Title :
A neural-fuzzy walking control of an autonomous biped robot
Author :
Ferreira, Joao P. ; Amaral, Tito G. ; Pires, Vitor Fernao ; Crisostomo, Manuel M. ; Coimbra, Paulo
fDate :
June 28 2004-July 1 2004
Abstract :
In this paper, an adaptive neural-fuzzy walking control of an autonomous biped robot is proposed. This control system uses a feed forward neural network based on nonlinear regression. The general regression neural network is used to construct the base of an adaptive neuro-fuzzy system. The neural network uses an iterative grid partition method for the initial structure identification of the controller parameters. Comparison results are done between the proposed method and the ANFIS tool provided in the fuzzy MATLAB toolbox. The robot´s control system uses an inverted pendulum to balance of the gaits. The effectiveness of the proposed control system is demonstrated by simulation and experimental tests
Keywords :
adaptive control; adaptive systems; digital simulation; feedforward neural nets; fuzzy control; fuzzy neural nets; fuzzy reasoning; fuzzy systems; iterative methods; legged locomotion; motion control; neurocontrollers; nonlinear control systems; pendulums; regression analysis; ANFIS tool; adaptive neurofuzzy system; adaptive neurofuzzy walking control; autonomous biped robot; controller parameters; feedforward neural network; fuzzy MATLAB toolbox; fuzzy reasoning; gait balance synthesis; inverted pendulum; iterative grid partition method; nonlinear regression; robot control system; structure identification; Adaptive control; Adaptive systems; Control systems; Feedforward neural networks; Feeds; Fuzzy neural networks; Legged locomotion; Neural networks; Nonlinear control systems; Programmable control;
Conference_Titel :
Automation Congress, 2004. Proceedings. World
Conference_Location :
Seville
Print_ISBN :
1-889335-21-5
