Lane departure intention estimation device

A lane departure intention estimation device comprising:

• an estimation section that estimates that a driver of a subject vehicle has no lane departure intention in a case where the driver of the subject vehicle is in a distracted state or a non-awake state;
• and
• a prediction section that uses a learned machine learning model to predict whether or not the driver of the subject vehicle has a lane departure intention based on a time-series signal and a first classification signal in a case where the driver of the subject vehicle is in neither the distracted state nor the non-awake state, the time-series signal including vehicle information that is information regarding the subject vehicle, lane information that is information regarding a lane in which the subject vehicle is traveling, and target information that is information regarding a target present around the subject vehicle, the first classification signal including a first signal indicating that the driver of the subject vehicle is in neither the distracted state nor the non-awake state, wherein
• the learned machine learning model is obtained by learning in which a learning time-series signal and learning data are used, the learning time-series signal including learning vehicle information that is information regarding a learning vehicle, learning lane information that is information regarding a lane in which the learning vehicle is traveling, and learning target information that is information regarding a target present around the learning vehicle, the learning data being a data set of a learning first classification signal and a label, the learning first classification signal indicating that a driver of the learning vehicle is in neither the distracted state nor the non-awake state, the label indicating whether or not the driver of the learning vehicle has a lane departure intention, wherein
• the first classification signal further includes a second signal indicating a line-of-sight direction of the driver of the subject vehicle and a third signal indicating the target at which the driver of the subject vehicle is gazing, and
• the learning first classification signal further includes a fourth signal indicating the line-of-sight direction of the driver of the subject vehicle and a fifth signal indicating the target at which the driver of the subject vehicle is gazing;
• and
• a control section that controls the subject vehicle based on a result of the estimation by the estimation section or a result of the prediction by the prediction section.