Title :
Learning of inverse-dynamics for SCARA robot
Author :
Ishibashi, Naoyuki ; Maeda, Yutaka
Author_Institution :
Grad. Sch. of Sci. & Eng., Kansai Univ., Suita, Japan
Abstract :
In this paper, we describe a positioning control for a SCARA robot using a recurrent neural network. The simultaneous perturbation optimization method is used for the learning rule of the recurrent neural network. Then the recurrent neural network learns inverse dynamics of the SCARA robot. We present details of the control scheme using the simultaneous perturbation. Moreover, we consider an example for two target positions using an actual SCARA robot. The result is shown.
Keywords :
learning (artificial intelligence); manipulator dynamics; neurocontrollers; perturbation techniques; position control; recurrent neural nets; SCARA robot; inverse-dynamics learning; positioning control; recurrent neural network; robot inverse dynamics; simultaneous perturbation optimization method; Control systems; Joints; Learning systems; Optimization methods; Recurrent neural networks; Service robots; Inverse dynamics; Inverse problem; Neural network; SCARA robot; Simultaneous perturbation;
Conference_Titel :
SICE Annual Conference (SICE), 2011 Proceedings of
Conference_Location :
Tokyo
Print_ISBN :
978-1-4577-0714-8
