Driver drowsiness detection

• US 9,205,844 B2
• Filed: 03/05/2014
• Issued: 12/08/2015
• Est. Priority Date: 03/05/2014
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Yang, Hsin-hsiang, Prakah-Asante, Kwaku O.
• Primary Examiner(s): CAMBY, RICHARD M
• Application Number:
  US14/197,534
• Publication Number:
  US 20150251663A1
• Time in Patent Office: 643 Days
• Field of Search: 701/36
• US Class Current: 1/1
• CPC Class Codes: B60W 2040/0827 due to sleepiness
• CPC Class Codes: B60W 2520/14 Yaw
• CPC Class Codes: B60W 40/08 related to drivers or passengers
• CPC Class Codes: B60W 40/114 Yaw movement
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms

Abstract

Data is collected related to a yaw-rate of a vehicle during a period of time. Based in part on the yaw-rate data, an actual trajectory and an ideal trajectory for the vehicle in the period of time are computed. A deviation of a yaw-rate associated with the actual trajectory is determined from a yaw-rate associated with the ideal trajectory. A variance of the deviation is calculated. An indication is provided of a dangerous driving condition if the variance exceeds a predetermined variance threshold.

Claims

1. A system, comprising a computer in a vehicle, the computer comprising a processor and a memory, wherein the computer is configured to:

collect data related to a yaw-rate of the vehicle during a period of time;

compute, based in part on the yaw-rate data, an actual trajectory and an ideal trajectory for the vehicle in the period of time;

determine a deviation of a yaw-rate associated with the actual trajectory from a yaw-rate associated with the ideal trajectory;

calculate a variance of the deviation; and

provide an indication of a dangerous driving condition if the variance exceeds a predetermined variance threshold.

2. The system of claim 1, wherein the dangerous driving condition is a drowsiness condition.

3. The system of claim 1, wherein the ideal trajectory is computed in part based on velocity data for the vehicle in the period of time.

4. The system of claim 1, wherein the ideal trajectory is computed based on a reference driver model.

5. The system of claim 4, wherein the reference driver model is an optimum preview driver model.

6. The system of claim 1, wherein the computer is further configured to ban-pass filter the deviation before calculating the variance.

7. The system of claim 6, wherein the ban-pass filer is configured according to a power spectral density analysis of yaw-rate deviations.

8. The system of claim 1, wherein the computer is further configured to increment a counter if the variance exceeds the predetermined variance threshold, wherein the indication of the dangerous driving condition is provided only if the counter exceeds a predetermined counter threshold.

9. A method, comprising:

collecting data related to a yaw-rate of a vehicle during a period of time;

computing, based in part on the yaw-rate data, an actual trajectory and an ideal trajectory for the vehicle in the period of time;

determining a deviation of a yaw-rate associated with the actual trajectory from a yaw-rate associated with the ideal trajectory;

calculating a variance of the deviation; and

providing an indication of a dangerous driving condition if the variance exceeds a predetermined variance threshold.

10. The method of claim 9, wherein the dangerous driving condition is a drowsiness condition.

11. The method of claim 9, wherein the ideal trajectory is computed in part based on velocity data for the vehicle in the period of time.

12. The method of claim 9, wherein the ideal trajectory is computed based on a reference driver model.

13. The method of claim 12, wherein the reference driver model is an optimum preview driver model.

14. The method of claim 9, wherein the computer is further configured to ban-pass filter the deviation before calculating the variance.

15. The method of claim 14, wherein the ban-pass filer is configured according to a power spectral density analysis of yaw-rate deviations.

16. The method of claim 9, further comprising incrementing a counter if the variance exceeds the predetermined variance threshold, wherein the indication of the dangerous driving condition is provided only if the counter exceeds a predetermined counter threshold.

17. A non-transitory computer-readable medium having instructions tangibly embodied thereon, the instructions including instructions to:

collect data related to a yaw-rate of the vehicle during a period of time;

compute, based in part on the yaw-rate data, an actual trajectory and an ideal trajectory for the vehicle in the period of time;

determine a deviation of a yaw-rate associated with the actual trajectory from a yaw-rate associated with the ideal trajectory;

calculate a variance of the deviation; and

provide an indication of a dangerous driving condition if the variance exceeds a predetermined variance threshold.

18. The medium of claim 17, wherein the ideal trajectory is computed based on a reference driver model.

19. The medium of claim 17, the instructions further including instructions to ban-pass filter the deviation before calculating the variance.

20. The medium of claim 19, wherein the ban-pass filer is configured according to a power spectral density analysis of yaw-rate deviations.