Driver scoring and safe driving notifications
View Patent ↗A method and apparatus may be used in a vehicle to generate a dynamic driver score. The method may include collecting data. The data may be collected at a predetermined interval. The data may include one or more frames. Each frame may correspond to the predetermined interval and may be divided into segments. Each frame may include a first acceleration data and a second acceleration data. The first acceleration data may be associated with an acceleration of a vehicle at a first segment of the frame, and the second acceleration data may be associated with an acceleration of the vehicle at a second segment of the frame. The frames may be grouped using machine learning methods to determine the driver score. The driver score may be used to modify driving behavior.
1. A method for use in a vehicle, the method comprising:
collecting data at a predetermined interval, wherein the data includes a plurality of frames and each frame of the plurality of frames corresponds to the predetermined interval and includes a first acceleration data and a second acceleration data;
assigning each of the plurality of frames to a group by comparing the first acceleration data and the second acceleration data to a predetermined threshold;
determining whether each of the plurality of frames is statistically likely to be an adverse behavior, wherein the determining includes:
analyzing each of the plurality of frames using a plurality of machine learning methods;
determining, for each of the plurality of machine learning methods, a preliminary classification for each of the plurality of frames; and
selecting a final classification for each of the plurality of frames based on a majority of the preliminary classifications for each of the plurality of frames; and
generating a driver score based on the determination.
2. The method of claim 1 , further comprising:
displaying a notification based on the driver score and a current velocity of the vehicle, wherein the notification is an indication to apply a braking mechanism.
3. The method of claim 2 , wherein the notification is displayed on a condition that a distance threshold between the vehicle and another vehicle is met, wherein the distance threshold is based on the driver score and the current velocity of the vehicle.
4. The method of claim 1 , further comprising:
displaying a navigational route based on the driver score.
5. The method of claim 1 , further comprising:
updating each of the plurality of machine learning methods based on the final classification of each of the plurality of frames.
6. The method of claim 1 , wherein on a condition that an acceleration during a frame is greater than a threshold, the adverse behavior is determined as a harsh accelerating (HA) event.
7. The method of claim 1 , wherein on a condition that a deceleration during a frame is greater than a threshold, the adverse behavior is determined as a harsh braking (HB) event.
8. The method of claim 1 , wherein on a condition that an acceleration and a deceleration during a frame is less than a threshold, the frame is determined as a clean frame.
9. The method of claim 1 , wherein each frame of the plurality of frames further includes a first velocity data and a second velocity data, the method further comprising:
assigning each of the plurality of frames to a group by comparing the first velocity data and the second velocity data to a predetermined threshold.
10. A method for use in a vehicle, the method comprising:
collecting data at a predetermined interval, wherein the data includes a plurality of frames and each frame of the plurality of frames corresponds to the predetermined interval and includes a first acceleration data and a second acceleration data;
assigning each of the plurality of frames to a group by comparing the first acceleration data and the second acceleration data to a predetermined threshold;
determining whether each of the plurality of frames is statistically likely to be an adverse behavior by:
analyzing each of the plurality of frames using a plurality of machine learning methods;
determining, for each of the plurality of machine learning methods, a preliminary classification for each of the plurality of frames; and
selecting a final classification for each of the plurality of frames based on a majority of the preliminary classifications for each of the plurality of frames;
generating a driver score based on the determination; and
displaying a notification based on the driver score and a current velocity of the vehicle.
11. The method of claim 10 , wherein the notification is an indication to apply a braking mechanism.
12. The method of claim 10 , wherein the notification is a navigational route based on the driver score.
13. The method of claim 10 , further comprising:
updating each of the plurality of machine learning methods based on the final classification of each of the plurality of frames.
14. The method of claim 10 , wherein the predetermined threshold is 7 mph/s and on a condition that an acceleration during a frame is greater than the predetermined threshold, the adverse behavior is determined as a harsh accelerating (HA) event.
15. The method of claim 10 , wherein the predetermined threshold is 7 mph/s and on a condition that a deceleration during a frame is greater than the predetermined threshold, the adverse behavior is determined as a harsh braking (HB) event.
16. The method of claim 10 , wherein the predetermined threshold is 7 mph/s and on a condition that an acceleration and a deceleration during a frame is less than the predetermined threshold, the frame is determined as a clean frame.
17. A vehicle communication system comprising:
a telematic control unit (TCU) comprising:
a communication unit configured to receive data from a plurality of sensors; and
a processor configured to collect data at a predetermined interval, wherein the data includes a plurality of frames and each frame of the plurality of frames corresponds to the predetermined interval and includes a first acceleration data and a second acceleration data;
the processor configured to assign each of the plurality of frames to a group by comparing the first acceleration data and the second acceleration data to a predetermined threshold;
the processor configured to determine whether each of the plurality of frames is statistically likely to be an adverse behavior, wherein the processor is further configured to:
analyze each of the plurality of frames using a plurality of machine learning methods,
determine, for each of the plurality of machine learning methods, a preliminary classification for each of the plurality of frames, and
select a final classification for each of the plurality of frames based on a majority of the preliminary classifications for each of the plurality of frames; and
the processor configured to generate a driver score based on the determination; and
a display configured to:
receive a notification based on the driver score and a current velocity of the vehicle; and
display the notification.
18. The vehicle communication system of claim 17 , wherein the display is configured to display the notification as an indication to apply a braking mechanism.
19. The vehicle communication system of claim 17 , wherein the display is configured to display the notification as a navigational route based on the driver score.