG by at least 1.37 dB using 2.7% samples in few-shot generalization.