In order to improve the performance of the lower limb exoskeleton robot, the lower limb exoskeleton is more suitable for the real human motion trajectory, a lower limb motion trajectory prediction method based on ARIMA(Autoregressive Integrated Moving Average) model is proposed. The method uses real human motion data as the original data set, selects appropriate model parameters and verifies the rationality of the model, the final experimental results show that the gait trajectory predicted by this method is basically consistent with the actual trajectory, and the prediction error does not exceed 2°.