HAND-EYE COORDINATION THROUGH ENDPOINT CLOSED-LOOP and LEARNED ENDPOINT OPEN-LOOP VISUAL SERVO CONTROL

Chris Gaskett; Aleš Ude; Gordon Cheng

doi:10.1142/S0219843605000430

HAND-EYE COORDINATION THROUGH ENDPOINT CLOSED-LOOP and LEARNED ENDPOINT OPEN-LOOP VISUAL SERVO CONTROL

Chris Gaskett
, Aleš Ude
, Gordon Cheng

James Cook University
ATR Computational Neuroscience Laboratory
JST-ICORP Computational Brain Project

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

We propose a hand-eye coordination system for a humanoid robot that supports bimanual reaching. The system combines endpoint closed-loop and open-loop visual servo control. The closed-loop component moves the eyes, head, arms, and torso, based on the position of the target and the robot's hands, as seen by the robot's head-mounted cameras. The open-loop component uses a motor-motor mapping that is learnt online to support movement when visual cues are not available.

Original language	English
Pages (from-to)	203-224
Number of pages	22
Journal	International Journal of Humanoid Robotics
Volume	2
Issue number	2
DOIs	https://doi.org/10.1142/S0219843605000430
State	Published - 1 Jun 2005
Externally published	Yes

Keywords

Hand-eye coordination
Learning
Self-organizing map
Visual servo control

Access to Document

10.1142/S0219843605000430

Cite this

@article{3f81825eb7314acfa3c45a98a6e89a31,

title = "HAND-EYE COORDINATION THROUGH ENDPOINT CLOSED-LOOP and LEARNED ENDPOINT OPEN-LOOP VISUAL SERVO CONTROL",

abstract = "We propose a hand-eye coordination system for a humanoid robot that supports bimanual reaching. The system combines endpoint closed-loop and open-loop visual servo control. The closed-loop component moves the eyes, head, arms, and torso, based on the position of the target and the robot's hands, as seen by the robot's head-mounted cameras. The open-loop component uses a motor-motor mapping that is learnt online to support movement when visual cues are not available.",

keywords = "Hand-eye coordination, Learning, Self-organizing map, Visual servo control",

author = "Chris Gaskett and Ale{\v s} Ude and Gordon Cheng",

note = "Publisher Copyright: {\textcopyright} 2005 World Scientific Publishing Company.",

year = "2005",

month = jun,

day = "1",

doi = "10.1142/S0219843605000430",

language = "English",

volume = "2",

pages = "203--224",

journal = "International Journal of Humanoid Robotics",

issn = "0219-8436",

publisher = "World Scientific Publishing Co. Pte Ltd",

number = "2",

}

TY - JOUR

T1 - HAND-EYE COORDINATION THROUGH ENDPOINT CLOSED-LOOP and LEARNED ENDPOINT OPEN-LOOP VISUAL SERVO CONTROL

AU - Gaskett, Chris

AU - Ude, Aleš

AU - Cheng, Gordon

PY - 2005/6/1

Y1 - 2005/6/1

N2 - We propose a hand-eye coordination system for a humanoid robot that supports bimanual reaching. The system combines endpoint closed-loop and open-loop visual servo control. The closed-loop component moves the eyes, head, arms, and torso, based on the position of the target and the robot's hands, as seen by the robot's head-mounted cameras. The open-loop component uses a motor-motor mapping that is learnt online to support movement when visual cues are not available.

AB - We propose a hand-eye coordination system for a humanoid robot that supports bimanual reaching. The system combines endpoint closed-loop and open-loop visual servo control. The closed-loop component moves the eyes, head, arms, and torso, based on the position of the target and the robot's hands, as seen by the robot's head-mounted cameras. The open-loop component uses a motor-motor mapping that is learnt online to support movement when visual cues are not available.

KW - Hand-eye coordination

KW - Learning

KW - Self-organizing map

KW - Visual servo control

UR - https://www.scopus.com/pages/publications/51649104141

U2 - 10.1142/S0219843605000430

DO - 10.1142/S0219843605000430

M3 - Article

AN - SCOPUS:51649104141

SN - 0219-8436

VL - 2

SP - 203

EP - 224

JO - International Journal of Humanoid Robotics

JF - International Journal of Humanoid Robotics

IS - 2

ER -

HAND-EYE COORDINATION THROUGH ENDPOINT CLOSED-LOOP and LEARNED ENDPOINT OPEN-LOOP VISUAL SERVO CONTROL

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this