DocumentCode :
1317318
Title :
Feedback error learning neural network for trans-femoral prosthesis
Author :
Kalanovic, Vojislav D. ; Popovic, Dejan ; Skaug, Nils T.
Author_Institution :
Dept. of Mech. Eng., South Dakota Sch. of Mines & Technol., Rapid City, SD, USA
Volume :
8
Issue :
1
fYear :
2000
fDate :
3/1/2000 12:00:00 AM
Firstpage :
71
Lastpage :
80
Abstract :
Feedback-error learning (FEL) neural network was developed for control of a powered trans-femoral prosthesis. Nonlinearities and time-variations of the dynamics of the plant, in addition to redundancy and dynamic uncertainty during the double support phase of walking, makes conventional control methods very difficult to use. Rule-based control, which uses a knowledge base determined by machine learning and finite automata method is limited since it does not respond well to perturbations and environmental changes. FEL can be regarded as a hybrid control, because it combines nonparametric identification with parametric modeling and control. This paper presents simulation of a powered trans-femoral prosthesis controlled by a FEL neural network. Results suggest that FEL can be used to identify inverse dynamics of an arbitrary trans-femoral prosthesis during simple single joint movements (e.g., sinusoidal oscillations). The identified inverse dynamics then allows the tracking of an arbitrary trajectory such as a desired walking pattern within a multijoint structure. Simulation shows that the identified controller responds correctly when the leg motion is exposed to a perturbation such as a frequent change of the ground reaction force or the hip joint torque generated by the user. FEL eliminates the need for precise, tedious, and complex identification of model parameters
Keywords :
artificial limbs; biocontrol; feedback; learning (artificial intelligence); neural nets; arbitrary trajectory tracking; desired walking pattern; feedback error learning neural network; finite automata method; ground reaction force; hip joint torque; hybrid control; inverse dynamics identification; leg motion; machine learning; model parameters identification; nonparametric identification; parametric modeling; powered trans-femoral prosthesis control; simple single joint movements; sinusoidal oscillations; Automatic control; Control nonlinearities; Learning automata; Legged locomotion; Machine learning; Neural networks; Neural prosthesis; Neurofeedback; Redundancy; Uncertainty;
fLanguage :
English
Journal_Title :
Rehabilitation Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
1063-6528
Type :
jour
DOI :
10.1109/86.830951
Filename :
830951
Link To Document :
بازگشت