We are concerned with the control of a 3-DOF robot arm actuated by pneumatic rubber muscles. The system is highly non-linear and somehow difficult to model therefore resorting to robust control is required. In order to alleviate the effects of nonlinearities and uncertainties, a combined control strategy based on neural network (NN) and the concept of sliding mode control (SMC) is proposed systematically. In this control structure a simple “two-layer” feedforward neural network (NN) with on line adaptive learning laws is used to estimate unknown plant dynamics and chattering phenomenon in conventional SMC is eliminated by incorporated a modified corrective control term. The algorithm is derived from Lyapunov stability analysis, so that both system tracking stability and error convergence can be guaranteed in the closed-loop system. Experimental results are presented and discussed.