Zero-Shot Generalization for Blockage Localization in mmWave Communication

2024/12/18 by Rafaela Scaciota, Scaciota, Rafaela, Malith Gallage +5
Engineering · #Millimeter-Wave Propagation and Modeling #Antenna Design and Optimization #Microwave Engineering and Waveguides

paper · pdf · doi:10.48550/arxiv.2412.17843

Abstract

This paper introduces a novel method for predicting blockages in millimeter-wave (mmWave) communication systems towards enabling reliable connectivity. It employs a self-supervised learning approach to label radio frequency (RF) data with the locations of blockage-causing objects extracted from light detection and ranging (LiDAR) data, which is then used to train a deep learning model that predicts object`s location only using RF data. Then, the predicted location is utilized to predict blockages, enabling adaptability without retraining when transmitter-receiver positions change. Evaluations demonstrate up to 74% accuracy in predicting blockage locations in dynamic environments, showcasing the robustness of the proposed solution.

Related

• Deep Learning for Moving Blockage Prediction using Real Millimeter Wave Measurements
• Machine Learning for Reliable mmWave Systems: Blockage Prediction and\n Proactive Handoff
• LiDAR-Aided Mobile Blockage Prediction in Real-World Millimeter Wave Systems
• Blockage Prediction Using Wireless Signatures: Deep Learning Enables Real-World Demonstration
• Radar Aided Proactive Blockage Prediction in Real-World Millimeter Wave\n Systems