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.

Dispatching and cooperative trajectory planning for multiple autonomous forklifts in a warehouse is a widely applied research topic. The conventional methods in this domain regard dispatching and planning as isolated procedures, which render the overall motion quality of the forklift team imperfect. The dispatching and planning problems should be considered simultaneously to achieve optimal cooperative trajectories. However, this approach renders a large-scale nonconvex problem, which is extremely difficult to solve in real time. A joint dispatching and planning method is proposed to balance solution quality and speed. The proposed method is characterized by its fast runtime, light computational burden, and high solution quality. In particular, the candidate goals of each forklift are enumerated. Each candidate dispatch solution is measured after concrete trajectories are generated via an improved hybrid A* search algorithm, which is incorporated with an artificial neural network to improve the cost evaluation process. The proposed joint dispatching and planning method is computationally cheap, kinematically feasible, avoids collisions with obstacles/forklifts, and finds the global optimum quickly. The presented motion planning strategy demonstrates that the integration of a neural network with the dispatching approach leads to a warehouse filling/emptying mission completion time that is 2% shorter than the most efficient strategy lacking machine-learning integration. Notably, the mission completion times across these strategies vary by approximately 15%.