Towards Improved Vehicle Arrival Time Prediction in Public Transportation: Integrating SUMO and Kalman Filter Models

Abstract

Accurate bus arrival time prediction is a key component for improving the attractiveness of public transport. In this research, a model of bus arrival time prediction, which aims to improve arrival time accuracy, is proposed. The arrival time will be predicted using a Kalman Filter (KF) model, by utilising information acquired from social networks. Social Networks feed road traffic information into the model, based on information provided by people who have witnessed events and then updated their social media accordingly. In order to accurately assess the efficiency of KF model, we simulate realistic road scenarios using the traffic simulator Simulation in Urban Mobility (SUMO). SUMO is capable of simulating real world road traffic using digital maps and realistic traffic models. This paper discusses modelling a road journey using Kalman Filters and verifying the results with a corresponding SUMO simulation. As a second step, SUMO based measures are used to inform the KF model. Integrating the SUMO measures with the KF model can be seen as an initial step to verifying our premise that realtime data from social networks can eventually be used to improve the accuracy of the KF prediction. Furthermore, it demonstrates an integrated experimental environment.