An adaptive self-organizing fuzzy sliding mode controller for a 2-DOF rehabilitation robot actuated by pneumatic muscle actuators

Pneumatic muscle actuators have the highest power/weight ratio and power/volume ratio among actuators of all types. Therefore, they can be used not only in rehabilitation engineering, but also as actuators in robots, including industrial robots and therapy robots. It is difficult to achieve excellent control performance using classical control methods because the compressibility of gas and the nonlinear elasticity of bladder containers cause parameter variations. An adaptive self-organizing fuzzy sliding mode control (ASOFSMC) is developed in this study. Its fuzzy sliding surface can help reduce the number of fuzzy rule. The self-organizing learning mechanism is employed to modify fuzzy rules on-line. The model-matching technique is then adopted to adjust the scaling factors. Finally, the Lyapunov theory is employed to prove the stability of the ASOFSMC. Experimental results show that this control strategy can attain excellent control performance.