In this paper, an iterative learning control (ILC) method based on sliding mode technique is proposed for hybrid force/position control of robot manipulators. Different from traditional ILC, the main purpose of the proposed ILC is to learn the dynamic parameters rather than the control signals. The sliding mode technique is applied to enhance the robustness of the proposed ILC method against external disturbances and noise. The switching gain of the sliding mode term is time-varying and learned by ILC such that the chattering is suppressed effectively compared to traditional sliding mode control (SMC). Simulation studies are performed on a two degrees of freedom planar parallel manipulator. Simulation results demonstrate that the proposed method can achieve higher force/position tracking performance than the traditional SMC and ILC.