Quantification of Contributing Degree to Braking Operation of Driver based on the Hidden Markov Model

摘要

In order to assist cognitive of driver, it is effective for driver to teach the objects that he should recognize in a visual way. However, it is expected that too much information is provided for a driver from the system and it cause him distraction. Therefore, information presentation without exaggeration and without omission is demanded for assistant system. In this paper, it is assumed that the objects which contribute to driver's braking operation should be presented to him. However, these objects changes according to the facing driving situation. Therefore, a selection method of these objects in the appeared objects model is desired. In this paper, a quantification method of contributing degree to braking operation is proposed to select object that system should present. In this method, the degree of contributing to braking operation is calculated based on a driving behavior model. This model express the relationship between the braking operation and time series features of the object that contributes to braking operation. Therefore, in this paper, the modeling method is also proposed.In the experiment, the modeled time series features of the objects that contribute to braking operation was evaluated based on the propose modeling method. Moreover, the calculated degree of contributing to braking operation based on the proposed method was evaluated by using driving simulator. As the results, it was confirmed that high detection accuracy of object that contributes to braking operation was confirmed.