Sparse Bayesian Learning Unfolding Network for Efficient DoA Estimation in Low SNR

Compressive sensing (CS) algorithms have demonstrated superior direction-of-arrival (DoA) estimation accuracy in the low signal-to-noise ratio (SNR) regime by exploiting inherent angular sparsity. However, traditional CS-based algorithms require numerous iterations to gradually converge well, resulting in high computational complexity and limiting their applicability in practical systems. In this paper, we propose a sparse Bayesian learning (SBL) unfolding network for superior and efficient DoA estimation. Specifically, the SBL framework is unfolded into a series of cascaded SBL layers, each corresponding to a hyperparameter update. Within each SBL layer, we introduce a Convolution-Transformer based source power estimation network (CTsNet) to better capture angular sparsity and generate more efficient update rule for the signal hyperparameter. Simultaneously, a convolution-based noise variance estimation network (CnNet) is proposed for accurate noise variance estimation, which controls the sharpness of the peak spectrum and affects the iterations of the signal hyperparameter. Simulation results demonstrate that the proposed method not only performs better than existing methods in terms of estimation accuracy and angular resolution, but also exhibits lower computational complexity compared with other SBL-based algorithms.