Experimental evaluations of prediction servoing to moving object by hand-eye robotic system

Yusuke Sunami, Mamoru Minami, Akira Yanou

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

3 Citations (Scopus)

Abstract

In the field of robot vision, a control method called visual servoing attracts attention. The visual servoing is a method to control robots by visual information in a feedback loop, which is obtained by video cameras. So, this method is expected to be able to make robots adapt to tasks in changing or unknown environment. However, when the target object moves quickly, it happens to be unable for the robots to track it due to dynamical effect, i.e., motion delay. To decrease the delay, we have proposed prediction servoing control method, which utilizes prediction of the target position based on the past observed position data of the object and learning by neural networks, and utilize predicted position as a desired position for the visual servoing. In this research, we have confirmed how the learnig function in neural networks work for precise prediction of target's future position through visual servoing experiments.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1310-1315
Number of pages6
Publication statusPublished - 2013
Event2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, Japan
Duration: Sep 14 2013Sep 17 2013

Other

Other2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013
CountryJapan
CityNagoya
Period9/14/139/17/13

Fingerprint

Visual servoing
End effectors
Robotics
Robots
Neural networks
Video cameras
Computer vision
Feedback
Experiments

Keywords

  • GA
  • Prediction servoing
  • Visual feedback control

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Sunami, Y., Minami, M., & Yanou, A. (2013). Experimental evaluations of prediction servoing to moving object by hand-eye robotic system. In Proceedings of the SICE Annual Conference (pp. 1310-1315)

Experimental evaluations of prediction servoing to moving object by hand-eye robotic system. / Sunami, Yusuke; Minami, Mamoru; Yanou, Akira.

Proceedings of the SICE Annual Conference. 2013. p. 1310-1315.

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

Sunami, Y, Minami, M & Yanou, A 2013, Experimental evaluations of prediction servoing to moving object by hand-eye robotic system. in Proceedings of the SICE Annual Conference. pp. 1310-1315, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, Japan, 9/14/13.
Sunami Y, Minami M, Yanou A. Experimental evaluations of prediction servoing to moving object by hand-eye robotic system. In Proceedings of the SICE Annual Conference. 2013. p. 1310-1315
Sunami, Yusuke ; Minami, Mamoru ; Yanou, Akira. / Experimental evaluations of prediction servoing to moving object by hand-eye robotic system. Proceedings of the SICE Annual Conference. 2013. pp. 1310-1315
@inproceedings{439ef556d10a4c0e976a48cb78566296,
title = "Experimental evaluations of prediction servoing to moving object by hand-eye robotic system",
abstract = "In the field of robot vision, a control method called visual servoing attracts attention. The visual servoing is a method to control robots by visual information in a feedback loop, which is obtained by video cameras. So, this method is expected to be able to make robots adapt to tasks in changing or unknown environment. However, when the target object moves quickly, it happens to be unable for the robots to track it due to dynamical effect, i.e., motion delay. To decrease the delay, we have proposed prediction servoing control method, which utilizes prediction of the target position based on the past observed position data of the object and learning by neural networks, and utilize predicted position as a desired position for the visual servoing. In this research, we have confirmed how the learnig function in neural networks work for precise prediction of target's future position through visual servoing experiments.",
keywords = "GA, Prediction servoing, Visual feedback control",
author = "Yusuke Sunami and Mamoru Minami and Akira Yanou",
year = "2013",
language = "English",
pages = "1310--1315",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Experimental evaluations of prediction servoing to moving object by hand-eye robotic system

AU - Sunami, Yusuke

AU - Minami, Mamoru

AU - Yanou, Akira

PY - 2013

Y1 - 2013

N2 - In the field of robot vision, a control method called visual servoing attracts attention. The visual servoing is a method to control robots by visual information in a feedback loop, which is obtained by video cameras. So, this method is expected to be able to make robots adapt to tasks in changing or unknown environment. However, when the target object moves quickly, it happens to be unable for the robots to track it due to dynamical effect, i.e., motion delay. To decrease the delay, we have proposed prediction servoing control method, which utilizes prediction of the target position based on the past observed position data of the object and learning by neural networks, and utilize predicted position as a desired position for the visual servoing. In this research, we have confirmed how the learnig function in neural networks work for precise prediction of target's future position through visual servoing experiments.

AB - In the field of robot vision, a control method called visual servoing attracts attention. The visual servoing is a method to control robots by visual information in a feedback loop, which is obtained by video cameras. So, this method is expected to be able to make robots adapt to tasks in changing or unknown environment. However, when the target object moves quickly, it happens to be unable for the robots to track it due to dynamical effect, i.e., motion delay. To decrease the delay, we have proposed prediction servoing control method, which utilizes prediction of the target position based on the past observed position data of the object and learning by neural networks, and utilize predicted position as a desired position for the visual servoing. In this research, we have confirmed how the learnig function in neural networks work for precise prediction of target's future position through visual servoing experiments.

KW - GA

KW - Prediction servoing

KW - Visual feedback control

UR - http://www.scopus.com/inward/record.url?scp=84888582212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888582212&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84888582212

SP - 1310

EP - 1315

BT - Proceedings of the SICE Annual Conference

ER -