Title :
Neural networks in feedforward control of a robot arm driven by antagonistically coupled drives
Author :
Milosavljevic, P. ; Bascarevic, N. ; Jovanovic, K. ; Kvascev, G.
Author_Institution :
Fac. of Electr. Eng., Univ. of Belgrade, Belgrade, Serbia
Abstract :
The paper deals with a rapidly growing trend in robotics - anthropomimetics. Following a human paragon, bio-inspired control of the robot arm is presented using artificial neural networks. This work demonstrates results achieved by feedforward control comparing feedforward backpropagation networks and radial bases networks. Use of radial bases network prevails as an efficient tool to evade the exact mathematical modeling and conventional control of the complex mechanical system that is highly nonlinear and includes passive compliance.
Keywords :
backpropagation; compliance control; manipulators; neurocontrollers; nonlinear control systems; radial basis function networks; antagonistically coupled drive; anthropomimetics; artificial neural network; bio-inspired control; complex mechanical system; feedforward backpropagation network; feedforward control; highly nonlinear system; human paragon; mathematical modeling; passive compliance; radial bases network; robot arm; robotics; Artificial neural networks; Elbow; Feedforward neural networks; Joints; Robots; Training; antagonistic drives; humanoid robot; radial basis networks; robot control;
Conference_Titel :
Neural Network Applications in Electrical Engineering (NEUREL), 2012 11th Symposium on
Conference_Location :
Belgrade
Print_ISBN :
978-1-4673-1569-2
DOI :
10.1109/NEUREL.2012.6419967
