Real-time Prediction of Arterial Vehicle Trajectories: An Application to Predictive Route Guidance for an Emergency Vehicle

Urban arterial networks are increasingly equipped with advanced roadside sensors that can track spatiotemporal trajectories of individual vehicles such as Bluetooth sensors. A large amount of vehicle trajectory data generated from such sensors provide new insights into drivers’ intersection-to-intersection movement patterns, which can be used to develop models and strategies to predict and enhance arterial traffic. This study proposes an arterial trajectory prediction model that predicts the next intersections that a vehicle will visit based on its previously visited intersections. The proposed model is based on Artificial Neural Networks and trained and tested on one-year Bluetooth data from Brisbane, Australia. The prediction results show that the model is capable of predicting a vehicle’s next intersection with the average accuracy higher than 75%. The study performs a simulation-based case study to demonstrate the model’s application to a predictive route guidance systems for an emergency vehicle. The simulation results show that the integration of the vehicle trajectory prediction capability allows the route guidance system to find a route that is faster and has less traffic disruptions than the route based on a shortest path algorithm.