Convolutional Neural Networks Based Joint AOA/TOF Estimation

This paper proposes one-dimensional convolutional neural networks (1D CNN) based approach for joint angle of arrival (AOA) and time of flight (TOF) estimation. In the network, received signal vectors which contain phase information are organized as an image and output data are scaled for unbiased learning. Simulation results show robustness against insufficient time slots and has low latency once the training is completed.