Skip to main content

ORIGINAL RESEARCH article

Front. Artif. Intell.
Sec. Machine Learning and Artificial Intelligence
Volume 7 - 2024 | doi: 10.3389/frai.2024.1420051

Efficient AGV Scheduling for Automated Container Terminals: Minimizing Empty Runs with Weight Constraints and Time Windows

Provisionally accepted
Jing Chen Jing Chen *Weijie He Weijie He Chaolong Zhang Chaolong Zhang Shuyue Wang Shuyue Wang
  • College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China

The final, formatted version of the article will be published soon.

    To improve the efficiency of automated container terminals, optimizing the scheduling of Automated Guided Vehicles (AGVs) is essential. Traditional AGV strategies often overlook the issue of empty runs. In contrast, the proposed model aims to minimize the empty runs of AGVs by ensuring each AGV unloads a container at the yard and immediately loads another container before returning to the quay. The key contributions of this study include the integration of weight constraints and time windows into the scheduling model, addressing both the safety and efficiency of AGV operations. A constraint penalty strategy is employed to handle overweight container tasks, and time windows are used to define the loading and unloading sequence for each container, considering the vessel's berthing time and the operational requirements of the yard. Using a Genetic Algorithm (GA) with penalty functions, the model is solved to obtain the minimum operating time for AGVs. Experimental results using simulated data provided the optimal AGV scheduling sequences, with the GA demonstrating certain advantages over other algorithms.The simulation data and code are available on GitHub for further validation and research.

    Keywords: Automated guided vehicles (AGVs), Automated container terminal, fully loaded, Weight constraints, Time windows, Genetic algorithm (GA), Penalty coefficients

    Received: 19 Apr 2024; Accepted: 29 Jul 2024.

    Copyright: © 2024 Chen, He, Zhang and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Jing Chen, College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.