Fish-catching by robot using prediction neural network - Reducing steady-state error to zero

Mamoru Minami, Tongxiao Zhang

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

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 have learned by previous experiments that fish is much smarter than a robot controlled by visual servoing whose escaping strategy is to make a steady state distance error between the net at robot's hand and the fish. To overcome the fish's escaping strategy we propose prediction servoing utilizing estimated future fish position by on-line adjusting N.N.. The effectiveness have been proven through visual servoing and fish catching experiments.

Original languageEnglish
Title of host publicationICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings
Pages5020-5025
Number of pages6
Publication statusPublished - 2009
Externally publishedYes
EventICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009 - Fukuoka, Japan
Duration: Aug 18 2009Aug 21 2009

Other

OtherICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009
CountryJapan
CityFukuoka
Period8/18/098/21/09

Fingerprint

Fish
Robots
Neural networks
Visual servoing
End effectors
Experiments

Keywords

  • Fish-catching
  • Neural network

ASJC Scopus subject areas

  • Information Systems
  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering

Cite this

Minami, M., & Zhang, T. (2009). Fish-catching by robot using prediction neural network - Reducing steady-state error to zero. In ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings (pp. 5020-5025). [5334628]

Fish-catching by robot using prediction neural network - Reducing steady-state error to zero. / Minami, Mamoru; Zhang, Tongxiao.

ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings. 2009. p. 5020-5025 5334628.

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

Minami, M & Zhang, T 2009, Fish-catching by robot using prediction neural network - Reducing steady-state error to zero. in ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings., 5334628, pp. 5020-5025, ICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009, Fukuoka, Japan, 8/18/09.
Minami M, Zhang T. Fish-catching by robot using prediction neural network - Reducing steady-state error to zero. In ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings. 2009. p. 5020-5025. 5334628
Minami, Mamoru ; Zhang, Tongxiao. / Fish-catching by robot using prediction neural network - Reducing steady-state error to zero. ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings. 2009. pp. 5020-5025
@inproceedings{59fea83d07de46a88666d4398470359d,
title = "Fish-catching by robot using prediction neural network - Reducing steady-state error to zero",
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 have learned by previous experiments that fish is much smarter than a robot controlled by visual servoing whose escaping strategy is to make a steady state distance error between the net at robot's hand and the fish. To overcome the fish's escaping strategy we propose prediction servoing utilizing estimated future fish position by on-line adjusting N.N.. The effectiveness have been proven through visual servoing and fish catching experiments.",
keywords = "Fish-catching, Neural network",
author = "Mamoru Minami and Tongxiao Zhang",
year = "2009",
language = "English",
isbn = "9784907764333",
pages = "5020--5025",
booktitle = "ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings",

}

TY - GEN

T1 - Fish-catching by robot using prediction neural network - Reducing steady-state error to zero

AU - Minami, Mamoru

AU - Zhang, Tongxiao

PY - 2009

Y1 - 2009

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 have learned by previous experiments that fish is much smarter than a robot controlled by visual servoing whose escaping strategy is to make a steady state distance error between the net at robot's hand and the fish. To overcome the fish's escaping strategy we propose prediction servoing utilizing estimated future fish position by on-line adjusting N.N.. The effectiveness have been proven through visual servoing and fish catching experiments.

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 have learned by previous experiments that fish is much smarter than a robot controlled by visual servoing whose escaping strategy is to make a steady state distance error between the net at robot's hand and the fish. To overcome the fish's escaping strategy we propose prediction servoing utilizing estimated future fish position by on-line adjusting N.N.. The effectiveness have been proven through visual servoing and fish catching experiments.

KW - Fish-catching

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=77951105933&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951105933&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77951105933

SN - 9784907764333

SP - 5020

EP - 5025

BT - ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings

ER -