Micro-Factors-Aware Scheduling of Multiple Autonomous Trucks in Open-Pit Mining via Enhanced Metaheuristics

Abstract

Traditional open-pit mineral transportation systems are typically subject to manual command, frequently leading to vehicular delays and traffic congestion. With the advancement of automation and electrification technologies, this study proposes a highly accurate scheduling method for multiple autonomous trucks in an open-pit mine. This model considers micro-level temporal and spatial factors to tackle the task of scheduling autonomous trucks within open-pit mines. The cost function of the concerned scheduling problem is a comprehensive evaluation of energy consumption, time, and output. Beyond the loading and unloading activities, the model also factors in the charging requirements of autonomous trucks in mining regions. The scheduling model integrates a Voronoi diagram search and optimal spatial path time matching, aiming to provide superior mission planning and decision-making solutions for autonomous trucks in mining regions. For an efficient solution to the scheduling problem, we propose an improved-evolution artificial bee colony (IE-ABC) algorithm. This algorithm improves the global search and re-initialization processes and conducts algorithm ablation experiments to closely examine their impact on optimization. Simulation results across various algorithms, cost function definition strategy, and encoding strategy show that our method can improve scheduling performance in energy consumption and time. Experimental results demonstrate that the proposed model and algorithm can effectively solve the scheduling decision-making problem in an unmanned open-pit mine.