Shotaro Yoshinaga, Sozo Inoue,
The lodging and food service industries, including lunch preparation, have a serious labor shortage compared to other industries. In addition, production automation has not been fully introduced. At present, many researches have been conducted for the purpose of collaborative work between humans and robots, but there are few examples of predicting and applying human complex behaviors. In this paper, we predict the movement after 1 second from complex behavior data, and evaluate the residual based on the difference in marker position. For comparison as machine learning, ARIMA, which is often used in time series analysis, is used for the prediction model.