A Lightweight Coordinate-Conditioned Diffusion Approach for 6G C-V2X Radio Environment Maps

2025-12-27

AI Summary

In 6G cellular vehicle-to-everything (C-V2X) systems, transmitting vehicles suffer from physical-layer interference due to the absence of dynamic, high-fidelity radio environment maps (REMs). To address this, we propose a Coordinate-Conditioned Denoising Diffusion Probabilistic Model (CCDDPM) enabling rapid, location-aware REM generation for arbitrary vehicular positions. Our method innovatively integrates coordinate-encoded Gaussian priors with noise conditioning and employs a lightweight dual-channel conditional U-Net architecture, achieving cross-location REM modeling from minimal historical vehicle data. CCDDPM significantly improves generation stability and spatial structural consistency, yielding REMs whose statistical characteristics closely match real channel measurements. Compared to mainstream generative models such as GANs, CCDDPM demonstrates superior robustness and convergence in few-shot scenarios. This work provides critical REM support for ultra-low-latency, high-reliability 6G vehicular communications.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Transmitter vehicles that broadcast 6G Cellular Vehicle-to-Everything (C-V2X)-based messages, e.g., Basic Safety Messages (BSMs), are prone to be impacted by PHY issues due to the lack of dynamic high-fidelity Radio Environment Map (REM) with dynamic location variation. This paper explores a lightweight diffusion-based generative approach, the Coordinate-Conditioned Denoising Diffusion Probabilistic Model (CCDDPM), that leverages the signal intensity-based 6G V2X Radio Environment Map (REM) from limited historical transmitter vehicles in a specific region, to predict the REMs for a transmitter vehicle with arbitrary coordinates across the same region. The transmitter vehicle coordinate is encoded as a smooth Gaussian prior and fused with the Gaussian noise through a lightweight two-channel conditional U-Net architecture. We demonstrate that the predicted REM closely matches the statistics and structure of ground-truth REM while exhibiting the improved stability and over other widely applied generative AI approaches. The resulting predictor enables rapid and scenario-consistent REM with arbitrary transmitter coordinates, which thereby supports more efficient 6G C-V2X communications where transmitter vehicles are less likely to suffer from the PHY issues.

Problem

• Predicts Radio Environment Maps for arbitrary transmitter coordinates
• Addresses lack of dynamic high-fidelity REMs in 6G C-V2X systems
• Enhances communication efficiency by reducing PHY issues for vehicles

Innovation

• Coordinate-Conditioned Diffusion Model for REM prediction
• Lightweight two-channel U-Net with Gaussian coordinate encoding
• Generates high-fidelity maps from limited historical transmitter data