Human-machine-interface (HMI) customization based on collision assessments

• US 7,710,248 B2
• Filed: 06/12/2007
• Issued: 05/04/2010
• Est. Priority Date: 06/12/2007
• Status: Active Grant

• Current Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Greene, Daniel H., Reich, James E., Liu, Juan
• Primary Examiner(s): Mehmood, Jennifer
• Application Number:
  US11/818,176
• Publication Number:
  US 20080309468A1
• Time in Patent Office: 1,057 Days
• Field of Search: 340/436, 340/437, 701300-302, 180/271, 180/272
• US Class Current: 340/436
• CPC Class Codes: B60R 2300/302 combining image information with GPS information or vehicle data, e.g. vehicle speed, gyro, steering angle data
• CPC Class Codes: B60R 2300/305 merging camera image with lines or icons
• CPC Class Codes: B60R 2300/307 virtually distinguishing relevant parts of a scene from the background of the scene
• CPC Class Codes: B60R 2300/8033 for pedestrian protection
• CPC Class Codes: B60R 2300/8093 for obstacle warning
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

One embodiment of the present invention provides a system that facilitates collision warning. During operation, the system receives information on one or more predicted collisions and determines a utility of issuing a warning for a predicted collision based on the received information. The system further schedules one or more warnings for the predicted collisions based on the utilities of issuing the warnings.

Claims

1. A method for facilitating collision warning, the method comprising:

receiving information on one or more predicted collisions;

determining a utility of issuing a warning for a predicted collision based on the received information and based on efficacy of the warning and a penalty for distraction caused by the warning; and

scheduling one or more warnings for the predicted collisions based on the determined utility of issuing the warnings.

2. The method of claim 1,

wherein the received information on a predicted collision includes a probability of the collision and an estimated benefit associated with a warning for the collision.

3. The method of claim 2,

wherein the estimated benefit associated with the warning for the collision is a function of the time when the warning is issued.

4. The method of claim 2,

wherein the received information on the predicted collision further includes one or more of:

a collision scenario,

a time of collision,

a location of collision, and

an estimated accuracy of the prediction.

5. The method of claim 1,

wherein determining the utility of issuing the warning comprises computing the following utility function:

$U=P·<br><br>Q·<br><br>B-\left(1-P·<br><br>Q\right)·<br><br>D;<br><br>$

wherein U denotes the utility, P denotes a collision probability, Q denotes the warning efficacy, B denotes a benefit of issuing the warning, and D denotes the penalty for distraction caused by the warning.

6. The method of claim 1,

wherein scheduling the warnings based on the utilities of issuing the warnings comprises:

selecting the warnings for which the utilities are greater than or equal to a predetermined threshold; and

ranking the selected warnings based on their corresponding estimated benefits.

7. The method of claim 1,

wherein the receiving of information on predicted collisions, determining of warning utilities, and scheduling of the warnings are performed at recurring time intervals.

8. The method of claim 1,

wherein the receiving of information, determining of the utility, and scheduling of the warnings are performed by a decision adaptor;

and wherein the method further comprises configuring the decision adaptor based on at least one of;

a warning efficacy,

a penalty for distraction caused by a warning,

a maximum warning rate, and

a rate for repeating the same warning.

9. The method of claim 1,

wherein the receiving of information, determining of the utility, and scheduling of the warnings are performed by a customized decision adaptor;

and wherein the method further comprises modeling a set of characteristics of a human-machine interface (HMI) at the customized decision adaptor.

10. The method of claim 1,

wherein the scheduling of warnings is based on a target rate and/or maximum rate of warnings, whereby an effective spacing can be achieved between two consecutive warnings.

11. A system for facilitating collision warning, the system comprising:

a receiving mechanism configured to receive information on one or more predicted collisions;

a decision mechanism configured to determine a utility of issuing a warning for a predicted collision and based on the received information based on efficacy of the warning and a penalty for distraction caused by the warning; and

a scheduler configured to schedule one or more warnings for the predicted collisions based on the determined utility of issuing the warnings.

12. The system of claim 11,

wherein the received information on a predicted collision includes a probability of the collision and an estimated benefit associated with a warning for the collision.

13. The system of claim 12,

wherein the estimated benefit associated with the warning for the collision is a function of the time when the warning is issued.

