DiffLoc: Diffusion Model-Based High-Precision Positioning for 6G Networks

2025-10-15

AI Summary

To address the poor scalability, heavy reliance on dense site surveys, and insufficient accuracy of conventional fingerprint-based localization in large-scale dynamic outdoor environments, this paper proposes DiffLoc—the first framework to integrate conditional generative diffusion models into wireless localization. DiffLoc learns the mapping from radio fingerprints to geographic coordinates end-to-end directly from massive MIMO uplink Sounding Reference Signal (SRS) channel state information. Leveraging consistency training, it reduces the sampling steps from 200 to just 2, significantly improving inference efficiency and robustness to mobility. Evaluated in a ray-tracing-based macrocell simulation environment in Tokyo, DiffLoc achieves a fusion localization accuracy of 0.5 cm and single-base-station accuracy of 1–2 cm—representing an order-of-magnitude improvement over traditional methods. These results demonstrate DiffLoc’s feasibility and superiority for high-precision, real-time localization in 6G networks.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Diffusion Models for Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

This paper introduces a novel framework for high-accuracy outdoor user equipment (UE) positioning that applies a conditional generative diffusion model directly to high-dimensional massive MIMO channel state information (CSI). Traditional fingerprinting methods struggle to scale to large, dynamic outdoor environments and require dense, impractical data surveys. To overcome these limitations, our approach learns a direct mapping from raw uplink Sounding Reference Signal (SRS) fingerprints to continuous geographic coordinates. We demonstrate that our DiffLoc framework achieves unprecedented sub-centimeter precision, with our best model (DiffLoc-CT) delivering 0.5 cm fusion accuracy and 1-2 cm single base station (BS) accuracy in a realistic, ray-traced Tokyo urban macro-cell environment. This represents an order-of-magnitude improvement over existing methods, including supervised regression approaches (over 10 m error) and grid-based fusion (3 m error). Our consistency training approach reduces inference time from 200 steps to just 2 steps while maintaining exceptional accuracy even for high-speed users (15-25 m/s) and unseen user trajectories, demonstrating the practical feasibility of our framework for real-time 6G applications.

Problem

• Achieving sub-centimeter outdoor positioning accuracy for 6G networks
• Overcoming traditional fingerprinting limitations in dynamic outdoor environments
• Enabling real-time positioning for high-speed users with minimal inference steps

Innovation

• Uses diffusion model on CSI for positioning
• Learns mapping from SRS fingerprints to coordinates
• Achieves sub-centimeter accuracy with fast inference