Method and apparatus for driver assistance

• US 8,031,063 B2
• Filed: 08/25/2004
• Issued: 10/04/2011
• Est. Priority Date: 09/12/2003
• Status: Expired due to Fees

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Schmitz, Carsten
• Primary Examiner(s): Hunnings; Travis
• Application Number:
  US10/570,977
• Publication Number:
  US 20070115105A1
• Time in Patent Office: 2,596 Days
• Field of Search: 340/438
• US Class Current: 340/439
• CPC Class Codes: B60K 31/047 the memory being digital
• CPC Class Codes: B60T 2201/08 Lane monitoring; Lane Keeping Systems
• CPC Class Codes: B60T 2201/082 using alarm actuation
• CPC Class Codes: B60W 2520/125 Lateral acceleration
• CPC Class Codes: B60W 2520/14 Yaw
• CPC Class Codes: B60W 2540/10 Accelerator pedal position
• CPC Class Codes: B60W 2540/18 Steering angle

Abstract

A method and an apparatus for driver assistance, in which a distinction is made, with the aid of operating variables and a classifier, between an intentional and unintentional lane change by the vehicle.

Claims

1. A method for assisting a driver of a vehicle, the method comprising:

classifying a detected lane change operation by the vehicle, on the basis of operating variables, as to whether the lane change is intentional or unintentional; and

generating an output signal as a function of the classification;

wherein the output signal generated is at least one of a warning and a lane keeping reaction when the lane change is unintentional, wherein the at least one of the warning and the lane keeping reaction is suppressed when the lane change is intentional,

wherein the classification of the lane change is based on operating variables of the vehicle which indicate a behavior of the driver, and

wherein a classification of a lane change to the right is performed using different criteria than a classification of a lane change to the left, including when a turn indicator has not been actuated.

2. The method according to claim 1, wherein one of the operating variables is one of a steering angle and a yaw rate of the vehicle.

3. The method according to claim 1, wherein one of the operating variables is a driver'"'"'s acceleration request, a variable derived from a deflection of an accelerator pedal.

4. The method according to claim 1, wherein one of the operating variables is a vehicle speed.

5. The method according to claim 1, wherein one of the operating variables is an angle between a vehicle track and a boundary of the lane.

6. The method according to claim 1, wherein one of the operating variables is one of a vehicle spacing from an edge marking of the lane and a vehicle lateral acceleration.

7. The method according to claim 1, wherein the classifying as to whether an intentional or unintentional lane change is present is made with the aid of a classifier that includes a neural network.

8. The method according to claim 1, further comprising generating an output variable by a classifier that assumes values between values for a definitely detected intentional lane change and for a definitely detected unintentional lane change.

9. The method according to claim 8, further comprising comparing the output variable of the classifier with an adjustable threshold value on the basis of which a determination is made as to whether an intentional or unintentional lane change is present.

10. The method according to claim 1, wherein the classifying as to whether an intentional or unintentional lane change is present is made on the basis of a classifier in which the operating variables are subjected to criteria on the basis of which the classification is made.

11. The method according to claim 1, wherein at least one of (a) previous values of and (b) a change over time of at least one of the operating variables are taken into account in determining when the classification of an intentional lane change or an unintentional lane change is performed.

12. The method according to claim 1, wherein the criteria on which the classification of intentional lane change and unintentional lane change are based differs from each other when the lane change is to the right side or the left side.

13. An apparatus for assisting a driver of a vehicle, comprising:

at least one evaluation unit for generating an output signal when a lane change operation by the vehicle is detected, the evaluation unit including a classifier for distinguishing on the basis of operating variables between an intentional and unintentional lane change, the evaluation unit generating the output signal as a function of a result of a classification;

wherein the output signal generated is at least one of a warning and a lane keeping reaction when the lane change is unintentional, wherein the at least one of the warning and the lane keeping reaction is suppressed when the lane change is intentional,

wherein the classification of the lane change is based on operating variables of the vehicle which indicate a behavior of the driver, and

wherein a classification of a lane change to the right is performed using different criteria than a classification of a lane change to the left, including when a turn indicator has not been actuated.

14. The apparatus according to claim 13, wherein one of the operating variables is one of a steering angle and a yaw rate of the vehicle.

15. The apparatus according to claim 13, wherein one of the operating variables is a driver'"'"'s acceleration request, a variable derived from a deflection of an accelerator pedal.

16. The apparatus according to claim 13, wherein one of the operating variables is a vehicle speed.

17. The apparatus according to claim 13, wherein one of the operating variables is an angle between a vehicle track and a boundary of the lane.

18. The apparatus according to claim 13, wherein one of the operating variables is one of a vehicle spacing from an edge marking of the lane and a vehicle lateral acceleration.

19. The apparatus according to claim 13, wherein the classifying as to whether an intentional or unintentional lane change is present is made with the aid of the classifier that includes a neural network.

20. The apparatus according to claim 13, wherein an output variable is generated by the classifier that assumes values between values for a definitely detected intentional lane change and for a definitely detected unintentional lane change.

21. The apparatus according to claim 20, wherein the output variable of the classifier is compared with an adjustable threshold value on the basis of which the classification is performed as to whether an intentional or unintentional lane change is present.

22. The apparatus according to claim 13, wherein the classifying as to whether an intentional or unintentional lane change is present is made on the basis of the classifier in which the operating variables are subjected to criteria on the basis of which the classification is made.

23. The apparatus according to claim 13, wherein at least one of (a) previous values of and (b) a change over time of at least one of the operating variables are taken into account the classification of whether there is an intentional lane change or an unintentional lane change.

24. The apparatus according to claim 13, wherein the criteria on which the classification of intentional lane change and unintentional lane change are based differs from each other when the lane change is to the right side or the left side.