Research on coordinated scheduling of straddle carriers and quay cranes in automated container terminals based on reinforcement learning

Abstract

 Aiming at the coordination and scheduling problem between Automated Straddle Carrier (Automated Straddle Carrier) and Quay Crane (QC) in automated container terminals, consider that the quay crane cannot cross the straddle carrier, and the straddle carrier and the quay crane cannot be in adjacent lanes at the same time. A mixed-integer optimization model with the objective function of minimizing the final completion time of the quay crane is established under the constraints of different operating speeds and different speeds of straddle carriers in different states. A genetic algorithm based on reinforcement learning is designed, and the initial population is generated by the Q-learning algorithm, and the genetic algorithm (GA) is iterated to increase the diversity of the initial population. Finally, taking 5 groups of experiments as examples, the model is compared and solved by GAMS solver, genetic algorithm and genetic algorithm based on reinforcement learning. The results of an example show that the genetic algorithm based on reinforcement learning can solve the model and make the value of the objective function smaller, thus verifying the feasibility of the modified algorithm.