Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system

Shuichi Sato, Masaru Nakano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We have been studying a new, lean and agile manufacturing concept. In this paper, we focus on an Automated Guided Vehicle (AGV) dispatching problem which in most cases, is resolved by using a First Come First Service (FCFS) rule in existing systems. We have developed a cooperative dispatching strategy using a Stochastic Learning Automaton (SLA) reinforcement learning method within the framework of a multi-agent system. We have implemented the idea that if an agent can't learn for itself, it should imitate other agents. We think the learning property including an imitation should be acquired in accordance with an agent's characteristics, such as its speed and failure rate. We will present an approach in which two kinds of SLAs run in parallel and each agent can autonomically acquire both behavior and learning properties. This paper demonstrates that our strategy can achieve an approximate 30% improvement in handling capability, compared with a FCFS rule in a realistic system. Furthermore, we demonstrate that an AGV can obtain its desired behavior more quickly by composing double SLAs.

Original languageEnglish
Title of host publicationProceedings of the Japan/USA Symposium on Flexible Automation
EditorsK. Stelson, F. Oba
Pages1287-1292
Number of pages6
Volume2
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 Japan-USA Symposium on Flexible Automation. Part 2 (of 2) - Boston, MA, USA
Duration: 1996 Jul 71996 Jul 10

Other

OtherProceedings of the 1996 Japan-USA Symposium on Flexible Automation. Part 2 (of 2)
CityBoston, MA, USA
Period96/7/796/7/10

Fingerprint

Materials handling
Reinforcement learning
Multi agent systems

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sato, S., & Nakano, M. (1996). Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system. In K. Stelson, & F. Oba (Eds.), Proceedings of the Japan/USA Symposium on Flexible Automation (Vol. 2, pp. 1287-1292)

Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system. / Sato, Shuichi; Nakano, Masaru.

Proceedings of the Japan/USA Symposium on Flexible Automation. ed. / K. Stelson; F. Oba. Vol. 2 1996. p. 1287-1292.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sato, S & Nakano, M 1996, Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system. in K Stelson & F Oba (eds), Proceedings of the Japan/USA Symposium on Flexible Automation. vol. 2, pp. 1287-1292, Proceedings of the 1996 Japan-USA Symposium on Flexible Automation. Part 2 (of 2), Boston, MA, USA, 96/7/7.
Sato S, Nakano M. Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system. In Stelson K, Oba F, editors, Proceedings of the Japan/USA Symposium on Flexible Automation. Vol. 2. 1996. p. 1287-1292
Sato, Shuichi ; Nakano, Masaru. / Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system. Proceedings of the Japan/USA Symposium on Flexible Automation. editor / K. Stelson ; F. Oba. Vol. 2 1996. pp. 1287-1292
@inproceedings{88b64f8831e74cdda36c4c0e7dfdc776,
title = "Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system",
abstract = "We have been studying a new, lean and agile manufacturing concept. In this paper, we focus on an Automated Guided Vehicle (AGV) dispatching problem which in most cases, is resolved by using a First Come First Service (FCFS) rule in existing systems. We have developed a cooperative dispatching strategy using a Stochastic Learning Automaton (SLA) reinforcement learning method within the framework of a multi-agent system. We have implemented the idea that if an agent can't learn for itself, it should imitate other agents. We think the learning property including an imitation should be acquired in accordance with an agent's characteristics, such as its speed and failure rate. We will present an approach in which two kinds of SLAs run in parallel and each agent can autonomically acquire both behavior and learning properties. This paper demonstrates that our strategy can achieve an approximate 30{\%} improvement in handling capability, compared with a FCFS rule in a realistic system. Furthermore, we demonstrate that an AGV can obtain its desired behavior more quickly by composing double SLAs.",
author = "Shuichi Sato and Masaru Nakano",
year = "1996",
language = "English",
volume = "2",
pages = "1287--1292",
editor = "K. Stelson and F. Oba",
booktitle = "Proceedings of the Japan/USA Symposium on Flexible Automation",

}

TY - GEN

T1 - Dispatching rule acquisition with double stochastic learning automata for dynamic material handling system

AU - Sato, Shuichi

AU - Nakano, Masaru

PY - 1996

Y1 - 1996

N2 - We have been studying a new, lean and agile manufacturing concept. In this paper, we focus on an Automated Guided Vehicle (AGV) dispatching problem which in most cases, is resolved by using a First Come First Service (FCFS) rule in existing systems. We have developed a cooperative dispatching strategy using a Stochastic Learning Automaton (SLA) reinforcement learning method within the framework of a multi-agent system. We have implemented the idea that if an agent can't learn for itself, it should imitate other agents. We think the learning property including an imitation should be acquired in accordance with an agent's characteristics, such as its speed and failure rate. We will present an approach in which two kinds of SLAs run in parallel and each agent can autonomically acquire both behavior and learning properties. This paper demonstrates that our strategy can achieve an approximate 30% improvement in handling capability, compared with a FCFS rule in a realistic system. Furthermore, we demonstrate that an AGV can obtain its desired behavior more quickly by composing double SLAs.

AB - We have been studying a new, lean and agile manufacturing concept. In this paper, we focus on an Automated Guided Vehicle (AGV) dispatching problem which in most cases, is resolved by using a First Come First Service (FCFS) rule in existing systems. We have developed a cooperative dispatching strategy using a Stochastic Learning Automaton (SLA) reinforcement learning method within the framework of a multi-agent system. We have implemented the idea that if an agent can't learn for itself, it should imitate other agents. We think the learning property including an imitation should be acquired in accordance with an agent's characteristics, such as its speed and failure rate. We will present an approach in which two kinds of SLAs run in parallel and each agent can autonomically acquire both behavior and learning properties. This paper demonstrates that our strategy can achieve an approximate 30% improvement in handling capability, compared with a FCFS rule in a realistic system. Furthermore, we demonstrate that an AGV can obtain its desired behavior more quickly by composing double SLAs.

UR - http://www.scopus.com/inward/record.url?scp=0030414468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030414468&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030414468

VL - 2

SP - 1287

EP - 1292

BT - Proceedings of the Japan/USA Symposium on Flexible Automation

A2 - Stelson, K.

A2 - Oba, F.

ER -