Aisin Seiki Kabushiki Kaisha

Other

Denso Corporation

Koji Oguri

Shinya Matsunaga

Takashi Kawano

Yoshifumi Kishimoto

Akihiro Imai

An absentminded state determination apparatus includes: a data obtaining element for obtaining a time series data of a physiological characteristic value of a participant, wherein a fluctuation component is overlapped on the time series data, and depends on a state of the participant including normal and absentminded states; a detection element for detecting reflecting portions of the time series data, which reflect on the fluctuation component; a counting element for counting the number of the reflecting portions of the time series data in a determination time period between a determination time and a certain past time; and a determination element for determining according to the number of the reflecting portions at the determination time whether the participant is in the absentminded state. The determination time period has a predetermined time width from the certain past time to the determination time.

Absentminded state determination apparatus

A verification value is calculated for an estimation result. The estimation result is corrected on the basis of the calculated verification value. This allows for output of a highly reliable estimation result. If it is determined that the class to which the state of a driver belongs has transitioned continuously, the estimation result is outputted. If it cannot be determined that the class to which the state of the driver belongs has transitioned continuously, a previous estimation result is outputted instead of the latest estimation result. This allows for output of a highly reliable estimation result.

State estimation device, state estimation method, and program

Disclosed is a state detecting device that detects characteristic quantities regarding the driver that are represented by biological information such as the eyelid opening degree and frequency of heartbeat of the driver, identifies the group to which the state of the driver belongs between a Groupand a Groupinto which multiple classes defined using the activity level of the driver as an indicator are sorted based on the detected characteristic quantities, outputs information including the identification results as output values, and detects the class to which the current state of the driver belongs based on loss values calculated from the output values. From the detected class, to what degree the activity level of the driver is impaired can be detected along with the level.

Growing community of inventors

Handa, Japan

Koji Oguri