Friday 27 May 2011

Wseas Transactions

New Subscription to Wseas Transactions

The following information was submitted:

Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 53-575
Full Name: Yutaka Maeda
Position: Professor
Age: ON
Sex: Male
Address: 3-3-35, Yamate-cho, Suita
Country: JAPAN
Tel:
Tel prefix:
Fax: +81-6-6368-0932
E-mail address: maedayut@kansai-u.ac.jp
Other E-mails:
Title of the Paper: Robot Control Using 2D Visual Information Via Database
Authors as they appear in the Paper: Yutaka Maeda, Shoutaro Matsuda and Kyouhei Hisakawa
Email addresses of all the authors:
Number of paper pages: 10
Abstract: This paper proposes a control scheme for a robot system via a database using two-dimensional(2D) visual images. Generally speaking, when we use visual images by cameras, three-dimensional(3D) calibration for the position information acquisition is necessary. Moreover, we calibrate the 3D camera coordinate and the robot coordinate. However, these processes are complicated. In addition, especially for hand-eye systems, the calibration is required for every movement of the robot. Thus the situation is more difficult. In this work, we propose a calibration-free robot system via a database which gives 3D quantity of deviation for the robot arm from 2D image data by two cameras. We also explain a method to establish and update the database effectively using the simultaneous perturbation optimization method. In order to confirm feasibility and viability, we consider a task to bounce a ping-pong ball continuously using the proposed control scheme. As a result, the hand-eye!
robot arm system with the control scheme can work well without the calibration.
Keywords: 2D visual information, Calibration-free, Hand-eye system, database, Simultaneous perturbation, Tracking control
EXTENSION of the file: .pdf
Special (Invited) Session: Image Processing and 2-D / 3-D Systems
Organizer of the Session: Prof. Richard Choras, Prof. Nikos E. Mastorakis, Prof. Valeri Mladenov
How Did you learn about congress: Image processing, Robot control, 2-D Systems
IP ADDRESS: 158.217.209.43