Predicting Vehicles' Positions Using Roadside Units: A Machine-Learning Approach

Abstract

In this paper, we study positioning systems using Vehicular Ad Hoc Networks (VANETs) to predict the position of vehicles. We use the reception power of the packets received by the Road Side Units (RSUs) and sent by the vehicles on the roads. In fact, the reception power is strongly influenced by the distance between a vehicle and a RSU. To predict the position of vehicles in this context, we adopt the machine-learning methodology. As a pre-requisite, the vehicles know their positions and the vehicles send their positions in the packets. The positioning system can thus perform a training sequence and build a model. The system is then able to handle a prediction request. In this request, a vehicle without external positioning will request its position from the neighboring RSUs. The RSUs which receive this request message from the vehicle will know the power at which the message was received and will study the positioning request using the training set. In this study, we use and compare three widely recognized techniques: K Nearest Neighbors (KNN), Support Vector Machine (SVM) and Random Forest. We study these techniques in various configurations and discuss their respective advantages and drawbacks. Our results show that these three techniques provide very good results in terms of position predictions when the error on the transmission power is small.