Back to results
US 12,734,883 B2Granted
Driving skill evaluation method, driving skill evaluation system, and non-transitory recording medium
AssigneeSubaru Corporation
InventorsNoeru Sato, Takeshi Torii
Life of this patent
Estimating the term…
Abstract
A driving skill evaluation method according to one embodiment of the disclosure includes: performing an evaluation process of evaluating a driving skill of a driver of a vehicle, based on traveling data of the vehicle; and performing an advice process of giving advice to the driver, based on an evaluation result of the driving skill of the driver. The advice process includes: giving first advice not based on the traveling data to the driver, when the driving skill evaluated by the evaluation process is a first skill level; and giving second advice based on the traveling data to the driver, when the driving skill evaluated by the evaluation process is a second skill level higher than the first skill level.
Claims6
A driving skill evaluation method comprising:
- performing an evaluation process of evaluating a driving skill of a driver of a vehicle, based on traveling data of the vehicle;
- and
- performing an advice process of giving advice to the driver, based on an evaluation result of the driving skill of the driver,
- wherein the advice process includes:
- giving first advice not based on the traveling data to the driver, when the driving skill evaluated by the evaluation process is a first skill level;
- and
- giving second advice based on the traveling data to the driver, when the driving skill evaluated by the evaluation process is a second skill level higher than the first skill level,
- wherein the second advice includes one of first detailed advice that is advice about acceleration or deceleration of the vehicle, or second detailed advice that is advice about steering of the vehicle,
- wherein the traveling data includes time-series data of a first parameter corresponding to a direction change in a traveling direction of the vehicle, and time-series data of a second parameter corresponding to a speed change in the traveling direction of the vehicle, the first parameter being a yaw angular velocity of the vehicle and the second parameter being a longitudinal acceleration rate in the traveling direction of the vehicle,
- wherein the traveling data includes data regarding when the vehicle is traveling at a curve, and
- wherein the evaluation process includes:
- deciding which of the first detailed advice and the second detailed advice the second advice is to include, based on the traveling data, when the evaluated driving skill is the second skill level;
- detecting multiple curves in a traveling course traveled by the vehicle, based on the time-series data of the first parameter;
- extracting, from the time-series data of the second parameter and the time-series data of the first parameter, data related to multiple curves serving as an evaluation target of driving skill evaluation;
- generating multiple kernel density estimation images related to the multiple curves, based on the extracted data related to the multiple curves;
- calculating an average value of image similarity levels based on the generated multiple kernel density estimation images and multiple kernel density estimation images related to a skilled driver and registered in advance;
- and
- evaluating the driving skill of the driver of the vehicle based on the average value of the image similarity levels.
15 more elements
A driving skill evaluation method comprising:
- performing an evaluation process of evaluating a driving skill of a driver of a vehicle, based on traveling data of the vehicle;
- and
- performing an advice process of giving advice to the driver, based on an evaluation result of the driving skill of the driver,
- wherein the advice process includes:
- giving first advice not based on the traveling data to the driver, when the driving skill evaluated by the evaluation process is a first skill level;
- and
- giving second advice based on the traveling data to the driver, when the driving skill evaluated by the evaluation process is a second skill level higher than the first skill level,
- wherein the traveling data comprises time-series data of a longitudinal acceleration rate in a traveling direction of the vehicle and time-series data of a yaw angular velocity of the vehicle, the traveling data including data regarding when the vehicle is traveling at a curve,
- wherein the evaluation process includes:
- detecting multiple curves in a traveling course traveled by the vehicle, based on the time-series data of the yaw angular velocity of the vehicle;
- extracting, from the time-series data of the longitudinal acceleration rate and the time-series data of the yaw angular velocity, data related to multiple curves serving as an evaluation target of driving skill evaluation;
- generating multiple kernel density estimation images related to the multiple curves, based on the extracted data related to the multiple curves;
- and
- evaluating the driving skill of the driver of the vehicle based on an average value of image similarity levels calculated by comparing the generated multiple kernel density estimation images with multiple kernel density estimation images related to a skilled driver and registered in advance.
11 more elements
A driving skill evaluation system comprising:
- a server apparatus including a processor,
- wherein the processor of the server apparatus operates as an evaluation circuit configured to evaluate a driving skill of a driver of a vehicle, based on traveling data of the vehicle, and as an advice circuit configured to give advice to the driver, based on an evaluation result of the driving skill of the driver, wherein
- the advice circuit is configured to:
- give first advice not based on the traveling data to the driver, when the driving skill evaluated by the evaluation circuit is a first skill level;
- and
- give second advice based on the traveling data to the driver, when the driving skill evaluated by the evaluation circuit is a second skill level higher than the first skill level,
- wherein the second advice includes one of first detailed advice that is advice about acceleration or deceleration of the vehicle, or second detailed advice that is advice about steering of the vehicle,
- wherein the traveling data includes time-series data of a first parameter corresponding to a direction change in a traveling direction of the vehicle, and time-series data of a second parameter corresponding to a speed change in the traveling direction of the vehicle, the first parameter being a yaw angular velocity of the vehicle and the second parameter being a longitudinal acceleration rate in the traveling direction of the vehicle,
- wherein the traveling data includes data regarding when the vehicle is traveling at a curve, and
- wherein the evaluation circuit is configured to:
- decide which of the first detailed advice and the second detailed advice the second advice is to include, based on the traveling data, when the driving skill evaluated by the evaluation circuit is the second skill level;
- detect multiple curves in a traveling course traveled by the vehicle, based on the time-series data of the first parameter;
- extract, from the time-series data of the second parameter and the time-series data of the first parameter, data related to multiple curves serving as an evaluation target of driving skill evaluation;
- generate multiple kernel density estimation images related to the multiple curves based on the extracted data related to the multiple curves;
- calculate an average value of image similarity levels based on the generated multiple kernel density estimation images and multiple kernel density estimation images related to a skilled driver and registered in advance;
- and
- evaluate the driving skill of the driver of the vehicle based on the average value of the image similarity levels.
14 more elements
Dependencies are inferred from the claim text.