Angle-of-Arrival Estimation for Vehicle-to-vehicle Communications based on Machine Learning

Abstract

For vehicular communications, angle-of-arrival (AOA) estimation plays an important role in smart antenna, beamforming, and assisted driving. Although there are a series of high-performance spectral- or parametric-based AOA estimation methods, they are difficult to realize real-time AOA estimation. In order to solve this problem, this paper proposes a machine-learning-based AOA estimation approach. The proposed method includes off-line training and on-line estimation processes. In the off-line training process, an estimation model is obtained by using the support vector machine (SVM) based on a large number of actual measurement data of vehicular communication scenarios. Then, in the on-line estimation process, the obtained model is used to realize AOA estimation in real-time according to the array snapshot data collected by the antenna array. Experimental results show that the proposed method can achieve real-time and accurate AOA estimation under reasonable configuration. This achievement has the potential for further application in vehicular communication systems.