Cellular neural networks and biologically inspired motion control

Paolo Arena; Luigi Fortuna

doi:10.1117/12.417229

12 February 2001 Cellular neural networks and biologically inspired motion control

Paolo Arena, Luigi Fortuna

Proceedings Volume 4190, Optomechatronic Systems; (2001) https://doi.org/10.1117/12.417229
Event: Intelligent Systems and Smart Manufacturing, 2000, Boston, MA, United States

Abstract

12 The main purpose of this paper is to present the Cellular Neural Network (CNN) Paradigm as a powerful strategy to design and to implement in hardware efficient locomotion control techniques. A gallery of biologically inspired walking robots are presented. Moreover, the availability of efficient distributed control structures needs a sensing capability of the same efficiency. Therefore the sensing stage is performed by using once again the CNN paradigm, but used as fast image processors. The strategy is supported by the fact that CNN devices with on-chip optical sensors are currently being tested and will be soon available. In such a way, images are acquired by a video camera with a CNN image processing device, able to extract the key features. These ones represent the `command' to take on the right locomotion pattern. Since all the methodology is realized by using analog processors, the whole strategy represents a real breakthrough in the smart sensing and control field.

Citation Download Citation

Paolo Arena and Luigi Fortuna "Cellular neural networks and biologically inspired motion control", Proc. SPIE 4190, Optomechatronic Systems, (12 February 2001); https://doi.org/10.1117/12.417229

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