In this paper, the adaptive neural network control scheme of coordinated motion between the basepsilas attitude and the armspsila joints of free-floating dual-arm space robot system with uncertain parameters is considered. The controller is developed based on the neural network modeling technique. It need neither linearly parameterize the dynamic equations of system, nor know any actual inertial parameters. In addition, it neither requires the evaluation of inverse dynamical model, nor the time-consuming training process. Furthermore, the robust control can be easily incorporated to suppress the neural network modeling errors. Simulation results based on a planar free-floating dual-arm space robot system verify the feasibility of the proposed adaptive neural network control scheme.