An Improvement of Trajectory Tracking Accuracy of Automatic Sewing Robot System by Variable Gain Learning Control

Takashi Yoshimi, Kenta Takezawa, Motoki Hirayama

研究成果: Article

抄録

In the sewing factory, non-routine tasks, especially curved surface sewing of three-dimensional products are still executed manually by human workers, because it is difficult to handle the sewing parts precisely by the automatic machine. Then, we are developing an automatic sewing robot system for their sewing. We evaluated the developed robot system and confirmed that the curved surface sewing motion is executed smoothly with low feeding speed. But, the trajectory tracking accuracy becomes bad when the feeding speed is high. Then, we applied learning control method to our robot system and confirmed that the trajectory tracking accuracy is improved sufficiently by this method even the sewing parts feeding speed is equal to human workers. However, we need much time to find suitable learning gains for getting the good result. So, we propose a variable gain learning control method which finds suitable learning gains automatically based on the trajectory tracking error of the robot arm. Finally, we confirmed that the enough trajectory tracking accuracy is achieved by the proposed method without much time and effort.

元の言語English
ページ(範囲)1-6
ページ数6
ジャーナルIFAC-PapersOnLine
51
発行部数22
DOI
出版物ステータスPublished - 2018 1 1

Fingerprint

Trajectories
Robots
Industrial plants

ASJC Scopus subject areas

  • Control and Systems Engineering

これを引用

An Improvement of Trajectory Tracking Accuracy of Automatic Sewing Robot System by Variable Gain Learning Control. / Yoshimi, Takashi; Takezawa, Kenta; Hirayama, Motoki.

:: IFAC-PapersOnLine, 巻 51, 番号 22, 01.01.2018, p. 1-6.

研究成果: Article

@article{95f232d41b6d437095339b592bd4f3b0,
title = "An Improvement of Trajectory Tracking Accuracy of Automatic Sewing Robot System by Variable Gain Learning Control",
abstract = "In the sewing factory, non-routine tasks, especially curved surface sewing of three-dimensional products are still executed manually by human workers, because it is difficult to handle the sewing parts precisely by the automatic machine. Then, we are developing an automatic sewing robot system for their sewing. We evaluated the developed robot system and confirmed that the curved surface sewing motion is executed smoothly with low feeding speed. But, the trajectory tracking accuracy becomes bad when the feeding speed is high. Then, we applied learning control method to our robot system and confirmed that the trajectory tracking accuracy is improved sufficiently by this method even the sewing parts feeding speed is equal to human workers. However, we need much time to find suitable learning gains for getting the good result. So, we propose a variable gain learning control method which finds suitable learning gains automatically based on the trajectory tracking error of the robot arm. Finally, we confirmed that the enough trajectory tracking accuracy is achieved by the proposed method without much time and effort.",
keywords = "Automatic sewing robot system, Curved surface sewing, Learning control, Non-routine task, Three-dimensional object, Trajectory tracking accuracy, Variable gain",
author = "Takashi Yoshimi and Kenta Takezawa and Motoki Hirayama",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.ifacol.2018.11.509",
language = "English",
volume = "51",
pages = "1--6",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "22",

}

TY - JOUR

T1 - An Improvement of Trajectory Tracking Accuracy of Automatic Sewing Robot System by Variable Gain Learning Control

AU - Yoshimi, Takashi

AU - Takezawa, Kenta

AU - Hirayama, Motoki

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In the sewing factory, non-routine tasks, especially curved surface sewing of three-dimensional products are still executed manually by human workers, because it is difficult to handle the sewing parts precisely by the automatic machine. Then, we are developing an automatic sewing robot system for their sewing. We evaluated the developed robot system and confirmed that the curved surface sewing motion is executed smoothly with low feeding speed. But, the trajectory tracking accuracy becomes bad when the feeding speed is high. Then, we applied learning control method to our robot system and confirmed that the trajectory tracking accuracy is improved sufficiently by this method even the sewing parts feeding speed is equal to human workers. However, we need much time to find suitable learning gains for getting the good result. So, we propose a variable gain learning control method which finds suitable learning gains automatically based on the trajectory tracking error of the robot arm. Finally, we confirmed that the enough trajectory tracking accuracy is achieved by the proposed method without much time and effort.

AB - In the sewing factory, non-routine tasks, especially curved surface sewing of three-dimensional products are still executed manually by human workers, because it is difficult to handle the sewing parts precisely by the automatic machine. Then, we are developing an automatic sewing robot system for their sewing. We evaluated the developed robot system and confirmed that the curved surface sewing motion is executed smoothly with low feeding speed. But, the trajectory tracking accuracy becomes bad when the feeding speed is high. Then, we applied learning control method to our robot system and confirmed that the trajectory tracking accuracy is improved sufficiently by this method even the sewing parts feeding speed is equal to human workers. However, we need much time to find suitable learning gains for getting the good result. So, we propose a variable gain learning control method which finds suitable learning gains automatically based on the trajectory tracking error of the robot arm. Finally, we confirmed that the enough trajectory tracking accuracy is achieved by the proposed method without much time and effort.

KW - Automatic sewing robot system

KW - Curved surface sewing

KW - Learning control

KW - Non-routine task

KW - Three-dimensional object

KW - Trajectory tracking accuracy

KW - Variable gain

UR - http://www.scopus.com/inward/record.url?scp=85058245371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058245371&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2018.11.509

DO - 10.1016/j.ifacol.2018.11.509

M3 - Article

AN - SCOPUS:85058245371

VL - 51

SP - 1

EP - 6

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 22

ER -