Deep Learning for Channel Estimation and Tracking in Vehicular to Infrastructure Communications

In this paper, we propose the deep learning-based channel estimation and tracking algorithm for vehicular millimeter-wave (mmWave) communications. More specifically, a deep neural network (DNN) is leveraged to learn the mapping function between the received training signals and the mmWave channel. Following channel estimation, long short-term memory (LSTM) is leveraged to track the channel. Simulation results demonstrate that the proposed algorithm efficiently estimates and tracks the mmWave channel with negligible training overhead.