Smart Transaction Picking in Tier-to-tier SBS/RS by Deep Q-Learning

Bartu Arslan, Banu Yetkin Ekren

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

By the rapid growth of e-commerce, the intralogistics sector is facing new challenges. Intralogistics sector requires more flexible, scalable processes with maximum reliability and availability. They are complicated and interconnected systems, whose all components are required to be perfectly coordinated with each other for optimal functionality. In this work, we study an intralogistics technology, shuttle-based storage and retrieval system (SBS/RS), where shuttles are tier-to-tier. In this novel system design, in an effort to increase shuttle utilization as well as decrease initial investment cost, shuttles are designed in a more flexible travel manner so that they can change their tiers within an aisle by using a separate lifting mechanism. Due to the complexity of such system design as well as aiming to obtain fast transaction process time by the decreased number of shuttles in the system, we implement a Deep Q-Learning (DQL) approach to let shuttles select the best transaction to process based on its targets. We compare the performance of the DQL by the average cycle time per transaction performance metric with the other well-known selection rules, First-in-First-Out (FIFO) and Shortest Process Time (SPT). Results show that Deep Q-Learning approach produces better results than those FIFO and SPT.
Original languageEnglish
Title of host publicationProceedings of the 11th Annual International Conference on Industrial Engineering and Operations Management, 2021
PublisherIEOM Society
Pages6415-6425
Number of pages11
ISBN (Electronic)978-1-7923-6124-1
ISBN (Print)9781792361241
Publication statusPublished - 2021
Externally publishedYes
Event11th Annual International Conference on Industrial Engineering and Operations Management - Virtual, Singapore
Duration: 7 Mar 202111 Mar 2021
http://ieomsociety.org/singapore2021/

Conference

Conference11th Annual International Conference on Industrial Engineering and Operations Management
Country/TerritorySingapore
Period7/03/2111/03/21
Internet address

Keywords

  • Deep Q-Learning
  • Deep Reinforcement Learning
  • Optimization
  • SBS/RS
  • Simulation

Fingerprint

Dive into the research topics of 'Smart Transaction Picking in Tier-to-tier SBS/RS by Deep Q-Learning'. Together they form a unique fingerprint.

Cite this