Browse Prior Art Database

A Computer Vision and Robotics Laboratory

IP.com Disclosure Number: IPCOM000131498D
Original Publication Date: 1982-Jun-01
Included in the Prior Art Database: 2005-Nov-11
Document File: 18 page(s) / 61K

Publishing Venue

Software Patent Institute

Related People

R.A. Jarvis: AUTHOR [+3]

Abstract

Using computer vision to support real-time, intelligent robotic manipulation of objects, an Australian laboratory is experimenting with a variety of equipment and algorithm combinations.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 6% of the total text.

Page 1 of 18

THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.

This record contains textual material that is copyright ©; 1982 by the Institute of Electrical and Electronics Engineers, Inc. All rights reserved. Contact the IEEE Computer Society http://www.computer.org/ (714-821-8380) for copies of the complete work that was the source of this textual material and for all use beyond that as a record from the SPI Database.

A Computer Vision and Robotics Laboratory

R.A. Jarvis,

Australian National University

Using computer vision to support real-time, intelligent robotic manipulation of objects, an Australian laboratory is experimenting with a variety of equipment and algorithm combinations.

Space exploration, deep-sea mining, prosthetics, manufacturing -- these are just a few of the potential applications of sensory-based robotics, a field that provides a growing intellectual challenge to researchers interested in developing the specialized equipment and methodologies required to implement these and other application areas. Although other sensing schemes -- force, tactile, and active/passive compliance -- have important roles to play, computer vision appears to offer the richest source of sensory information for intelligent robotic manipulation in the widest range of environments.

Since research into sensory-based robotics is still in its early stages, it is not yet clear just what combination of equipment and algorithms best supports various specific applications; therefore, it is important to provide a laboratory environment that permits a wide variety of experimental setups, each of which can be configured without a major reorganization of the necessary functional components. The laboratory described in this article has been constructed with this versatility requirement in mind. Such a laboratory can be provided at relatively modest expense by taking advantage of inexpensive "offthe- shelf" microprocessor equipment.

Each of the five subsystems shown in Figure I can be viewed both as essential, relatively modular functional components of the computer vision and robotics laboratory, and as parts to be tightly integrated, synchronized, and controlled in the service of some hand/eye coordination task. The role of the image display system may not, at first, be as clear as that of the other subsystems. In a sense, an entirely successful experiment would not involve image display at all since the proper machine interpretation of visual input could simply be demonstrated through correct robotic manipulation of the objects concerned. However, the display of reconstituted raw image data and intermediate, pictorially illustratable results is most important as this information literally provides a window into the processes being developed and debugged by the user. Such display also allows some of the experimental results to be judged for consistency with human interpretation in a comparatively easy manner. Additionally, through the use of...