Scheduling of twin automated stacking cranes based on Deep Reinforcement Learning

Xin Jin, Nan Mi, Wen Song, Qiqiang Li

Abstract: Highlights•An end-to-end DRL method is proposed to solve twin ASCs scheduling problem.•A novel MDP model for twin ASCs scheduling is designed.•An attention based neural structure is proposed for grasp pairwise relationships.•The proposed DRL method can generate high-quality solutions with low time cost.