Taxi Route Recommendation Based on Urban Traffic Coulomb's Law

With the advances and availability of networking and data processing technologies, the number of researches supporting taxi as a mean of transportation and further optimization of their route selection is increasing and broadly discussed. For the taxis, when they are cruising on the street the drivers looking for passengers, most drivers rely on their experience and intuition for the guideline to optimize their cruise routes and increase profit. This approach, however, is not efficient and usually increases the traffic load in urban cities. A solution is highly required to match and recommend appropriate cruising routes to taxis so that aimless cruising would be avoided and the drivers income would be increased. In this paper, we propose a route recommendation algorithm based on the Urban Traffic Coulomb's Law to model the relationship between the taxis and passengers in urban traffic scenarios. Different from existing route recommendation methods, the relationship among taxis and passengers are fully taken into account in the proposed algorithm, e.g. the attractiveness between taxis and passengers and the repulsion among taxis. It collects useful information from historical trajectories, and calculates the traffic attraction for cruising taxis, based on which optimal road segments are recommended to drivers to pick up desired passengers. Extensive experiments are conducted on the road network based on massive real-world trajectories to verify the effectiveness, and evaluations demonstrate that the proposed method outperforms among existing methods and can increase the drivers' income by more than 8%.