Skip to Content

"A Robotic Eye Controller Based on Cooperative Neural Agents"

Congresses name: 

IJCNN 2010 International Joint Conference on Neural Networks

Place: 

Bracelona

Date: 
July 18-23 2010

 Abstract:
A neural behavior initiating agent (BIA) is proposed to integrate relevant compressed image information coming from
others cooperating and specialized neural agents. Using this arrangement the problem of tracking and recognizing a moving
icon has been solved by partitioning it into three simpler and separated tasks. Neural agents associated to those tasks proved
to be easier to train and show a good general performance. The obtained neural controller can handle spurious images and solve
an acute image related task in a dynamical environment. Under prolonged dead-lock conditions the controller shows traces of
genuine spontaneity. The overall performance has been tested using a pan and tilt camera platform and real images taken from
several objects, showing the good tracking results discussed in the paper.

 

AttachmentSize
A Robotic Eye Controller Based on cooperative Neural Agents.pdf500.78 KB