# Terahertz-Band Joint Ultra-Massive MIMO Radar-Communications: Model-Based and Model-Free Hybrid Beamforming arXiv: https://arxiv.org/abs/2103.00328 ยท HTML: https://mlsanity.com/paper/2103.00328/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 22 of its 75 references that are in the map. - First posted on arXiv 27 Feb 2021. ## Builds on (most cited first, 22 of 22) - [Manopt, a Matlab toolbox for optimization on manifolds](https://mlsanity.com/paper/1308.5200/) (2013) - [Federated Learning for Channel Estimation in Conventional and RIS-Assisted Massive MIMO](https://mlsanity.com/paper/2008.10846/) (2020) - [Joint Radar and Communication Design: Applications, State-of-the-art, and the Road Ahead](https://mlsanity.com/paper/1906.00789/) (2019) - [DeepMUSIC: Multiple Signal Classification via Deep Learning](https://mlsanity.com/paper/1912.04357/) (2019) - [White Paper on Broadband Connectivity in 6G](https://mlsanity.com/paper/2004.14247/) (2020) - [An Overview of Signal Processing Techniques for Terahertz Communications](https://mlsanity.com/paper/2005.13176/) (2020) - [Joint Antenna Selection and Hybrid Beamformer Design using Unquantized and Quantized Deep Learning Networks](https://mlsanity.com/paper/1905.03107/) (2019) - [Channel Estimation and Hybrid Combining for Wideband Terahertz Massive MIMO Systems](https://mlsanity.com/paper/2102.06772/) (2021) - [Toward Millimeter Wave Joint Radar-Communications: A Signal Processing Perspective](https://mlsanity.com/paper/1905.00690/) (2019) - [A Family of Deep Learning Architectures for Channel Estimation and Hybrid Beamforming in Multi-Carrier mm-Wave Massive MIMO](https://mlsanity.com/paper/1912.10036/) (2019) - [Doppler-Resilient 802.11ad-Based Ultra-Short Range Automotive Joint Radar-Communications System](https://mlsanity.com/paper/1902.01306/) (2019) - [Hybrid Beamforming for Terahertz Wireless Communications: Challenges, Architectures, and Open Problems](https://mlsanity.com/paper/2101.08469/) (2021) - [Ultra-Massive MIMO Systems at Terahertz Bands: Prospects and Challenges](https://mlsanity.com/paper/1902.11090/) (2019) - [Sparse Array Selection Across Arbitrary Sensor Geometries with Deep Transfer Learning](https://mlsanity.com/paper/2004.11637/) (2020) - [Deep Learning Based Channel Covariance Matrix Estimation with User Location and Scene Images](https://mlsanity.com/paper/2101.07471/) (2021) - [A Deep Learning Framework for Hybrid Beamforming Without Instantaneous CSI Feedback](https://mlsanity.com/paper/2006.10971/) (2020) - [Co-Designing Statistical MIMO Radar and In-band Full-Duplex Multi-User MIMO Communications -- Part I: Signal Processing](https://mlsanity.com/paper/2006.14774/) (2020) - [A Block Sparsity Based Estimator for mmWave Massive MIMO Channels with Beam Squint](https://mlsanity.com/paper/1904.12272/) (2019) - [Terahertz-Band Ultra-Massive Spatial Modulation MIMO](https://mlsanity.com/paper/1905.04732/) (2019) - [Hybrid Beamforming With Sub-arrayed MIMO Radar: Enabling Joint Sensing and Communication at mmWave Band](https://mlsanity.com/paper/1810.09812/) (2018) - [Displaced Sensor Automotive Radar Imaging](https://mlsanity.com/paper/2010.04085/) (2020) - [Reconfigurable Intelligent Surface Based Hybrid Precoding for THz Communications](https://mlsanity.com/paper/2012.06261/) (2020) ## Built on by (most cited first, 5 of 5) - [Beurling-Selberg Extremization for Dual-Blind Deconvolution Recovery in Joint Radar-Communications](https://mlsanity.com/paper/2211.09253/) (2022) - [Unsupervised Learning-Based Joint Resource Allocation and Beamforming Design for RIS-Assisted MISO-OFDMA Systems](https://mlsanity.com/paper/2506.22448/) (2025) - [Federated Multi-Task Learning for THz Wideband Channel and DoA Estimation](https://mlsanity.com/paper/2207.06017/) (2022) - [Multi-Antenna Dual-Blind Deconvolution for Joint Radar-Communications via SoMAN Minimization](https://mlsanity.com/paper/2303.13609/) (2023) - [Sparse Array Design for Direction Finding using Deep Learning](https://mlsanity.com/paper/2308.04615/) (2023) ## Abstract (arXiv) Wireless communications and sensing at terahertz (THz) band are increasingly investigated as promising short-range technologies because of the availability of high operational bandwidth at THz. In order to address the extremely high attenuation at THz, ultra-massive multiple-input multiple-output (MIMO) antenna systems have been proposed for THz communications to compensate propagation losses. However, the cost and power associated with fully digital beamformers of these huge antenna arrays are prohibitive. In this paper, we develop wideband hybrid beamformers based on both model-based and model-free techniques for a new group-of-subarrays (GoSA) ultra-massive MIMO structure in low-THz band. Further, driven by the recent developments to save the spectrum, we propose beamformers for a joint ultra-massive MIMO radar-communications system, wherein the base station serves multi-antenna user equipment (RX), and tracks radar targets by generating multiple beams toward both RX and the targets. We formulate the GoSA beamformer design as an optimization problem to provide a trade-off between the unconstrained communications beamformers and the desired radar beamformers. To mitigate the beam split effect at THz band arising from frequency-independent analog beamformers, we propose a phase correction technique to align the beams of multiple subcarriers toward a single physical direction. To further decrease the ultra-massive MIMO computational complexity and enhance robustness, we also implement deep learning solutions to the proposed model-based hybrid beamformers. Numerical experiments demonstrate that both techniques outperform the conventional approaches in terms of spectral efficiency and radar beampatterns, as well as exhibiting less hardware cost and computation time.