14. The system of claim 12,

wherein the received information on the predicted collision further includes one or more of:

a collision scenario,

a time of collision,

a location of collision, and

an estimated accuracy of the prediction.

15. The system of claim 11,

wherein while determining the utility of issuing the warning, the decision mechanism is configured to compute the following utility function:

$U=P·<br><br>Q·<br><br>B-\left(1-P·<br><br>Q\right)·<br><br>D;<br><br>$

wherein U denotes the utility, P denotes a collision probability, Q denotes the warning efficacy, B denotes a benefit of issuing the warning, and D denotes the penalty for distraction caused by the warning.

16. The system of claim 11,

wherein while scheduling the warnings based on the utilities of issuing the warnings, the scheduler is configured to:

select the warnings for which the utilities are greater than or equal to a predetermined threshold; and

rank the selected warnings based on their corresponding estimated benefits.

17. The system of claim 11,

wherein receiving mechanism, the decision mechanism, and the scheduler are configured to receive information on predicted collisions, determine warning utilities, and schedule the warnings, respectively, at recurring time intervals.

18. The system of claim 11,

wherein the receiving mechanism, the decision mechanism, and the scheduler reside in a decision adaptor which is configured based on at least one of:

a warning efficacy,

a penalty for distraction caused by a warning,

a maximum warning rate, and

a rate for repeating the same warning.

19. The system of claim 11,

wherein the receiving mechanism, the decision mechanism, and the scheduler reside in a customized decision adaptor which is configured to model a set of characteristics of an HMI.

20. The system of claim 11,

wherein while scheduling the warnings, the scheduler is configured to schedule the warnings based on a target rate and/or maximum rate of warnings, thereby allowing an effective spacing to be achieved between two consecutive warnings.

21. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for facilitating collision warning, the method comprising:

receiving information on one or more predicted collisions;

determining a utility of issuing a warning for a predicted collision based on the received information and based on efficacy of the warning and a penalty for distraction caused by the warning; and

scheduling one or more warnings for the predicted collisions based on the determined utility of issuing the warnings.

22. The computer-readable storage medium of claim 21,

wherein the received information on a predicted collision includes a probability of the collision and an estimated benefit associated with a warning for the collision.

23. The computer-readable storage medium of claim 22,

wherein the estimated benefit associated with the warning for the collision is a function of the time when the warning is issued.

24. The computer-readable storage medium of claim 22,

wherein the received information on the predicted collision further includes one or more of:

a collision scenario,

a time of collision,

a location of collision, and

an estimated accuracy of the prediction.

25. The computer-readable storage medium of claim 21,

wherein determining the utility of issuing the warning comprises computing the following utility function:

$U=P·<br><br>Q·<br><br>B-\left(1-P·<br><br>Q\right)·<br><br>D;<br><br>$

wherein U denotes the utility, P denotes a collision probability, Q denotes the warning efficacy, B denotes a benefit of issuing the warning, and D denotes the penalty for distraction caused by the warning.

26. The computer-readable storage medium of claim 21,

wherein scheduling the warnings based on the utilities of issuing the warnings comprises:

selecting the warnings for which the utilities are greater than or equal to a predetermined threshold; and

ranking the selected warnings based on their corresponding estimated benefits.

27. The computer-readable storage medium of claim 21,

wherein the receiving of information on predicted collisions, determining of warning utilities, and scheduling of the warnings are performed at recurring time intervals.

28. The computer-readable storage medium of claim 21,

wherein the receiving of information, determining of the utility, and scheduling of the warnings are performed by a decision adaptor;

and wherein the method further comprises configuring the decision adaptor based on at least one of;

a warning efficacy,

a penalty for distraction caused by a warning,

a maximum warning rate, and

a rate for repeating the same warning.

29. The computer-readable storage medium of claim 21,

wherein the receiving of information, determining of the utility, and scheduling of the warnings are performed by a customized decision adaptor;

and wherein the method further comprises modeling a set of characteristics of a human-machine interface (HMI) at the customized decision adaptor.

30. The computer readable storage medium of claim 21,

wherein the scheduling of warnings is based on a target rate or maximum rate of warnings, whereby an effective spacing can be achieved between two consecutive warnings.