A Multiagent System for Truck Dispatching in Open-pit Mines

Abstract

Material handling is an important logistic process for open-pit mines. In this process, shovels extract materials and load trucks that transport these materials to different destinations. To support this process, different centralized dispatching solutions have been implemented based on mathematical programming, heuristic processes or simulation modelling. Weaknesses in these methods can be observed in addressing the dynamics of a mine and by not providing a precise dispatching solution. In this paper, we present a solution based on Multiagent Systems (MAS) where the equipment items are represented by intelligent agents that interact with each other to meet the production goals at a minimum cost. The results obtained by applying the MAS in a simulated open-pit mine with actual data show more specific solutions than the current centralized solutions in a practical calculation time frame. In addition, the MAS decreases the truck costs on average by 18%.