Title :
Controlling a New Biped Robot Model Since Walking Using Neural Network
Author :
Tabar, Amhad Forouzan ; Khoogar, Ahmad Reza ; Fakharzadegan, Mohammad Javade
Author_Institution :
Malek Ashtar Univ. of Technol., Tehran
Abstract :
In this paper, a new biped model are evaluated and then a stable neural network controller is used to control it. The biped model has slink and 6 degrees of freedom and actuated by plated pneumatic artificial muscle, which have a very high power to weight ratio and an inherent adaptable compliance. This NN controller allow accurate and dynamic following of prescribed trajectories, not simply control using "via" points specified by a teach pendant. It can significantly improve the accuracy requirements by retraining the basic PD/PID loop, but adding an inner adaptive loop that allows the controller to learn unknown parameters such as friction coefficient, thereby improving tracking accuracy. Simulation results show that NN controller tracking performance is much better than PD controller tracking performance.
Keywords :
legged locomotion; neurocontrollers; three-term control; PD-PID loop; adaptive loop; biped robot model; neural network controller; plated pneumatic artificial muscle; walking; Adaptive control; Artificial neural networks; Friction; Legged locomotion; Muscles; Neural networks; PD control; Programmable control; Three-term control; Tracking loops; Bipd robot; Plated Pneumatic Artificial Muscle; neural network;
Conference_Titel :
Integration Technology, 2007. ICIT '07. IEEE International Conference on
Conference_Location :
Shenzhen
Print_ISBN :
1-4244-1092-4
Electronic_ISBN :
1-4244-1092-4
DOI :
10.1109/ICITECHNOLOGY.2007.4290415