Supervised learning based super-resolution DoA estimation utilizing antenna array extrapolation

In this paper, we propose a novel algorithm based on supervised learning for antenna array extrapolation for the purpose of super resolution DoA estimation. We use multiple signal classification (MUSIC) as a DoA estimation technique to estimate the DoA. In order to reduce the computational burden, existing approaches focus on interpolating the missing elements in a virtual array using a sparse array (or non-uniform linear arrays) or employ antenna selection within the same aperture. In contrast, here we utilize an uniform linear array (ULA) using a low number of antennas (within a small array aperture) to extrapolate another ULA with a higher number of antennas (within a bigger aperture). This approach is not restricted to any specific antenna array configuration, in fact it can be generalized to any array configuration. We propose an algorithm which utilizes the advances of supervised learning (dictionary learning) to find a mapping between the receive signal of the small to the bigger ULA using multiple training scenarios. Each scenario is trained using the received signal of both apertures from multiple targets within different angle ranges in a multiple input multiple output (MIMO) radar setup. In the testing phase, however, we can only use the small ULA to approach the performance of the bigger ULA to a certain extent. For example, if the small ULA is a 10 × 10 antenna array and the bigger ULA is a 16 × 16 antenna array, then by means of dictionary learning, we predict the receive signal of the bigger ULA using only the small ULA. Simulations show that using our approach, the training based small ULA can resolve more targets, especially in low SNR environments when compared to the untrained ULA.