Intelligent Geographical Information System for Vehicle Routing (IGIS-VR): A modeling framework

In Egypt, freight movement relies heavily on road transport. Commercial vehicles constitute a major segment of the vehicle population that travels the country´s roads contributing to (and suffering from) daily congestion. Enhancing CV operations by minimizing their en-route travel times benefits both traffic network users as well as CV´s business owners. The absence of traffic data collection infrastructure, in many developing countries, hampers the usage of readily available vehicle routing systems. This paper introduces a modeling framework of an Intelligent Geographical Information System for Vehicle Routing (IGIS-VR). IGIS-VR integrates a Geographic information system (GIS) and a Reinforcement learning (RL) system to address the Capacitated Vehicle Routing Problems with Time Windows (CVRPTW). The developed model uses CVs as probe vehicles for on-the-move data collection. Collected data is manipulated through a self-adaptive learning environment to capture traffic network dynamics. The Q-learning concepts of the Temporal Difference (TD) solution approach of RL are used in the model formulation. Different estimation procedures for the model main parameters are explored.