A single-dependent agent approach for stochastic time-dependent truck dispatching in open-pit mining

Material transportation is one of the most important aspects of open-pit mine operations. The problem usually involves a truck dispatching system in which decisions on truck assignments and destinations are taken in real-time. Due to its significance, several decision systems for material transportation in open-pit mining have been developed in the last few years, improving productivity and reducing operational costs. This paper presents a single-dependent agent approach based on Time-dependent Markov Decision Processes (TiMDPs) to model the truck dispatching problem in an example mine. The uncertainty is present in the model as stochastic path selections by the truck driver. Simulations are executed using the SimEvents™ framework, and the results compared to other dispatching heuristics commonly used in the mining industry show the superiority of the proposed approach.