Can a two-link manipulator learn how to write?

Basel Alali, Kentaro Hirata, Kenji Sugimoto

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

This paper considers a version of the problem of how to teach robots to write characters in an actual environment. In particular, a feedforward controller is designed for two-link manipulators to improve tracking performance despite limited knowledge of the surroundings. An adaptive scheme, called MIMO-FEL (Multi-input Multi-output Feedback Error Learning), is employed to achieve the objective. After convergence, the feedforward controllers are switched depending on the target character to be written. This switching strategy is a clear contrast with the precise identification approach, which uses a single general-purpose controller.

Original languageEnglish
Title of host publicationIFAC Proceedings Volumes (IFAC-PapersOnline)
Volume17
Edition1 PART 1
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event17th World Congress, International Federation of Automatic Control, IFAC - Seoul, Korea, Republic of
Duration: Jul 6 2008 → Jul 11 2008

Other

Other17th World Congress, International Federation of Automatic Control, IFAC
CountryKorea, Republic of
CitySeoul
Period7/6/08 → 7/11/08

Fingerprint

Manipulators
Controllers
Robots
Feedback

Keywords

  • Adaptation and learning in physical agents
  • Adaptive control of systems
  • Adaptive system and control

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Alali, B., Hirata, K., & Sugimoto, K. (2008). Can a two-link manipulator learn how to write? In IFAC Proceedings Volumes (IFAC-PapersOnline) (1 PART 1 ed., Vol. 17) https://doi.org/10.3182/20080706-5-KR-1001.0217

Can a two-link manipulator learn how to write? / Alali, Basel; Hirata, Kentaro; Sugimoto, Kenji.

IFAC Proceedings Volumes (IFAC-PapersOnline). Vol. 17 1 PART 1. ed. 2008.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Alali, B, Hirata, K & Sugimoto, K 2008, Can a two-link manipulator learn how to write? in IFAC Proceedings Volumes (IFAC-PapersOnline). 1 PART 1 edn, vol. 17, 17th World Congress, International Federation of Automatic Control, IFAC, Seoul, Korea, Republic of, 7/6/08. https://doi.org/10.3182/20080706-5-KR-1001.0217
Alali B, Hirata K, Sugimoto K. Can a two-link manipulator learn how to write? In IFAC Proceedings Volumes (IFAC-PapersOnline). 1 PART 1 ed. Vol. 17. 2008 https://doi.org/10.3182/20080706-5-KR-1001.0217
Alali, Basel ; Hirata, Kentaro ; Sugimoto, Kenji. / Can a two-link manipulator learn how to write?. IFAC Proceedings Volumes (IFAC-PapersOnline). Vol. 17 1 PART 1. ed. 2008.
@inproceedings{66887a4da911410996591acb2d13a61b,
title = "Can a two-link manipulator learn how to write?",
abstract = "This paper considers a version of the problem of how to teach robots to write characters in an actual environment. In particular, a feedforward controller is designed for two-link manipulators to improve tracking performance despite limited knowledge of the surroundings. An adaptive scheme, called MIMO-FEL (Multi-input Multi-output Feedback Error Learning), is employed to achieve the objective. After convergence, the feedforward controllers are switched depending on the target character to be written. This switching strategy is a clear contrast with the precise identification approach, which uses a single general-purpose controller.",
keywords = "Adaptation and learning in physical agents, Adaptive control of systems, Adaptive system and control",
author = "Basel Alali and Kentaro Hirata and Kenji Sugimoto",
year = "2008",
doi = "10.3182/20080706-5-KR-1001.0217",
language = "English",
isbn = "9783902661005",
volume = "17",
booktitle = "IFAC Proceedings Volumes (IFAC-PapersOnline)",
edition = "1 PART 1",

}

TY - GEN

T1 - Can a two-link manipulator learn how to write?

AU - Alali, Basel

AU - Hirata, Kentaro

AU - Sugimoto, Kenji

PY - 2008

Y1 - 2008

N2 - This paper considers a version of the problem of how to teach robots to write characters in an actual environment. In particular, a feedforward controller is designed for two-link manipulators to improve tracking performance despite limited knowledge of the surroundings. An adaptive scheme, called MIMO-FEL (Multi-input Multi-output Feedback Error Learning), is employed to achieve the objective. After convergence, the feedforward controllers are switched depending on the target character to be written. This switching strategy is a clear contrast with the precise identification approach, which uses a single general-purpose controller.

AB - This paper considers a version of the problem of how to teach robots to write characters in an actual environment. In particular, a feedforward controller is designed for two-link manipulators to improve tracking performance despite limited knowledge of the surroundings. An adaptive scheme, called MIMO-FEL (Multi-input Multi-output Feedback Error Learning), is employed to achieve the objective. After convergence, the feedforward controllers are switched depending on the target character to be written. This switching strategy is a clear contrast with the precise identification approach, which uses a single general-purpose controller.

KW - Adaptation and learning in physical agents

KW - Adaptive control of systems

KW - Adaptive system and control

UR - http://www.scopus.com/inward/record.url?scp=79961019629&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79961019629&partnerID=8YFLogxK

U2 - 10.3182/20080706-5-KR-1001.0217

DO - 10.3182/20080706-5-KR-1001.0217

M3 - Conference contribution

SN - 9783902661005

VL - 17

BT - IFAC Proceedings Volumes (IFAC-PapersOnline)

ER -

Access to Document