A method for searching assembly orders by utilizing reinforcement learning

Keijiro Watanabe, Kyosuke Arai, Shuhei Inada

Research output: Contribution to journalArticle

Abstract

In recent years, the movement to introduce robots in production systems with the aim of replacing manual labor or combining manual and robot labor has started. In particular, dual-arm robots, which have two robotic arms, are gaining much attention in view of their ability to replace manual laborers. However, planning an efficient work system beforehand and teaching the lean movements to the robots are essential for using them more effectively. In assembly processes, the result of selecting the assembly order greatly influences the productivity of the production process. In such a background, this paper examines a method for determining an assembly order with high work efficiency. Under the assumption that dual-arm robots assemble the products that can be assembled easily (i.e., stacking toy blocks is used here), we propose a computational model for searching a highly efficient assembly order utilizing reinforcement learning. We also consider a method for using the results of previous learning model studies to effectively find solutions for new assembly models. Regression analysis is utilized to transfer the past learning results.

Original languageEnglish
Pages (from-to)121-130
Number of pages10
JournalJournal of Japan Industrial Management Association
Volume69
Issue number3
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Reinforcement learning
Reinforcement Learning
Robot
Robots
Personnel
Robotic arms
Stacking
Production Systems
Regression Analysis
Regression analysis
Computational Model
Productivity
Robotics
Teaching
Planning
Model
Learning
Movement
Labor

Keywords

  • Assembly order
  • Disassembly order
  • Dual-arm robot
  • Q-learning
  • Regression analysis
  • Reinforcement learning

ASJC Scopus subject areas

  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering
  • Applied Mathematics

Cite this

A method for searching assembly orders by utilizing reinforcement learning. / Watanabe, Keijiro; Arai, Kyosuke; Inada, Shuhei.

In: Journal of Japan Industrial Management Association, Vol. 69, No. 3, 01.01.2018, p. 121-130.

Research output: Contribution to journalArticle

@article{7f5d4f370f304201ad6ac3263794f00c,
title = "A method for searching assembly orders by utilizing reinforcement learning",
abstract = "In recent years, the movement to introduce robots in production systems with the aim of replacing manual labor or combining manual and robot labor has started. In particular, dual-arm robots, which have two robotic arms, are gaining much attention in view of their ability to replace manual laborers. However, planning an efficient work system beforehand and teaching the lean movements to the robots are essential for using them more effectively. In assembly processes, the result of selecting the assembly order greatly influences the productivity of the production process. In such a background, this paper examines a method for determining an assembly order with high work efficiency. Under the assumption that dual-arm robots assemble the products that can be assembled easily (i.e., stacking toy blocks is used here), we propose a computational model for searching a highly efficient assembly order utilizing reinforcement learning. We also consider a method for using the results of previous learning model studies to effectively find solutions for new assembly models. Regression analysis is utilized to transfer the past learning results.",
keywords = "Assembly order, Disassembly order, Dual-arm robot, Q-learning, Regression analysis, Reinforcement learning",
author = "Keijiro Watanabe and Kyosuke Arai and Shuhei Inada",
year = "2018",
month = "1",
day = "1",
doi = "10.11221/jima.69.121",
language = "English",
volume = "69",
pages = "121--130",
journal = "Journal of Japan Industrial Management Association",
issn = "0386-4812",
publisher = "Nihon Keikei Kogakkai",
number = "3",

}

TY - JOUR

T1 - A method for searching assembly orders by utilizing reinforcement learning

AU - Watanabe, Keijiro

AU - Arai, Kyosuke

AU - Inada, Shuhei

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In recent years, the movement to introduce robots in production systems with the aim of replacing manual labor or combining manual and robot labor has started. In particular, dual-arm robots, which have two robotic arms, are gaining much attention in view of their ability to replace manual laborers. However, planning an efficient work system beforehand and teaching the lean movements to the robots are essential for using them more effectively. In assembly processes, the result of selecting the assembly order greatly influences the productivity of the production process. In such a background, this paper examines a method for determining an assembly order with high work efficiency. Under the assumption that dual-arm robots assemble the products that can be assembled easily (i.e., stacking toy blocks is used here), we propose a computational model for searching a highly efficient assembly order utilizing reinforcement learning. We also consider a method for using the results of previous learning model studies to effectively find solutions for new assembly models. Regression analysis is utilized to transfer the past learning results.

AB - In recent years, the movement to introduce robots in production systems with the aim of replacing manual labor or combining manual and robot labor has started. In particular, dual-arm robots, which have two robotic arms, are gaining much attention in view of their ability to replace manual laborers. However, planning an efficient work system beforehand and teaching the lean movements to the robots are essential for using them more effectively. In assembly processes, the result of selecting the assembly order greatly influences the productivity of the production process. In such a background, this paper examines a method for determining an assembly order with high work efficiency. Under the assumption that dual-arm robots assemble the products that can be assembled easily (i.e., stacking toy blocks is used here), we propose a computational model for searching a highly efficient assembly order utilizing reinforcement learning. We also consider a method for using the results of previous learning model studies to effectively find solutions for new assembly models. Regression analysis is utilized to transfer the past learning results.

KW - Assembly order

KW - Disassembly order

KW - Dual-arm robot

KW - Q-learning

KW - Regression analysis

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85060713937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060713937&partnerID=8YFLogxK

U2 - 10.11221/jima.69.121

DO - 10.11221/jima.69.121

M3 - Article

VL - 69

SP - 121

EP - 130

JO - Journal of Japan Industrial Management Association

JF - Journal of Japan Industrial Management Association

SN - 0386-4812

IS - 3

ER -