Title :
A learning dynamics model for robot
Author_Institution :
Res. Inst. of Robot., Shanghai Jiaotong Univ., Shanghai
Abstract :
A new ANN (artificial neural network) structure is proposed to learn dynamics model of robot. The characterizing feature is that some integral units are appended to a recurrent ANN structure, so it can image dynamic process commendably. Generalization capacity of the learning dynamics model is discussed, as well as its application in optimization, etc. The effectiveness of the method is confirmed by simulated experiments but based on a real robot.
Keywords :
intelligent robots; learning (artificial intelligence); neurocontrollers; optimisation; artificial neural network; generalization capacity; learning dynamics model; Artificial neural networks; Friction; Intelligent robots; Neural networks; Nonlinear dynamical systems; Nonlinear equations; Robot kinematics; Robotics and automation; Torque; Trajectory; artificial neural network; dynamics model; generalization capacity; optimization;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593062
