Robust Hybrid Beamforming with Liquid Crystal Antennas and Liquid Neural Networks

2026-04-08

AI Summary

This work addresses the challenges of strong atmospheric absorption, large Doppler spread, and the impracticality of conventional phase shifters in sub-terahertz (sub-THz) multi-user MIMO systems by proposing a hybrid beamforming framework that integrates liquid crystal-based reconfigurable antennas with liquid neural networks. The approach enables lossless analog beamforming through voltage-controlled tuning of the liquid crystal’s permittivity and models the time-varying channel dynamics using liquid neural networks governed by ordinary differential equations. Manifold optimization is further employed to compress the beam search space. Evaluated at 108 GHz in NYURay urban scenarios, the proposed method achieves an 88.6% improvement in spectral efficiency over machine learning baselines and a 1.9× gain compared to the 3GPP TR 38.901 model, while demonstrating enhanced robustness to channel estimation errors.

Abstract

Sub-terahertz (sub-THz) multi-user multiple-input multiple-output (MU-MIMO) systems unlock immense bandwidth for 6G wireless communications. However, practical deployment of wireless systems in sub-THz bands faces critical challenges such as increased atmospheric absorption, reduced channel coherence time due to increased Doppler spread at higher carrier frequencies, and hardware bottlenecks as low-loss sub-THz phase shifters are difficult to realize. To overcome the hardware and channel estimation challenges of sub-THz systems, this paper proposes a hybrid beamforming (BF) framework that integrates reconfigurable liquid crystal (LC) antennas with a liquid neural network (LNN) for transmitter. Specifically, we employ an LC antenna as the analog BF stage of a hybrid BF architecture, exploiting its voltage-driven permittivity tunability to achieve high-gain beam steering without the need for lossy phase shifters. For digital BF, we utilize an ordinary differential equations-defined LNN to learn temporal channel dynamics, and use a manifold optimization technique to compress the search space. We validated the proposed method on simulated site-specific 108 GHz ray-tracing channels in an urban scenario using NYURay, a ray-tracing simulator validated against 142 GHz propagation measurements. The 108 GHz carrier frequency matches the operating band of the LC antenna hardware. The proposed method achieves an 88.6\% spectral efficiency (SE) gain and higher robustness to imperfect channel estimation compared to the learning-aided gradient descent and gated recurrent unit machine learning baselines, and 1.9 times higher SE than the 3GPP TR~38.901 standard antenna model, highlighting the potential of LC-based hardware for sub-THz communications.

Problem

• sub-THz
• MU-MIMO
• channel estimation
• hardware bottleneck
• Doppler spread

Innovation

• liquid crystal antennas
• liquid neural networks
• hybrid beamforming
• sub-THz communications
• manifold optimization