Search

Pneumatic muscle actuators have the highest power/weight ratio of any actuator and therefore it has a broad application prospect in soft robotics. This paper presents a two degree of freedom (2-DOF) pneumatic muscle actuator that consists of four pneumatic artificial muscles (PAMs) and two rotation joins. However, this pneumatic muscle actuator has highly nonlinear and hysteretic properties (among muscle force, muscle displacement and pressure in the muscle), which lead to difficulty in accurate position control. Pneumatic muscle actuator usually necessitate the use various nonlinear techniques for control in order to improve their performance. The paper contains selection of computational intelligence methods designed for application in pneumatic muscle actuator. There are described and compared MLP neural network and RBF neural network. [ABSTRACT FROM AUTHOR]

The control of the standard pneumatic muscle actuators is provided by increasing the air pressure in the one artificial muscle, while reducing the pressure in the second (antagonist) artificial muscle. The paper contains information about the control and basic properties of the rotary actuator based on pneumatic artificial muscles. It presents equations for the values of the actuator arm displacement depending on an input pressure; it shows the static characteristics of the actuator and the utilization of the muscle contraction. Pneumatic artificial muscles are connected in an antagonistic system through an oval centrally symmetric pulley. Due to the fact that with increasing rotating of actuator arm the torque decrease from the both artificial muscles; the stiffness of the actuator also decreasing in both directions. The proposed method of the present control in this paper has resulted in a small increase of torque of the rotary muscle actuator and thus adequate and symmetric stiffness of actuator. [ABSTRACT FROM AUTHOR]