System and method of detecting drowsy driving

• US 9,008,857 B2
• Filed: 12/06/2013
• Issued: 04/14/2015
• Est. Priority Date: 12/26/2012
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Kim, Jinkwon, Lee, Byoung Joon, Jung, Ho Choul, Kim, Samyong
• Primary Examiner(s): Marc, McDieunel
• Application Number:
  US14/099,240
• Publication Number:
  US 20140180496A1
• Time in Patent Office: 494 Days
• Field of Search: 701/1, 701/36, 340/438, 340/439, 340/575, 340/576, 340/937
• US Class Current: 701/1
• CPC Class Codes: B60R 16/0236 for economical driving
• CPC Class Codes: B60R 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: Y02T 10/84 Data processing systems or methods, management, administration

Abstract

A system and method of detecting drowsy driving that include a controller configured to calculate basic characteristics based on steering torque information and lateral displacement information for every first time and basic thresholds based on the basic characteristics for a second time. In addition, the controller calculates a current characteristic based on the steering torque information and the lateral displacement information for every third time and calculates current thresholds based on the current characteristic for a fourth time. The controller then compares the current thresholds and the current characteristics to determine whether drowsy driving is generated.

Claims

1. A method of detecting drowsy driving, comprising:

calculating, by a controller, basic characteristics based on steering torque information and lateral displacement information for every first time;

calculating, by the controller, basic thresholds based on the basic characteristics for a second time;

calculating, by the controller, a current characteristic based on the steering torque information and the lateral displacement information for every third time;

calculating, by the controller, current thresholds based on the current characteristics for a fourth time; and

comparing, by the controller, the current thresholds and the current characteristics to determine whether drowsy driving is generated,

wherein the basic characteristic and the current characteristic are any one of a limitation of a range of a maximum value and a minimum value of the information, evaluation of an inclination, and analysis of a frequency.

2. The method of claim 1, wherein the first time is the same as the third time.

3. The method of claim 1, wherein the thresholds are calculated using the following equation:

Th_torque=f_current(x_torque)+a*C_torque

Th_offset=f_current(x_offset)+β

*C_offset

wherein, x_torque is a current characteristic of the steering torque, x_offset is a current characteristic of the lateral displacement variance, f_current(x_torque) is a mean value of x_torque, f_current(x_offset) is a mean value of x_offset, a and β

are constant values, and C_torque and C_offset are standard deviation.

4. The method of claim 3, wherein Th_torque and Th_offset of the current thresholds are basic thresholds.

5. The method of claim 1, wherein the second time is 20 minutes.

6. The method of claim 5, wherein the fourth time is 2 minutes.

7. The method of claim 1, wherein the method further includes:

determining, by the controller, the number of occurrences when the current characteristic value for the fourth time is greater than the current threshold.

8. The method of claim 7, wherein the method further includes:

determining, by the controller, drowsy driving when the number of occurrences when the current characteristic value is greater than the current threshold is equal to or greater than 5.

9. A system that detects drowsy driving, comprising:

a controller configured to;

calculate basic characteristics based on steering torque information and lateral displacement information for every first time;

calculate basic thresholds based on the basic characteristics for a second time;

calculate a current characteristic based on the steering torque information and the lateral displacement information for every third time;

calculate current thresholds based on the current characteristics for a fourth time; and

compare the current thresholds and the current characteristics to determine whether drowsy driving is generated,

wherein the basic characteristic and the current characteristic are any one of a limitation of a range of a maximum value and a minimum value of the information, evaluation of an inclination, and analysis of a frequency.

10. The system of claim 9, wherein the first time is the same as the third time.

11. The system of claim 9, wherein the thresholds are calculated using the following equation:

Th_torque=f_current(x_torque)+a*C_torque

Th_offset=f_current(x_offset)+β

*C_offset

wherein, x_torque is a current characteristic of the steering torque, x_offset is a current characteristic of the lateral displacement variance, f_current(x_torque) is a mean value of x_torque, f_current(x_offset) is a mean value of x_offset, a and β

are constant values, and C_torque and C_offset are standard deviation.

12. The system of claim 11, wherein Th_torque and Th_offse of the current thresholds are basic thresholds.

13. The system of claim 9, wherein the controller is further configured to:

determine the number of occurrences when the current characteristic value for the fourth time is greater than the current threshold.

14. The system of claim 13, wherein the controller is further configured to:

determine drowsy driving when the number of occurrences when the current characteristic value is greater than the current threshold is equal to or greater than 5.

15. A non-transitory computer readable medium containing program instructions executed by a controller, the computer readable medium comprising:

program instructions that calculate basic characteristics based on steering torque information and lateral displacement information for every first time;

program instructions that calculate basic thresholds based on the basic characteristics for a second time;

program instructions that calculate a current characteristic based on the steering torque information and the lateral displacement information for every third time;

program instructions that calculate current thresholds based on the current characteristics for a fourth time; and

program instructions that compare the current thresholds and the current characteristics to determine whether drowsy driving is generated,

wherein the basic characteristic and the current characteristic are any one of a limitation of a range of a maximum value and a minimum value of the information, evaluation of an inclination, and analysis of a frequency.

16. The non-transitory computer readable medium of claim 15, wherein the first time is the same as the third time.

17. The non-transitory computer readable medium of claim 15, wherein the thresholds are calculated using the following equation:

Th_torque=f_current(x_torque)+a*C_torque

Th_offset=f_current(x_offset)+β

*C_offset

wherein, x_torque is a current characteristic of the steering torque, x_offset is a current characteristic of the lateral displacement variance, f_current(x_torque) is a mean value of x_torque, f_current(x_offset) is a mean value of x_offset, a and β

are constant values, and C_torque and C_offset are standard deviation.