Integrated Sensing and Communication for 6G: Ten Key Machine Learning Roles

Abstract

Integrating sensing and communication is a defining theme for future wireless systems. This is motivated by the promising performance gains, especially as they assist each other, and by the better utilization of the wireless and hardware resources. Realizing these gains in practice, however, is subject to several challenges where leveraging machine learning can provide a potential solution. This article focuses on ten key machine learning roles for joint sensing and communication, sensingaided communication, and communication-aided sensing systems, explains why and how machine learning can be utilized, and highlights important directions for future research. The article also presents real-world results for some of these machine learning roles based on the large-scale real-world dataset DeepSense 6G, which could be adopted in investigating a wide range of integrated sensing and communication problems.

MIMO Coded Generalized Reduced Dimension Fourier Algorithm for 3-D Microwave Imaging

“…The development of the current model to integrate sensing and communication functions [62,63] will be considered as future work.…”

Terahertz Communications and Sensing for 6G and Beyond: A Comprehensive Review

“…Hence, it attracted a lot of interest recently as a key enabler for implementing integrated sensing and communications (ISAC) for 6G and beyond [61]. On top of implementing THz communications and THz sensing in a unified system, these dual-functional wireless networks offer a great synergy through sensing-aided communication [62], [63] and communication-aided sensing [64], as we will elaborate in Sec. IX.…”

Maritime Communications: A Survey on Enabling Technologies, Opportunities, and Challenges

“…The benefits of these algorithms may cover simulation scenarios beyond what can be obtained with theoretical modeling and experimental measurements, particularly if we want to utilize signals in the optical band and potentially in the THz band. Leveraging data-driven learning can further enable joint sensing and communication as advocated in terrestrial networks [172]. Reinforcement learning (RL), an ML paradigm widely applied for decision-making problems, can also improve the performance of UAV-based maritime communications.…”