Vehicular Visible Light Positioning Using Receiver Diversity with Machine Learning

This paper proposes a 2-D vehicular visible light positioning (VLP) system using existing streetlights and diversity receivers. Due to the linear arrangement of streetlights, traditional techniques based on triangulation or similar algorithms fail. Thus, in this work, we propose spatial angular receiver with machine learning (ML) for VLP. It is shown that multi-layer neural network (NN) proposed scheme outperforms other ML can offer high accuracy root mean square (RMS) error 0.22 m 0.14 during day night time, respectively. Furthermore, NN shows robustness VLP across different weather conditions road scenarios. The results show only dense fog deteriorates performance due reduced visibility road.