On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion

Wei Song, Mamoru Minami

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

3 Citations (Scopus)

Abstract

This paper presents a pose measurement method of a 3D object detected by hand-eye cameras. We propose a motion-feedforward (MFF) method to improve visual recognition dynamics, which become worse by disturbing hand-eye motion during visual servoing of the robot manipulator. The MFF method is used to compensate the fictional target motions in the camera view Induced by the end-effctor's motion, so the pose recognition can be assumed invariant for dynamic hand-eye motion. The effectiveness of the proposed method is confirmed by simulations of object's 3D pose recognition being affected by dynamical oscillations of hand-eye cameras.

Original languageEnglish
Title of host publicationIEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
Pages1047-1052
Number of pages6
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2008 - Xi'an, China
Duration: Aug 2 2008Aug 5 2008

Other

Other2008 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2008
CountryChina
CityXi'an
Period8/2/088/5/08

Fingerprint

Cameras
Visual servoing
End effectors
Manipulators
Robots

ASJC Scopus subject areas

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

Cite this

Song, W., & Minami, M. (2008). On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM (pp. 1047-1052). [4601806] https://doi.org/10.1109/AIM.2008.4601806

On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion. / Song, Wei; Minami, Mamoru.

IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. 2008. p. 1047-1052 4601806.

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

Song, W & Minami, M 2008, On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion. in IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM., 4601806, pp. 1047-1052, 2008 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2008, Xi'an, China, 8/2/08. https://doi.org/10.1109/AIM.2008.4601806
Song W, Minami M. On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. 2008. p. 1047-1052. 4601806 https://doi.org/10.1109/AIM.2008.4601806
Song, Wei ; Minami, Mamoru. / On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion. IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. 2008. pp. 1047-1052
@inproceedings{730e41e93bab427daf70e569269c7d96,
title = "On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion",
abstract = "This paper presents a pose measurement method of a 3D object detected by hand-eye cameras. We propose a motion-feedforward (MFF) method to improve visual recognition dynamics, which become worse by disturbing hand-eye motion during visual servoing of the robot manipulator. The MFF method is used to compensate the fictional target motions in the camera view Induced by the end-effctor's motion, so the pose recognition can be assumed invariant for dynamic hand-eye motion. The effectiveness of the proposed method is confirmed by simulations of object's 3D pose recognition being affected by dynamical oscillations of hand-eye cameras.",
author = "Wei Song and Mamoru Minami",
year = "2008",
doi = "10.1109/AIM.2008.4601806",
language = "English",
isbn = "9781424424955",
pages = "1047--1052",
booktitle = "IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM",

}

TY - GEN

T1 - On-line motion-feedforward pose recognition invariant For dynamic hand-eye motion

AU - Song, Wei

AU - Minami, Mamoru

PY - 2008

Y1 - 2008

N2 - This paper presents a pose measurement method of a 3D object detected by hand-eye cameras. We propose a motion-feedforward (MFF) method to improve visual recognition dynamics, which become worse by disturbing hand-eye motion during visual servoing of the robot manipulator. The MFF method is used to compensate the fictional target motions in the camera view Induced by the end-effctor's motion, so the pose recognition can be assumed invariant for dynamic hand-eye motion. The effectiveness of the proposed method is confirmed by simulations of object's 3D pose recognition being affected by dynamical oscillations of hand-eye cameras.

AB - This paper presents a pose measurement method of a 3D object detected by hand-eye cameras. We propose a motion-feedforward (MFF) method to improve visual recognition dynamics, which become worse by disturbing hand-eye motion during visual servoing of the robot manipulator. The MFF method is used to compensate the fictional target motions in the camera view Induced by the end-effctor's motion, so the pose recognition can be assumed invariant for dynamic hand-eye motion. The effectiveness of the proposed method is confirmed by simulations of object's 3D pose recognition being affected by dynamical oscillations of hand-eye cameras.

UR - http://www.scopus.com/inward/record.url?scp=52449083576&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52449083576&partnerID=8YFLogxK

U2 - 10.1109/AIM.2008.4601806

DO - 10.1109/AIM.2008.4601806

M3 - Conference contribution

SN - 9781424424955

SP - 1047

EP - 1052

BT - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM

ER -