Research on Self Driving Customized Bus Lines Based on Users’ Real-Time Needs

In order to solve the problem that the existing customized bus can only select transfer points on the static line, and cannot dynamically plan the route according to the user's real-time demand, this paper establishes a route planning model of unmanned customized bus with the total cost minimization as the optimization goal. The model comprehensively considers the operating cost, passenger satisfaction and charging demand of driverless public transport to ensure efficient transportation and excellent user experience. Dijkstra algorithm is applied to solve the shortest path selection problem involved in the model, and genetic algorithm is used to solve the model. The route selection schemes of vehicle transportation plan, driving route and charging plan are obtained to achieve the goal of minimizing the total cost. The validity and practicability of the model and method are verified by the example of Sioux Falls network.