SDOA-Net: An Efficient Deep Learning-Based DOA Estimation Network for Imperfect Array

TL;DR

SDOA-Net is a deep learning-based DOA estimation network designed for imperfect arrays, utilizing sampled signals for improved accuracy, faster convergence, and applicability to multiple targets in realistic scenarios.

Contribution

This paper introduces SDOA-Net, a novel DL-based DOA estimation method that uses sampled signals instead of covariance matrices, enabling better performance on imperfect arrays and multi-target scenarios.

Findings

Outperforms existing DOA methods for imperfect arrays

Converges faster than previous DL-based approaches

Applicable to any number of targets without retraining

Abstract

The estimation of direction of arrival (DOA) is a crucial issue in conventional radar, wireless communication, and integrated sensing and communication (ISAC) systems. However, low-cost systems often suffer from imperfect factors, such as antenna position perturbations, mutual coupling effect, inconsistent gains/phases, and non-linear amplifier effect, which can significantly degrade the performance of DOA estimation. This paper proposes a DOA estimation method named super-resolution DOA network (SDOA-Net) based on deep learning (DL) to characterize the realistic array more accurately. Unlike existing DL-based DOA methods, SDOA-Net uses sampled received signals instead of covariance matrices as input to extract data features. Furthermore, SDOA-Net produces a vector that is independent of the DOA of the targets but can be used to estimate their spatial spectrum. Consequently, the same training network can be applied to any number of targets, reducing the complexity of implementation. The proposed SDOA-Net with a low-dimension network structure also converges faster than existing DL-based methods. The simulation results demonstrate that SDOA-Net outperforms existing DOA estimation methods for imperfect arrays. The SDOA-Net code is available online at https://github.com/chenpengseu/SDOA-Net.git.