Multi-task deep reinforcement learning for dynamic scheduling of large-scale fleets in earthmoving operations

Abstract

Large-scale earthwork transportation encounters queuing congestion and dynamic uncertainties, while existing methods ignore complex traffic behaviors and exhibit limited responsiveness and generalization. This paper proposes a multi-task Deep Reinforcement Learning (DRL) framework for the dynamic scheduling of large fleets across supply sites and traffic networks. In the framework, multiple agents interact in complex environments modeled by discrete-event simulation, utilizing long short-term memory networks that consider queuing behaviors and dynamic trends of transportation systems to allocate rational materials, supply sites, and routes collaboratively, with an invariant update strategy to balance generalization and task-specific optimization during training. Experiments demonstrate that the model generates dynamic schedules within 7 min, reducing transportation time by 24 %. The trained agent can adapt to the changing transportation demand in complex construction environments and enhance transportation efficiency. This paper demonstrates the potential of DRL in scheduling more complex construction projects and promoting real-time lean control of modern logistics.