Title :
Simulation control of a biped robot with Support Vector Regression
Author :
Ferreira, João P. ; Crisostomo, Manuel ; Coimbra, A. Paulo ; Ribeiro, Bernardete
Author_Institution :
Coimbra Super. Inst. of Eng., Coimbra
Abstract :
This paper describes the control of an autonomous biped robot that uses the Support Vector Regression (SVR) method for its longitudinal balance. This SVR uses the Zero Moment Point (ZMP) position and its variation as input and the longitudinal correction of the robot´s body is obtained as the output. The SVR was trained based on simulation data that was confirmed with the real robot. This method showed to be faster (with similar accuracy) than a recurrent network or a neuro-fuzzy control of the biped balance.
Keywords :
legged locomotion; position control; regression analysis; support vector machines; autonomous biped robot simulation control; support vector regression; zero moment point position; Computational modeling; Computer simulation; Control systems; Humans; Kinematics; Mathematical model; Nonlinear control systems; Robot control; Stability; Torso; SVR; ZVP; biped robot; stability;
Conference_Titel :
Intelligent Signal Processing, 2007. WISP 2007. IEEE International Symposium on
Conference_Location :
Alcala de Henares
Print_ISBN :
978-1-4244-0829-0
Electronic_ISBN :
978-1-4244-0830-6
DOI :
10.1109/WISP.2007.4447538
