Driving condition-monitoring apparatus for automotive vehicles

• US 5,821,860 A
• Filed: 05/20/1997
• Issued: 10/13/1998
• Est. Priority Date: 05/20/1996
• Status: Expired due to Fees

• Current Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Original Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Inventors: Yokoyama, Shintaro, Kojima, Kouichi
• Primary Examiner(s): Mulien, Jr., Thomas J.
• Assistant Examiner(s): PHAM, TOAN NGOC
• Application Number:
  US08/859,206
• Time in Patent Office: 511 Days
• Field of Search: 340/576, 340/439, 340/517, 340/521, 340/575, 701/41, 701/45, 701/59, 701/65
• US Class Current: 340/576
• CPC Class Codes: B60K 28/066 actuating a signalling device B60K28/063 takes precedence
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms

Abstract

A driving condition-monitoring apparatus for an automotive vehicle monitors a driving condition of a driver of the automotive vehicle. At least one of behavior of the vehicle, a driving operation of the driver, and at least one condition of the driver is detected to thereby generate driving condition-indicative data indicative of the driving condition of the driver. It is determined whether the driving condition of the driver is abnormal, based on the driving condition-indicative data generated. When it is not determined that the driving condition of the driver is abnormal, a degree of normality of the driving condition of the driver is determined by inputting a plurality of pieces of the driving condition-indicative data to a neural network. At least one of warning and control of the vehicle is carried out depending on a result of the determination as to whether the driving condition of the driver is abnormal and the degree of normality of the driving condition of the driver.

Claims

1. A driving condition-monitoring apparatus for an automotive vehicle, for monitoring a driving condition of a driver of said automotive vehicle, the apparatus comprising:

driving condition-detecting means for detecting at least one of behavior of said vehicle, a driving operation of said driver, and at least one condition of said driver to thereby generate driving condition-indicative data indicative of said driving condition of said driver;

first driving condition-determining means for determining whether said driving condition of said driver is abnormal, based on said driving condition-indicative data generated by said driving condition-detecting means;

second driving condition-determining means for determining a degree of normality of said driving condition of said driver, by inputting a plurality of pieces of said driving condition-indicative data to a neural network when said first driving condition-determining means does not determine that said driving condition of said driver is abnormal; and

control means for carrying out at least one of warning and control of said vehicle depending upon a result of the determination by said first driving condition-determining means and said degree of normality of said driving condition of said driver determined by said second driving condition-determining means.

2. A driving condition-monitoring apparatus according to claim 1, wherein said first driving condition-determining means determines whether said driving condition of said driver is abnormal, based on a distribution of said plurality of pieces of said driving condition-indicative data.

3. A driving condition-monitoring apparatus according to claim 1, wherein when said first driving condition-determining means does not determine that said driving condition of said driver is abnormal, said first driving condition-determining means further determines whether said driving condition of said driver is normal, based on said driving condition-indicative data generated by said driving condition-detecting means, said determination of said degree of normality of said driving condition of said driver by said second driving condition-determining means being inhibited when said first driving condition-determining means has determined that said driving condition of said driver is either definitely normal or definitely abnormal.

4. A driving condition-monitoring apparatus according to claim 2, wherein when said first driving condition-determining means does not determine that said driving condition of said driver is abnormal, said first driving condition-determining means further determines whether said driving condition of said driver is normal, based on said driving condition-indicative data generated by said driving condition-detecting means, said determination of said degree of normality of said driving condition of said driver by said second driving condition-determining means being inhibited when said first driving condition-determining means has determined that said driving condition of said driver is either definitely normal or definitely abnormal.

5. A driving condition-monitoring apparatus according to claim 4, wherein said first driving condition-determining means forms pattern data indicative of said distribution of said plurality of pieces of driving condition-indicative data, and compares said pattern data thus formed with predetermined abnormality-indicative pattern data indicative of respective abnormal driving conditions of said driver and predetermined normality-indicative pattern data indicative of respective normal driving conditions of said driver, said first driving condition-determining means determining that said driving condition of said driver is abnormal when said formed pattern data is identical with any of said predetermined abnormality-indicative pattern data, and determining that said driving condition of said driver is normal when said formed pattern data is identical with any of said predetermined normality-indicative pattern data.

6. A driving condition-monitoring apparatus according to claim 1, wherein said second driving condition-determining means calculates a driving condition-indicative parameter by said neural network, based on said driving condition-indicative data and compares said driving condition-indicative parameter with a plurality of reference values to thereby determine which of an abnormal region, an intermediate region, and a normal region said degree of normality of said driving condition of said driver belongs.

7. A driving condition-monitoring apparatus according to claim 6, wherein said second driving condition determining means calculates said driving condition-indicative parameter for comparison with said plurality of reference values by the use of a single neural network.

8. A driving condition-monitoring apparatus according to claim 6, wherein said second driving condition-determining means includes first driving condition-indicative parameter-calculating means for calculating a first driving condition-indicative parameter which represents said driving condition of said driver more accurately when said driving condition of said driver is close to abnormality, based on said driving condition-indicative data by the use of a first neural network, second driving condition-indicative parameter-calculating means for calculating a second driving condition-indicative parameter which represents said driving condition of said driver more accurately when said driving condition of said driver is close to normality, based on said driving condition-indicative data by the use of a second neural network, abnormal region-determining means for comparing said first driving condition-indicative parameter with an abnormality-determining reference value to determine whether said degree of normality of said driving condition of said driver belongs to said abnormal region, and normal region-determining means for comparing said second driving condition-indicative parameter with a normality-determining reference value to determine whether said degree of normality of said driving condition of said driver belongs to said normal region.

9. A driving condition-monitoring apparatus according to claim 8, wherein when said normal region-determining means does not determine that said degree of normality of said driving condition of said driver belongs to said normal region, said second driving condition-determining means determines whether said degree of normality of said driving condition of said driver is in a portion of said intermediate region close to said abnormal region or a portion of said intermediate region close to said normal region, based on said first driving condition-indicative parameter, said second driving condition-indicative parameter, and a predetermined reference for determining said intermediate region.

10. A driving condition-monitoring apparatus according to claim 1, wherein said driving condition-detecting means includes means for calculating meandering amount data representative of an amount of meandering of said vehicle as said driving condition-indicative data.

11. A driving condition-monitoring apparatus according to claim 10, wherein said driving condition-detecting means includes behavior amount-detecting means for detecting a behavior amount of said vehicle related to a yawing motion of said vehicle or a lateral motion of said vehicle, vehicle speed-detecting means for detecting traveling speed of said vehicle, behavior reference value-setting means for setting a behavior reference value based on changes in said behavior amount, and lateral deviation behavior amount-calculating means for calculating a lateral deviation behavior amount of said vehicle, based on said behavior amount, said traveling speed of said vehicle, and said behavior reference value.

12. A driving condition-monitoring apparatus according to claim 11, wherein said driving condition-detecting means calculates a time-integrated value of an absolute value of said lateral deviation behavior amount of said vehicle as said meandering amount data.

13. A driving condition-monitoring apparatus according to claim 11, wherein said driving condition-detecting means calculates a standard deviation of said lateral deviation behavior amount as said meandering amount data.

14. A driving condition-monitoring apparatus according to claim 11, wherein said driving condition-detecting means calculates a difference between a maximum value of said lateral deviation behavior amount and a minimum value of said lateral deviation behavior amount over a predetermined time period, as said meandering amount data.