Autors: POPESCU,D., SELISTEANU,D., POPESCU,L. Title: Model based Neural Control for a Robotic Leg Keywords: robotic leg, neural control, computed torque control, trajec Abstract: In this paper a comparison of classical and neural control strategies for a robotic leg with two revolute joints is presented. The classical control scheme is based on a computed torque control. Better results are obtained when a model based neural control strategy is implemented. The performances of the implemented control strategies for trajectory tracking are analysed by computer simulation. If a classical controller already controls a robot leg the advantage of proposed structure is that extension to a model based neural controller for performances improvement is easy. References Issue
|
Вид: публикация в национален форум