2021/11/29 by Umut Demirhan, Demirhan, Umut, Ahmed Alkhateeb +1 · 2 citations
Engineering · Physics and Astronomy · #Advanced Optical Sensing Technologies #FOS: Computer and information sciences #FOS: Electrical engineering #Indoor and Outdoor Localization Technologies #Information Theory (cs.IT) #Millimeter-Wave Propagation and Modeling #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2111.14805
openalex publication_date 2021/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Millimeter wave (mmWave) and sub-terahertz communication systems rely mainly\non line-of-sight (LOS) links between the transmitters and receivers. The\nsensitivity of these high-frequency LOS links to blockages, however, challenges\nthe reliability and latency requirements of these communication networks. In\nthis paper, we propose to utilize radar sensors to provide sensing information\nabout the surrounding environment and moving objects, and leverage this\ninformation to proactively predict future link blockages before they happen.\nThis is motivated by the low cost of the radar sensors, their ability to\nefficiently capture important features such as the range, angle, velocity of\nthe moving scatterers (candidate blockages), and their capability to capture\nradar frames at relatively high speed. We formulate the radar-aided proactive\nblockage prediction problem and develop two solutions for this problem based on\nclassical radar object tracking and deep neural networks. The two solutions are\ndesigned to leverage domain knowledge and the understanding of the blockage\nprediction problem. To accurately evaluate the proposed solutions, we build a\nlarge-scale real-world dataset, based on the DeepSense framework, gathering\nco-existing radar and mmWave communication measurements of more than 10\nthousand data points and various blockage objects (vehicles, bikes, humans,\netc.). The evaluation results, based on this dataset, show that the proposed\napproaches can predict future blockages 1 second before they happen with more\nthan 90 % F1 score (and more than 90 % accuracy). These results, among\nothers, highlight a promising solution for blockage prediction and reliability\nenhancement in future wireless mmWave and terahertz communication systems.\n