Computational GIS and Agent-Based Model Development for Routing Optimization to Facilitate Pavement Condition Data Collection

Transportation agencies across the world have been implementing different types of Pavement Management Systems (PMS) to facilitate pavement management and maintenance. Obtaining the necessary information in a manual pavement distress data collection process is costly and time-consuming. Research on the data collection of pavement conditions has focused mainly on evaluating the quality of the data collected, and there is limited research on ways to improve the efficiency of the data collection process (e.g., selection of optimized routes for collecting data). In this study, Geographical Information Systems (GIS) and Agent-Based Modeling (ABM), using swarm intelligence, are integrated to optimize decision-making processes for optimal routing selection in manual data collection process. The GIS platform provides the road spatial database containing the pavement sections that will be evaluated. Ant Colony Optimization (ACO) was selected as the algorithm to optimize the decision-making process of pavement evaluation crews (agents) during the pavement distress data collection process. Both the GIS and ABM models are developed using available data from the manual pavement distress data collection process in summer 2012 for the State of New Mexico. The results of this research will improve the understanding of route selection for pavement data collection.