Abstract— This paper presents an alternative approach for the control of an antagonistic muscle actuated manipulator. The proposed method uses a neuronal network called NeuraBase to learn the sensor events obtained via a rotary encoder and to control the motor events of two DC motors, to rotate the manipulator. A neuron layer called the controller network links the sensor neuron events to the motor neurons. The proposed NeuraBase network model (NNM) has demonstrated its ability to successfully control the antagonistic muscle manipulator, in the absence of a dynamic model and theoretical control methods. The controller also demonstrated its robustness in the adaptive learning of control with imposed system changes.

Index Terms—neural network, antagonistic muscle, muscle actuator, control

Cite: Robert Hercus, Kit-Yee Wong, and Kim-Fong Ho, "Control of a Muscle Actuated Manipulator using the NeuraBASE Network Model," Jounal of Automation and Control Engineering, Vol. 2, No. 3, pp. 302-309, September, 2014. doi: 10.12720/joace.2.3.302-309