ADMM-Net for Communication Interference Removal in Stepped-Frequency Radar

TL;DR

ADMM-Net is a novel neural network architecture inspired by ADMM, designed to effectively remove communication interference and enhance super-resolution radar imaging in spectrum-sharing scenarios.

Contribution

It introduces a complex-valued neural network based on ADMM iterations with learnable parameters for interference removal in radar imaging, tailored for spectrum-sharing environments.

Findings

Lower error compared to traditional ADMM

Reduced computational cost

Effective interference removal in super-resolution radar imaging

Abstract

Complex ADMM-Net, a complex-valued neural network architecture inspired by the alternating direction method of multipliers (ADMM), is designed for interference removal in super-resolution stepped frequency radar angle-range-doppler imaging. Tailored to an uncooperative scenario wherein a MIMO radar shares spectrum with communications, the ADMM-Net recovers the radar image---which is assumed to be sparse---and simultaneously removes the communication interference, which is modeled as sparse in the frequency domain owing to spectrum underutilization. The scenario motivates an $\ell_1$-minimization problem whose ADMM iteration, in turn, undergirds the neural network design, yielding a set of generalized ADMM iterations that have learnable hyperparameters and operations. To train the network we use random data generated according to the radar and communication signal models. In numerical experiments ADMM-Net exhibits markedly lower error and computational cost than ADMM and CVX.