skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Application of artificial intelligence to robotic vision

Abstract

A brief introduction to artificial intelligence (AI) and the general vision process is provided. Two samples of AI researchers' work toward general computer vision are given. The first is a model-based vision system while the second is based on results of studies on human vision. The current state of machine vision in industrial robotics is demonstrated using a well known vision algorithm developed at SRI International. A part of a prototype robotic assembly project with vision is sketched to show the application of some AI tools to practical work. 8 references.

Authors:
;
Publication Date:
OSTI Identifier:
5290704
Resource Type:
Book
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; ROBOTS; VISION; ALGORITHMS; ARTIFICIAL INTELLIGENCE; PATTERN RECOGNITION; MATHEMATICAL LOGIC 990200* -- Mathematics & Computers

Citation Formats

Chao, P.S., and Frick, P.A. Application of artificial intelligence to robotic vision. United States: N. p., 1983. Web.
Chao, P.S., & Frick, P.A. Application of artificial intelligence to robotic vision. United States.
Chao, P.S., and Frick, P.A. 1983. "Application of artificial intelligence to robotic vision". United States. doi:.
@article{osti_5290704,
title = {Application of artificial intelligence to robotic vision},
author = {Chao, P.S. and Frick, P.A.},
abstractNote = {A brief introduction to artificial intelligence (AI) and the general vision process is provided. Two samples of AI researchers' work toward general computer vision are given. The first is a model-based vision system while the second is based on results of studies on human vision. The current state of machine vision in industrial robotics is demonstrated using a well known vision algorithm developed at SRI International. A part of a prototype robotic assembly project with vision is sketched to show the application of some AI tools to practical work. 8 references.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 1983,
month = 1
}

Book:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this book.

Save / Share:
  • This book discusses the principles and applications of artificial intelligence. It provides the details on the most prominent languages currently being used to develop artificial intelligence, LISP and Prolog. It is shown how the computer is made to understand knowledge and how it can retrieve and manipulate that knowledge through frames, semantic networks, state space, belief systems, and the LEAP data base. Once the fundamentals are discussed, the author delves deeper, explaining: how computers are able to make logical deductions...methods used to move the computer through a knowledge base...and even shows readers what takes place as a computer attempts tomore » solve problems. A series of programming exercises are also provided that illustrate all the important concepts learned from each chapter.« less
  • This sourcebook provides information on the developments in artificial intelligence originating in Japan. Spanning such innovations as software productivity, natural language processing, CAD, and parallel inference machines, this volume lists leading organizations conducting research or implementing AI systems, describes AI applications being pursued, illustrates current results achieved, and highlights sources reporting progress.
  • One of the central claims of mechanism has been that human beings are nothing more than (very complicated) machines. This claim has been found quite disturbing by some people, and over the years there have been numerous attempts to remove the annoyance by providing a convincing refutation. The most familiar form that such attempts at refutation take is that of an argument purporting to show that humans are possessed of some quality, feature, characteristic, or ability, X, which machines cannot possibly have. The evidence for humans possessing X, on the other hand, is usually empirical: we have merely to lookmore » in order to see that humans have X. The possession of X, then, is supposed to distinguish men from machines. The author believes none of these attempts will ever succeed. He does not, however, argue for this conclusion anywhere in the present work. This is because, he sees no way of proving the quite general statement that there is no such trait X. Instead, he chooses to examine and criticise some ten or twelve specific arguments, each of which advances some particular candidate for X. In each case he finds that the argument in question fails to establish any essential difference between men and machines.« less
  • Recent research results in the area of parallel algorithms for problem solving, search, natural language parsing, and computer vision, are brought together in this book. The research reported demonstrates that substantial parallelism can be exploited in various machine intelligence and vision problems. Extensive experimental studies are presented that will help the reader in assessing the usefulness of an approach to a specific problem.
  • Flexible operation of a robot in an uncalibrated environment requires the ability to recover unknown or partially known parameters of the workspace through sensing. Of the sensors available to a robotic agent, visual sensors provide information that is richer and more complete than other sensors. In this paper we present robust techniques for the derivation of depth from feature points on a target`s surface and for the accurate and high-speed tracking of moving targets. We use these techniques in a system that operates with little or no a priori knowledge of the object-related parameters present in the environment. The systemmore » is designed under the Controlled Active Vision framework and robustly determines parameters such as velocity for tracking moving objects and depth maps of objects with unknown depths and surface structure. Such determination of extrinsic environmental parameters is essential for performing higher level tasks such as inspection, exploration, tracking, grasping, and collision-free motion planning. For both applications, we use the Minnesota Robotic Visual Tracker (a visual sensor mounted on the end-effector of a robotic manipulator combined with a real-time vision system) to automatically select feature points on surfaces, to derive an estimate of the environmental parameter in question, and to supply a control vector based upon these estimates to guide the manipulator.« less