MD-DOA: A Model-Based Deep Learning DOA Estimation Architecture

Direction-of-arrival (DOA) estimation is widely used in the field of array signal processing. The model-based (MB) algorithms rely on domain knowledge and assumptions, facing limitations in estimating coherent sources and running on a few snapshots and so on. In contrast, deep learning approaches can learn from data, offering a promising alternative for DOA estimation. In this article, a novel end-to-end MB deep learning DOA estimation architecture (MD-DOA) is proposed to estimate the DOAs of multiple narrowband signals captured by a uniform linear array (ULA). Specifically, the multibranch convolutional recurrent neural network with a residual link (MBCR2net) is developed to extract multiscale features and learn correlation in received temporal signals. Subsequently, the weighted noise subspace network (WNSnet) is proposed to learn a more representative noise subspace from the one obtained by eigenvalue decomposition (EVD), developing the more precise subspace division. The matrix reshape process (MRP) then generates the pseudo covariance matrix (PCM) and captures the correlation in the weighted noise subspace. Notably, EVD and MRP are the MB modules to preserve the interpretability. Finally, the PCM-based DOA-finding network (PDFnet) estimates the desired DOAs. MD-DOA integrates the MB and data-driven (DD) advantages. It inherits the overall framework of the subspace-based methods while using the network to augment the covariance matrix estimation, subspace division, and peak-finding process. Our proposed architecture can operate successfully in the presence of array mismatch, low signal-to-noise ratios (SNRs), and a few snapshots. It is also applicable to real-world measurements and demonstrates superior performance compared with other existing algorithms in this field.