Vehicle Positioning With Deep-Learning-Based Direction-of-Arrival Estimation of Incoherently Distributed Sources

In this article, a novel vehicle positioning system architecture based on direction-of-arrival (DOA) estimation of incoherently distributed (ID) sources is proposed employing massive multiple-input-multiple-output (MIMO) arrays. Such an architecture with the associated signal model is more consistent with the actual array application and multipath transmission scenarios. First, an end-to-end two-dimensional (2-D) DOA estimation of ID sources utilizing a dual one-dimensional (1-D) convolutional neural network (D1D-CNN) under the deep learning (DL) framework is performed, where the normalized covariance matrix data is used for both offline training and online estimation. Then, the received SNR information is exploited to select a set of DOA estimates provided by multiple collaborative BSs for positioning. Moreover, transfer learning and an attention mechanism are employed to promote its generalization ability and achieve robustness against array perturbations. Simulation results are provided to show that the proposed method outperforms the state-of-the-art methods in terms of computational complexity, positioning accuracy, and robustness against array perturbations.

Automated summary

In this article, a novel vehicle positioning system architecture based on DOA estimation of ID sources utilizing massive MIMO arrays is proposed. The system employs a D1D-CNN for 2-D DOA estimation and utilizes received SNR information for selecting DOA estimates for positioning. Transfer learning and an attention mechanism are also employed for improving the generalization ability and robustness against array perturbations of the system.