Fish catching by visual servoing using neural network prediction

Toshiaki Yoshida, Mamoru Minami, Yasushi Mae

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

2 Citations (Scopus)

Abstract

This paper presents a method to predict a fish motion by Neural Network (N.N.) with on-line learning when a robot is pursuing fish-catching by a net at hand through hand-eye robot visual servoing. We assume the motion trajectory of a fish swimming in a pool be approximated by a circle with time varying radius and center position. We try to improve prediction accuracy of a fish motion by using N.N. whose inputs are radii and angular velocities in past three control-times and outputs are radius and angular velocity in the following control period. Using radius and angular velocity obtained by circular approximation, we confirmed that the proposed N.N. prediction system can maintain good prediction performances under the proposed on-line learning process.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages2372-2378
Number of pages7
DOIs
Publication statusPublished - 2007
Externally publishedYes
EventSICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007 - Takamatsu, Japan
Duration: Sep 17 2007Sep 20 2007

Other

OtherSICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007
CountryJapan
CityTakamatsu
Period9/17/079/20/07

Fingerprint

Visual servoing
Fish
Angular velocity
Neural networks
End effectors
Robots
Trajectories

Keywords

  • Back propagation
  • Gazing-GA
  • Neural network
  • Prediction

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yoshida, T., Minami, M., & Mae, Y. (2007). Fish catching by visual servoing using neural network prediction. In Proceedings of the SICE Annual Conference (pp. 2372-2378). [4421385] https://doi.org/10.1109/SICE.2007.4421385

Fish catching by visual servoing using neural network prediction. / Yoshida, Toshiaki; Minami, Mamoru; Mae, Yasushi.

Proceedings of the SICE Annual Conference. 2007. p. 2372-2378 4421385.

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

Yoshida, T, Minami, M & Mae, Y 2007, Fish catching by visual servoing using neural network prediction. in Proceedings of the SICE Annual Conference., 4421385, pp. 2372-2378, SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007, Takamatsu, Japan, 9/17/07. https://doi.org/10.1109/SICE.2007.4421385
Yoshida T, Minami M, Mae Y. Fish catching by visual servoing using neural network prediction. In Proceedings of the SICE Annual Conference. 2007. p. 2372-2378. 4421385 https://doi.org/10.1109/SICE.2007.4421385
Yoshida, Toshiaki ; Minami, Mamoru ; Mae, Yasushi. / Fish catching by visual servoing using neural network prediction. Proceedings of the SICE Annual Conference. 2007. pp. 2372-2378
@inproceedings{3e2e907cf9d44a7a9e2c9f7e3dfdbcbc,
title = "Fish catching by visual servoing using neural network prediction",
abstract = "This paper presents a method to predict a fish motion by Neural Network (N.N.) with on-line learning when a robot is pursuing fish-catching by a net at hand through hand-eye robot visual servoing. We assume the motion trajectory of a fish swimming in a pool be approximated by a circle with time varying radius and center position. We try to improve prediction accuracy of a fish motion by using N.N. whose inputs are radii and angular velocities in past three control-times and outputs are radius and angular velocity in the following control period. Using radius and angular velocity obtained by circular approximation, we confirmed that the proposed N.N. prediction system can maintain good prediction performances under the proposed on-line learning process.",
keywords = "Back propagation, Gazing-GA, Neural network, Prediction",
author = "Toshiaki Yoshida and Mamoru Minami and Yasushi Mae",
year = "2007",
doi = "10.1109/SICE.2007.4421385",
language = "English",
isbn = "4907764286",
pages = "2372--2378",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Fish catching by visual servoing using neural network prediction

AU - Yoshida, Toshiaki

AU - Minami, Mamoru

AU - Mae, Yasushi

PY - 2007

Y1 - 2007

N2 - This paper presents a method to predict a fish motion by Neural Network (N.N.) with on-line learning when a robot is pursuing fish-catching by a net at hand through hand-eye robot visual servoing. We assume the motion trajectory of a fish swimming in a pool be approximated by a circle with time varying radius and center position. We try to improve prediction accuracy of a fish motion by using N.N. whose inputs are radii and angular velocities in past three control-times and outputs are radius and angular velocity in the following control period. Using radius and angular velocity obtained by circular approximation, we confirmed that the proposed N.N. prediction system can maintain good prediction performances under the proposed on-line learning process.

AB - This paper presents a method to predict a fish motion by Neural Network (N.N.) with on-line learning when a robot is pursuing fish-catching by a net at hand through hand-eye robot visual servoing. We assume the motion trajectory of a fish swimming in a pool be approximated by a circle with time varying radius and center position. We try to improve prediction accuracy of a fish motion by using N.N. whose inputs are radii and angular velocities in past three control-times and outputs are radius and angular velocity in the following control period. Using radius and angular velocity obtained by circular approximation, we confirmed that the proposed N.N. prediction system can maintain good prediction performances under the proposed on-line learning process.

KW - Back propagation

KW - Gazing-GA

KW - Neural network

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=50249092796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249092796&partnerID=8YFLogxK

U2 - 10.1109/SICE.2007.4421385

DO - 10.1109/SICE.2007.4421385

M3 - Conference contribution

AN - SCOPUS:50249092796

SN - 4907764286

SN - 9784907764289

SP - 2372

EP - 2378

BT - Proceedings of the SICE Annual Conference

ER -