Control apparatus, control method, and non-transitory computer readable recording medium

1 . A control apparatus for a vehicle, comprising processing circuitry configured to perform automated driving control of the vehicle by using a machine learning model, wherein

the vehicle is configured to be drivable by an operator, and

the processing circuitry is further configured to execute:

by the machine learning model, calculating a steering control amount, a driving control amount, and a braking control amount;

by the machine learning model, calculating a first confidence score for the steering control amount, a second confidence score for the driving control amount, and a third confidence score for the braking control amount;

calculating a reliability regarding an inference result by the machine learning model while performing the automated driving control based on the first confidence score, the second confidence score, and the third confidence score;

when a first condition indicating that the reliability has decreased is met, performing notification for prompting the operator to check a driving environment of the vehicle; and

when a second condition indicating that the reliability has further decreased in addition to the first condition is met, performing notification for requesting hands-on to the operator.

2 . The control apparatus according to claim 1 , wherein

the first condition is that the reliability is less than a first threshold, and

the second condition is that the reliability is less than a second threshold which is smaller than the first threshold.

3 . The control apparatus according to claim 2 , wherein

the processing circuitry is further configured to execute:

acquiring surrounding environment information of the vehicle;

calculating a complexity of a traffic situation around the vehicle based on the surrounding environment information; and

changing the first threshold or the second threshold depending on the complexity.

4 . The control apparatus according to claim 1 , wherein

the machine learning model includes a recognition model and a planning model, the recognition model recognizing a situation around the vehicle, the planning model generating a target trajectory of the automated driving control,

the reliability includes a first reliability and a second reliability, the first reliability related to the inference result by the recognition model, the second reliability related to the inference result by the planning model,

the first condition is that at least one of the first reliability and the second reliability is less than a predetermined threshold, and

the second condition is that both the first reliability and the second reliability are less than the predetermined threshold.

5 . A control method for a vehicle configured to be drivable by an operator, including:

performing automated driving control of the vehicle by using a machine learning model;

by the machine learning model, calculating a steering control amount, a driving control amount, and a braking control amount;

by the machine learning model, calculating a first confidence score for the steering control amount, a second confidence score for the driving control amount, and a third confidence score for the braking control amount;

calculating a reliability regarding an inference result by the machine learning model while performing the automated driving control based on the first confidence score, the second confidence score, and the third confidence score;

when a first condition indicating that the reliability has decreased is met, performing notification for prompting the operator to check a driving environment of the vehicle; and

when a second condition indicating that the reliability has further decreased in addition to the first condition is met, performing notification for requesting hands-on to the operator.

6 . A non-transitory computer readable recording medium on which a computer program for controlling a vehicle configured to be drivable by an operator is recorded, the computer program, when executed by a computer, causing the computer to execute:

performing automated driving control of the vehicle by using a machine learning model;

by the machine learning model, calculating a steering control amount, a driving control amount, and a braking control amount;

by the machine learning model, calculating a first confidence score for the steering control amount, a second confidence score for the driving control amount, and a third confidence score for the braking control amount;

calculating a reliability regarding an inference result by the machine learning model while performing the automated driving control based on the first confidence score, the second confidence score, and the third confidence score;

when a first condition indicating that the reliability has decreased is met, performing notification for prompting the operator to check a driving environment of the vehicle; and

when a second condition indicating that the reliability has further decreased in addition to the first condition is met, performing notification for requesting hands-on to the operator.