Artificial Neural-Net Based Intelligent Robotics Control

Yoh-Han Pao; Dejan J. Sobajic

doi:10.1117/12.942801

19 February 1988 Artificial Neural-Net Based Intelligent Robotics Control

Yoh-Han Pao, Dejan J. Sobajic

Proceedings Volume 0848, Intelligent Robots and Computer Vision VI; (1988) https://doi.org/10.1117/12.942801
Event: Advances in Intelligent Robotics Systems, 1987, Cambridge, CA, United States

Abstract

Fast real-time intelligent control of dynamic systems can be implemented with a combination of logic-based (higher level) strategies and automatic reflexive pattern driven responses generated with artificial neural-nets (ANN). In this paper we are concerned with the adaptive control of a robot manipulator with two degrees of freedom. The objective is to move the end effector of a two limbed manipulator towards a target point until the positions of two coincide. The task is to generate the control signals for movement of the arm through the use of ANN. Control algorithm is computationally simple and robust due to the exploitation of highly parallel information processing capabilities of multilayered neural-nets. Feasibility of obstacle avoidance is discussed also. The proposed approach was evaluated with a computer simulation. A feedforward neural-net was used for this purpose. The results are presented and discussed in this paper.

Citation Download Citation

Yoh-Han Pao and Dejan J. Sobajic "Artificial Neural-Net Based Intelligent Robotics Control", Proc. SPIE 0848, Intelligent Robots and Computer Vision VI, (19 February 1988); https://doi.org/10.1117/12.942801

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available