DocumentCode :
3297775
Title :
Implementation of an adaptive neural controller for sensory-motor coordination
Author :
Kuperstein, Michael ; Rubinstein, Jorge
Author_Institution :
Neurogen Lab. Inc., Brookline, MA, USA
fYear :
1989
fDate :
0-0 1989
Firstpage :
305
Abstract :
A theory and the prototype of a neural controller called INFANT that learns sensory-motor coordination from its own experience are presented. INFANT adapts unforeseen changes in the geometry of the physical motor system and to the location, orientation, shape, and size of objects. It can learn to accurately grasp an elongated object without any information about the geometry of the physical sensory-motor system. This new neural controller relies on the self-consistency between sensory and motor signals to achieve unsupervised learning. It is designed to be generalized for coordinating any number of sensory inputs with limbs of any number of joints. INFANT is implemented with an image processor, stereo cameras, and a 5 degrees-of-freedom robot arm. Its average grasping accuracy after learning is 3% of the arm´s length in position and 6 degrees in orientation.<>
Keywords :
adaptive control; learning systems; neural nets; robots; virtual machines; 5 degrees-of-freedom robot arm; INFANT; adaptive neural controller; image processor; learning systems; physical motor system; robots; self-consistency; sensory-motor coordination; stereo cameras; unsupervised learning; virtual machines; Adaptive control; Learning systems; Neural networks; Robots; Virtual computers;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
Type :
conf
DOI :
10.1109/IJCNN.1989.118715
Filename :
118715
Link To Document :
بازگشت