Assessment is the core and fundament of rehabilitation, which can guide the whole treatment process. In the rehabilitation, doctors or therapists need to assess the function of patients in upper/lower-limb, based on subjective assessment and objective assessment. While it may cause large error and high cost by traditional ways. Therefore, artificial intelligence technology is applied to the field of medical rehabilitation. This review will summarize the application of objective assessment methods which are base on artificial intelligence including not limited, trajectory error feature, joint angels and joint angular velocity, sEMG signal feature. Finally, the review concludes that existing objective methods are generally affected by the scale of data and the number of feature. This review will give instruction for a lager application in rehabilitation field.