DECISION-SUPPORT FOR VEHICLE DISPATCHING USING GENETIC PROGRAMMING

Vehicle dispatching consists of allocating real-time service requests to a fleet of moving vehicles. In this paper, each vehicle is associat ed with a vector of attribute values that describes its current situat ion with respect to new incoming service requests. Using this attribut e description, a utility function aimed at approximating the decision process of a professional dispatcher is constructed through genetic pr ogramming. Computational results are reported on requests collected fr om a courier service company and a comparison is provided with a neura l network model and a simple dispatching policy.