Estimation of next human action and its timing based on the human action model considering time series information of the situation

In order to realize a system that supports human actions timely, the system must have a certain model of human actions. Therefore, we propose a modeling method of human actions. In this method, it is supposed that a person changes his action according to the situation around him, and the causality between the situation around a person and the change of a human action is modeled. This causality is expressed by an If-then-Rule style where a human action and the situation around a human are expressed by a discrete event and time series data respectively. Moreover, as the necessary function for human support systems, an estimation method of the next human action and its execution timing is consisted based on the proposed modeling method. The usefulness of the proposed modeling and estimation methods is examined through the estimation experiment of next human action and its execution timing with a radio-controlled vehicle.