Time Difference of Arrival Estimation of Stationary Targets Utilizing Deep Neural Network

Abstract

Time difference of arrival (TDOA) is widely used in the field of passive location because of its flexible base station deployment and simple principle. However, when solving the solution of stationary targets position, the traditional method, such as the two-stage weighted least squares (TSWLS) algorithm, is easily affected by noise, and cannot achieve good localization results in practical situations. To solve this problem, we propose a deep neural network (DNN) for TDOA estimation of stationary targets. First, a large number of simulation samples are generated according to the TDOA model. Each sample contains the time difference from each secondary base station to the main base station, the error of time difference, and the real three-dimensional (3-D) coordinates of the targets. Next, a suitable DNN architecture is designed to solve the solution of the stationary target position. The simulation results prove that the method proposed herein outperforms TSWLS for multiple base stations based on the TDOA model.