Self-adaptive output tracking with applications to active binocular tracking

Sisil Kumarawadu, Keigo Watanabe, Kazuo Kiguchi, Kiyotaka Izumi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this article we present a neurally-inspired self-adaptive active binocular tracking scheme and an efficient mathematical model for online computation of desired binocular-head trajectories. The self-adaptive neural network (NN) model is general and can be adopted in output tracking schemes of any partly known robotic systems. The tracking scheme ingeniously combines the conventional Resolved Velocity Control (RVC) technique and an adaptive compensating NN model constructed using SoftMax basis functions as nonlinear activation function. Desired trajectories to the servo controller are computed online by the use of a suitable linear kinematics mathematical model of the system. Online weight tuning algorithm guarantees tracking with small errors and error rates as well as bounded NN weights.

Original languageEnglish
Pages (from-to)129-147
Number of pages19
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume36
Issue number2
DOIs
Publication statusPublished - Feb 2003
Externally publishedYes

Fingerprint

Binoculars
Neural networks
Trajectories
Mathematical models
Velocity control
Kinematics
Robotics
Tuning
Chemical activation
Controllers

Keywords

  • Active vision
  • Adaptive tracking
  • Neural networks
  • Robotic systems
  • SoftMax function

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Self-adaptive output tracking with applications to active binocular tracking. / Kumarawadu, Sisil; Watanabe, Keigo; Kiguchi, Kazuo; Izumi, Kiyotaka.

In: Journal of Intelligent and Robotic Systems: Theory and Applications, Vol. 36, No. 2, 02.2003, p. 129-147.

Research output: Contribution to journalArticle

@article{4ea8b3d1d1f14ec6b4b57b79ceee0eb0,
title = "Self-adaptive output tracking with applications to active binocular tracking",
abstract = "In this article we present a neurally-inspired self-adaptive active binocular tracking scheme and an efficient mathematical model for online computation of desired binocular-head trajectories. The self-adaptive neural network (NN) model is general and can be adopted in output tracking schemes of any partly known robotic systems. The tracking scheme ingeniously combines the conventional Resolved Velocity Control (RVC) technique and an adaptive compensating NN model constructed using SoftMax basis functions as nonlinear activation function. Desired trajectories to the servo controller are computed online by the use of a suitable linear kinematics mathematical model of the system. Online weight tuning algorithm guarantees tracking with small errors and error rates as well as bounded NN weights.",
keywords = "Active vision, Adaptive tracking, Neural networks, Robotic systems, SoftMax function",
author = "Sisil Kumarawadu and Keigo Watanabe and Kazuo Kiguchi and Kiyotaka Izumi",
year = "2003",
month = "2",
doi = "10.1023/A:1022620623402",
language = "English",
volume = "36",
pages = "129--147",
journal = "Journal of Intelligent and Robotic Systems: Theory and Applications",
issn = "0921-0296",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Self-adaptive output tracking with applications to active binocular tracking

AU - Kumarawadu, Sisil

AU - Watanabe, Keigo

AU - Kiguchi, Kazuo

AU - Izumi, Kiyotaka

PY - 2003/2

Y1 - 2003/2

N2 - In this article we present a neurally-inspired self-adaptive active binocular tracking scheme and an efficient mathematical model for online computation of desired binocular-head trajectories. The self-adaptive neural network (NN) model is general and can be adopted in output tracking schemes of any partly known robotic systems. The tracking scheme ingeniously combines the conventional Resolved Velocity Control (RVC) technique and an adaptive compensating NN model constructed using SoftMax basis functions as nonlinear activation function. Desired trajectories to the servo controller are computed online by the use of a suitable linear kinematics mathematical model of the system. Online weight tuning algorithm guarantees tracking with small errors and error rates as well as bounded NN weights.

AB - In this article we present a neurally-inspired self-adaptive active binocular tracking scheme and an efficient mathematical model for online computation of desired binocular-head trajectories. The self-adaptive neural network (NN) model is general and can be adopted in output tracking schemes of any partly known robotic systems. The tracking scheme ingeniously combines the conventional Resolved Velocity Control (RVC) technique and an adaptive compensating NN model constructed using SoftMax basis functions as nonlinear activation function. Desired trajectories to the servo controller are computed online by the use of a suitable linear kinematics mathematical model of the system. Online weight tuning algorithm guarantees tracking with small errors and error rates as well as bounded NN weights.

KW - Active vision

KW - Adaptive tracking

KW - Neural networks

KW - Robotic systems

KW - SoftMax function

UR - http://www.scopus.com/inward/record.url?scp=0037306129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037306129&partnerID=8YFLogxK

U2 - 10.1023/A:1022620623402

DO - 10.1023/A:1022620623402

M3 - Article

AN - SCOPUS:0037306129

VL - 36

SP - 129

EP - 147

JO - Journal of Intelligent and Robotic Systems: Theory and Applications

JF - Journal of Intelligent and Robotic Systems: Theory and Applications

SN - 0921-0296

IS - 2

ER -