Postural control of a two degree of freedom biped using a simple neural network

Author

Hasan, Samer S. ; Shiavi, Richard G. ; Peterson, Steven W. ; Bonds, A.B.

Author_Institution

Dept. of Biomed. Eng., Vanderbilt Univ., Nashville, TN, USA

Volume

1

fYear

1992

fDate

Oct. 29 1992-Nov. 1 1992

Firstpage

37

Lastpage

38

Abstract

A neural network controller, employing 3 neuron-like adaptive elements, was used to control a planar double-inverted pendulum biped model. The net learned to balance the biped about the vertical equilibrium point and maintain dynamic stability. Simulations show consistent similarities between model dynamics and human postural dynamics, despite the simple controller architecture, and encourage further evaluation using more elaborate models.

Keywords

learning (artificial intelligence); medical computing; medical control systems; neurophysiology; physiological models; 3 neuron-like adaptive elements; human postural dynamics; net learning; neural network controller; planar double-inverted pendulum biped model; postural control; vertical equilibrium point; Adaptation model; Biological system modeling; Neuromuscular;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1992 14th Annual International Conference of the IEEE

Conference_Location

Paris

Print_ISBN

0-7803-0785-2

Electronic_ISBN

0-7803-0816-6

Type

conf

DOI

10.1109/IEMBS.1992.5760845

Filename

5760845