SAINT: Self-Adaptive Interactive Navigation Tool for Cloud-Based Vehicular Traffic Optimization

This paper proposes a self-adaptive interactive navigation tool (SAINT), which is tailored for cloud-based vehicular traffic optimization in road networks. The legacy navigation systems make vehicles navigate toward their destination less effectively with individually optimal navigation paths rather than network-wide optimal navigation paths, particularly during rush hours. To the best of our knowledge, SAINT is the first attempt to investigate a self-adaptive interactive navigation approach through the interaction between vehicles and vehicular cloud. The vehicles report their navigation experiences and travel paths to the vehicular cloud so that the vehicular cloud can know real-time road traffic conditions and vehicle trajectories for better navigation guidance for other vehicles. With these traffic conditions and vehicle trajectories, the vehicular cloud uses a mathematical model to calculate road segment congestion estimation for global traffic optimization. This model provides each vehicle with a navigation path that has minimum traffic congestion in the target road network. Using the simulation with a realistic road network, it is shown that our SAINT outperforms the legacy navigation scheme, which is based on Dijkstra's algorithm with a real-time road traffic snapshot. On a road map of Manhattan in New York City, our SAINT can significantly reduce the travel delay during rush hours by 19%.