Teaching motor schemes using adaptive accommodation algorithms for complex assembly

Byungduk Kang, Jangwoo Park, Byungchan Kim, Sungchul Kang, Shin Suk Park

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

Abstract

Complex assembly involves the objects with complex geometry, where unexpected contacts may occur frequently during insertion due to the complex shapes of assembled parts and the environment. In the previous study, we developed adaptive control algorithm (adaptive accommodation method) for 2D- and 3D-complex assembly tasks. In this study, we developed an artificial neural network (ANN) model for complex assembly. First, the proposed model learns assembly schemes through teaching signals from the adaptive accommodation method. Then the trained ANN model was used to execute complex assembly tasks in different geometric conditions. To test the validity of the proposed strategy, the trained ANN model trained with adaptive accommodation algorithm performed Tassembly. The simulation results showed that proposed ANN model can successfully achieve task goals as the adaptive accommodation method. For future studies, we are planning to use the developed ANN module trained by human demonstration for various contact tasks.

Original languageEnglish
Title of host publication39th International Symposium on Robotics, ISR 2008
Pages431-435
Number of pages5
Publication statusPublished - 2008 Dec 1
Event39th International Symposium on Robotics, ISR 2008 - Seoul, Korea, Republic of
Duration: 2008 Oct 152008 Oct 17

Other

Other39th International Symposium on Robotics, ISR 2008
CountryKorea, Republic of
CitySeoul
Period08/10/1508/10/17

Fingerprint

Teaching
Neural networks
Demonstrations
Planning
Geometry

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

Cite this

Kang, B., Park, J., Kim, B., Kang, S., & Park, S. S. (2008). Teaching motor schemes using adaptive accommodation algorithms for complex assembly. In 39th International Symposium on Robotics, ISR 2008 (pp. 431-435)

Teaching motor schemes using adaptive accommodation algorithms for complex assembly. / Kang, Byungduk; Park, Jangwoo; Kim, Byungchan; Kang, Sungchul; Park, Shin Suk.

39th International Symposium on Robotics, ISR 2008. 2008. p. 431-435.

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

Kang, B, Park, J, Kim, B, Kang, S & Park, SS 2008, Teaching motor schemes using adaptive accommodation algorithms for complex assembly. in 39th International Symposium on Robotics, ISR 2008. pp. 431-435, 39th International Symposium on Robotics, ISR 2008, Seoul, Korea, Republic of, 08/10/15.
Kang B, Park J, Kim B, Kang S, Park SS. Teaching motor schemes using adaptive accommodation algorithms for complex assembly. In 39th International Symposium on Robotics, ISR 2008. 2008. p. 431-435
Kang, Byungduk ; Park, Jangwoo ; Kim, Byungchan ; Kang, Sungchul ; Park, Shin Suk. / Teaching motor schemes using adaptive accommodation algorithms for complex assembly. 39th International Symposium on Robotics, ISR 2008. 2008. pp. 431-435
@inproceedings{c94d69a6002c4f63954be7de740dbef0,
title = "Teaching motor schemes using adaptive accommodation algorithms for complex assembly",
abstract = "Complex assembly involves the objects with complex geometry, where unexpected contacts may occur frequently during insertion due to the complex shapes of assembled parts and the environment. In the previous study, we developed adaptive control algorithm (adaptive accommodation method) for 2D- and 3D-complex assembly tasks. In this study, we developed an artificial neural network (ANN) model for complex assembly. First, the proposed model learns assembly schemes through teaching signals from the adaptive accommodation method. Then the trained ANN model was used to execute complex assembly tasks in different geometric conditions. To test the validity of the proposed strategy, the trained ANN model trained with adaptive accommodation algorithm performed Tassembly. The simulation results showed that proposed ANN model can successfully achieve task goals as the adaptive accommodation method. For future studies, we are planning to use the developed ANN module trained by human demonstration for various contact tasks.",
author = "Byungduk Kang and Jangwoo Park and Byungchan Kim and Sungchul Kang and Park, {Shin Suk}",
year = "2008",
month = "12",
day = "1",
language = "English",
pages = "431--435",
booktitle = "39th International Symposium on Robotics, ISR 2008",

}

TY - GEN

T1 - Teaching motor schemes using adaptive accommodation algorithms for complex assembly

AU - Kang, Byungduk

AU - Park, Jangwoo

AU - Kim, Byungchan

AU - Kang, Sungchul

AU - Park, Shin Suk

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Complex assembly involves the objects with complex geometry, where unexpected contacts may occur frequently during insertion due to the complex shapes of assembled parts and the environment. In the previous study, we developed adaptive control algorithm (adaptive accommodation method) for 2D- and 3D-complex assembly tasks. In this study, we developed an artificial neural network (ANN) model for complex assembly. First, the proposed model learns assembly schemes through teaching signals from the adaptive accommodation method. Then the trained ANN model was used to execute complex assembly tasks in different geometric conditions. To test the validity of the proposed strategy, the trained ANN model trained with adaptive accommodation algorithm performed Tassembly. The simulation results showed that proposed ANN model can successfully achieve task goals as the adaptive accommodation method. For future studies, we are planning to use the developed ANN module trained by human demonstration for various contact tasks.

AB - Complex assembly involves the objects with complex geometry, where unexpected contacts may occur frequently during insertion due to the complex shapes of assembled parts and the environment. In the previous study, we developed adaptive control algorithm (adaptive accommodation method) for 2D- and 3D-complex assembly tasks. In this study, we developed an artificial neural network (ANN) model for complex assembly. First, the proposed model learns assembly schemes through teaching signals from the adaptive accommodation method. Then the trained ANN model was used to execute complex assembly tasks in different geometric conditions. To test the validity of the proposed strategy, the trained ANN model trained with adaptive accommodation algorithm performed Tassembly. The simulation results showed that proposed ANN model can successfully achieve task goals as the adaptive accommodation method. For future studies, we are planning to use the developed ANN module trained by human demonstration for various contact tasks.

UR - http://www.scopus.com/inward/record.url?scp=84876774431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876774431&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84876774431

SP - 431

EP - 435

BT - 39th International Symposium on Robotics, ISR 2008

ER -