Title :
Modular neurocontrollers for reaching movements
Author :
Urban, J.P. ; Buessler, J.L. ; Gresser, J.
Author_Institution :
TROP Res. Group, Univ. of Mulhouse, France
Abstract :
Robotic controllers take advantage from neural network´s learning capabilities as long as the dimensionality of the problem is kept moderate. This paper illustrates the possibilities offered by the combination of several neural networks to design more complex modular controllers. We propose a bi-directional architecture to derive the learning rules of the modules. The neurocontroller is trained globally, based on the interactions of the system with its environment, as one would do for a single network. The approach is evaluated on a robotic reaching application. The modular decomposition does not affect the controller interface. The computational cost is reduced and the rapid and efficient learning is maintained
Keywords :
adaptive systems; learning (artificial intelligence); motion control; neurocontrollers; robots; bidirectional architecture; dimensionality; learning rules; modular decomposition; modular neurocontrollers; neural network; reaching movements; robotic controllers; Bidirectional control; Cameras; Computational efficiency; Control systems; Data processing; Neural networks; Robot control; Robot sensing systems; Robot vision systems; Visual servoing;
Conference_Titel :
Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4778-1
DOI :
10.1109/ICSMC.1998.728141