Designing guide-path networks for automated guided vehicle system by using the Q-learning technique

Jae Kook Lim, Joon Mook Lim, Kazuho Yoshimoto, Kap Hwan Kim, Teruo Takahashi

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    This paper suggests a Q-learning technique for designing guide-path networks for automated guided vehicle systems. This study uses the total travel time as the decision criteria for constructing guide-path layouts. The Q-learning technique is applied to the estimation of the travel time of vehicles on each segment of the guide-path. Computational experiments were performed to evaluate the performance of the proposed algorithm. The simulation results showed that the proposed algorithm is superior to Kim and Tanchoco's (1993) in terms of average travel time, interference time, and number of deliveries.

    Original languageEnglish
    Pages (from-to)1-17
    Number of pages17
    JournalComputers and Industrial Engineering
    Volume44
    Issue number1
    DOIs
    Publication statusPublished - 2003 Jan

    Fingerprint

    Automated Guided Vehicles
    Q-learning
    Travel Time
    Travel time
    Path
    Computational Experiments
    Layout
    Interference
    Evaluate
    Automated guided vehicles
    Simulation
    Experiments

    Keywords

    • Automated guided vehicle system
    • Beam search
    • Guide-path network design
    • Q-learning

    ASJC Scopus subject areas

    • Management Science and Operations Research
    • Information Systems and Management
    • Industrial and Manufacturing Engineering
    • Applied Mathematics

    Cite this

    Designing guide-path networks for automated guided vehicle system by using the Q-learning technique. / Lim, Jae Kook; Lim, Joon Mook; Yoshimoto, Kazuho; Kim, Kap Hwan; Takahashi, Teruo.

    In: Computers and Industrial Engineering, Vol. 44, No. 1, 01.2003, p. 1-17.

    Research output: Contribution to journalArticle

    Lim, Jae Kook ; Lim, Joon Mook ; Yoshimoto, Kazuho ; Kim, Kap Hwan ; Takahashi, Teruo. / Designing guide-path networks for automated guided vehicle system by using the Q-learning technique. In: Computers and Industrial Engineering. 2003 ; Vol. 44, No. 1. pp. 1-17.
    @article{7d5f68b855bc45d69fda5db0f418715f,
    title = "Designing guide-path networks for automated guided vehicle system by using the Q-learning technique",
    abstract = "This paper suggests a Q-learning technique for designing guide-path networks for automated guided vehicle systems. This study uses the total travel time as the decision criteria for constructing guide-path layouts. The Q-learning technique is applied to the estimation of the travel time of vehicles on each segment of the guide-path. Computational experiments were performed to evaluate the performance of the proposed algorithm. The simulation results showed that the proposed algorithm is superior to Kim and Tanchoco's (1993) in terms of average travel time, interference time, and number of deliveries.",
    keywords = "Automated guided vehicle system, Beam search, Guide-path network design, Q-learning",
    author = "Lim, {Jae Kook} and Lim, {Joon Mook} and Kazuho Yoshimoto and Kim, {Kap Hwan} and Teruo Takahashi",
    year = "2003",
    month = "1",
    doi = "10.1016/S0360-8352(02)00128-6",
    language = "English",
    volume = "44",
    pages = "1--17",
    journal = "Computers and Industrial Engineering",
    issn = "0360-8352",
    publisher = "Elsevier Limited",
    number = "1",

    }

    TY - JOUR

    T1 - Designing guide-path networks for automated guided vehicle system by using the Q-learning technique

    AU - Lim, Jae Kook

    AU - Lim, Joon Mook

    AU - Yoshimoto, Kazuho

    AU - Kim, Kap Hwan

    AU - Takahashi, Teruo

    PY - 2003/1

    Y1 - 2003/1

    N2 - This paper suggests a Q-learning technique for designing guide-path networks for automated guided vehicle systems. This study uses the total travel time as the decision criteria for constructing guide-path layouts. The Q-learning technique is applied to the estimation of the travel time of vehicles on each segment of the guide-path. Computational experiments were performed to evaluate the performance of the proposed algorithm. The simulation results showed that the proposed algorithm is superior to Kim and Tanchoco's (1993) in terms of average travel time, interference time, and number of deliveries.

    AB - This paper suggests a Q-learning technique for designing guide-path networks for automated guided vehicle systems. This study uses the total travel time as the decision criteria for constructing guide-path layouts. The Q-learning technique is applied to the estimation of the travel time of vehicles on each segment of the guide-path. Computational experiments were performed to evaluate the performance of the proposed algorithm. The simulation results showed that the proposed algorithm is superior to Kim and Tanchoco's (1993) in terms of average travel time, interference time, and number of deliveries.

    KW - Automated guided vehicle system

    KW - Beam search

    KW - Guide-path network design

    KW - Q-learning

    UR - http://www.scopus.com/inward/record.url?scp=0037209989&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0037209989&partnerID=8YFLogxK

    U2 - 10.1016/S0360-8352(02)00128-6

    DO - 10.1016/S0360-8352(02)00128-6

    M3 - Article

    AN - SCOPUS:0037209989

    VL - 44

    SP - 1

    EP - 17

    JO - Computers and Industrial Engineering

    JF - Computers and Industrial Engineering

    SN - 0360-8352

    IS - 1

    ER -