Bridging Simulation and Reality: A 3D Clustering-Based Deep Learning Model for UAV-Based RF Source Localization

TL;DR

This paper introduces a novel 3D clustering-based deep learning model for UAV RF source localization, bridging the simulation-reality gap with an improved propagation model and demonstrating high accuracy and efficiency in real-world tests.

Contribution

It presents the Enhanced Two-Ray propagation model and the 3D Cluster-Based RealAdaptRNet, improving simulation accuracy and robustness of RF source localization in real environments.

Findings

Enhanced Two-Ray model outperforms traditional models in simulation accuracy.

RealAdaptRNet achieves an average localization error of 18.2 meters in real-world tests.

Model uses 33.5 times fewer parameters, enabling efficient computation.

Abstract

Localization of radio frequency (RF) sources has critical applications, including search and rescue, jammer detection, and monitoring of hostile activities. Unmanned aerial vehicles (UAVs) offer significant advantages for RF source localization (RFSL) over terrestrial methods, leveraging autonomous 3D navigation and improved signal capture at higher altitudes. Recent advancements in deep learning (DL) have further enhanced localization accuracy, particularly for outdoor scenarios. DL models often face challenges in real-world performance, as they are typically trained on simulated datasets that fail to replicate real-world conditions fully. To address this, we first propose the Enhanced Two-Ray propagation model, reducing the simulation-to-reality gap by improving the accuracy of propagation environment modeling. For RFSL, we propose the 3D Cluster-Based RealAdaptRNet, a DL-based method leveraging 3D clustering-based feature extraction for robust localization. Experimental results demonstrate that the proposed Enhanced Two-Ray model provides superior accuracy in simulating real-world propagation scenarios compared to conventional free-space and two-ray models. Notably, the 3D Cluster-Based RealAdaptRNet, trained entirely on simulated datasets, achieves exceptional performance when validated in real-world environments using the AERPAW physical testbed, with an average localization error of 18.2 m. The proposed approach is computationally efficient, utilizing 33.5 times fewer parameters, and demonstrates strong generalization capabilities across diverse trajectories, making it highly suitable for real-world applications.