After that, a fuzzy neural network control design with mixed performance was proposed aiming at different requirement to uncertainty, which separately compensate parameter uncertainties and external disturbances of robot system . this method can ensure the robust stability that under a prescribed attenuation level for the external disturbance, and also strengthens compensation to parameter uncertainties . the theory of hybrid force / position control is clear, however, it is difficult to implement 针对实际应用中对不确定的不同要求,又提出了一种具有混合/性能指标的神经网络控制方法,对机器人不确定性(包括参数不确定性和外部扰动)分别进行补偿,保证了系统对外界干扰在给定的干扰衰减度下具有鲁棒稳定性的同时,还增强了系统对参数不确定性的补偿。