Method for controlling output of a classification algorithm

• US 7,525,442 B1
• Filed: 02/27/2006
• Issued: 04/28/2009
• Est. Priority Date: 08/26/2002
• Status: Active Grant

• Current Assignee: Automotive Technologies International Incorporated
• Original Assignee: Automotive Technologies International Incorporated
• Inventors: Breed, David S., Chen, Tie-Qi, Piirainen, Ray
• Primary Examiner(s): Swarthout; Brent
• Application Number:
  US11/364,901
• Time in Patent Office: 1,156 Days
• Field of Search: 340/439, 340/438, 340/425.5, 340/436, 340/667, 340/666, 701/45, 280/735, 280/734, 180/271, 702/127, 738/625.81
• US Class Current: 340/667
• CPC Class Codes: B60R 21/01516 using force or pressure sensing means
• CPC Class Codes: B60R 21/0153 using field detection presence sensors

Abstract

Method for controlling output of a classification algorithm which classifies an occupant of a seat in a vehicle in which a bladder or other type of weight sensor is arranged in a bottom cushion of the seat, data relating to the pressure exerted by the occupant on the bottom cushion is obtained from the weight sensor, the occupant is initially classified, a current classification is output using data from the weight sensor, the occupant is periodically re-classified using data from the weight sensor, and a classification change is allowed only upon obtaining evidence of a new classification which is greater than evidence of the current classification. The classification change may be enabled by determining a substantially consecutive period of time when the re-classification is unchanged and different from the current classification, and enabling the classification change upon when the consecutive period of time is greater than a threshold.

Claims

1. A method for controlling output of a classification algorithm which classifies an occupant of a seat in a vehicle, comprising:

obtaining data about weight of the occupant;

using a processor for classifying the occupant and outputting a current classification using weight data;

conducting multiple re-classifications of the occupant using weight data;

determining a substantially consecutive period of time that the occupant has been classified or re-classified as the current classification;

setting a comparison threshold as the lesser of the consecutive period of time that the occupant has been classified or re-classified as the current re-classification or a predetermined maximum time value;

determining a substantially consecutive period of time that the occupant has been classified differently than the current classification; and

changing the current classification only when the consecutive period of time that the occupant has been classified differently than the current classification is greater than the comparison threshold.

2. The method of claim 1, wherein the determination of the consecutive period of time that the occupant has been classified or re-classified as the current classification is made after each re-classification of the occupant when the re-classification of the occupant is the same as the current classification.

3. The method of claim 1, further comprising resetting the classification by classifying the occupant and outputting the classification, upon detection of an empty seat.

8. The method of claim 1, wherein the step of obtaining data about weight of the occupant comprises arranging a weight sensor in connection with the seat and obtaining data relating to the pressure exerted by the occupant on a bottom cushion of the seat from the weight sensor which is related to the weight of the occupant.

9. The method of claim 8, wherein the step of arranging the weight sensor in connection with the seat comprises arranging a bladder weight sensor in the bottom cushion of the seat.

10. The method of claim 8, wherein the step of arranging the weight sensor in connection with the seat comprises arranging a strain gage weight sensor in connection with the seat.

11. The method of claim 8, further comprising resetting the classification by classifying the occupant and outputting the classification, upon detection of an empty seat as detected by the weight sensor.

12. The method of claim 1, further comprising conducting an initial classification of the occupant based on satisfaction of a condition.

13. The method of claim 1, further comprising conducting an initial classification of the occupant based on detection of closure of a door.

14. The method of claim 1, further comprising:

detecting an empty seat; and

conducting an initial classification of the occupant upon detection of an object in the seat after detection of an empty seat.

15. The method of claim 1, further comprising:

detecting switching on of the vehicle ignition; and

conducting an initial classification of the occupant upon detection of an object in the seat after detection of the switching on of the vehicle ignition.

16. The method of claim 1, further comprising:

providing a sensor to detect switching on of the vehicle ignition; and

conducting an initial classification of the occupant upon detection of an object in the seat after detection of the switching on of the vehicle ignition by the sensor.

17. The method of claim 1, wherein the classifications of the occupant are performed using a trained neural network.

18. The method of claim 1, wherein the classifications of the occupant are performed using a combination neural network or a modular neural network.

19. The method of claim 1, further comprising:

resetting the classification by classifying the occupant and outputting the classification upon detection of a condition selected from a group consisting of an empty seat, opening of a door, ignition of the vehicle, motion of the vehicle and absence of motion of the vehicle.

20. The method of claim 1, further comprising resetting the classification by classifying the occupant and outputting the classification, upon detection of a condition selected from a group consisting of motion of the vehicle and absence of motion of the vehicle.

4. A method for controlling output of a classification algorithm which classifies an occupant of a seat in a vehicle, comprising:

arranging a spatial sensor system to generate a field over a bottom cushion of the seat and in which the occupant is expected to be situated;

obtaining data about the occupant from the spatial sensor system;

using a processor for classifying the occupant and outputting a current classification using data about the occupant from the spatial sensor system;

conducting multiple re-classifications of the occupant using data about the occupant from the spatial sensor system;

determining a substantially consecutive period of time that the occupant has been classified or re-classified as the current classification;

setting a comparison threshold as the lesser of the consecutive period of time that the occupant has been classified or re-classified as the current re-classification or a predetermined maximum time value;

determining a substantially consecutive period of time that the occupant has been classified differently than the current classification; and

changing the current classification only when the consecutive period of time that the occupant has been classified differently than the current classification is greater than the comparison threshold.

5. The method of claim 4, wherein the spatial sensor system includes a spatial sensor selected from a group consisting of a capacitance-based sensor, an electric field-based sensor, a radar or other electromagnetic wave-based sensor, and an ultrasonic-based sensor.

6. The method of claim 4, wherein the determination of the consecutive period of time that the occupant has been classified or re-classified as the current classification is made after each re-classification of the occupant when the re-classification of the occupant is the same as the current classification.

7. The method of claim 4, further comprising resetting the classification by classifying the occupant and outputting the classification, upon detection of an empty seat as detected by the spatial sensor system.

21. A method for controlling output of a classification algorithm which classifies an occupant of a seat in a vehicle, comprising:

using a processor for classifying the occupant and outputting a current classification;

conducting multiple re-classifications of the occupant to obtain a tentative re-classification each time;

after each re-classification in which the tentative re-classification of the occupant is the same as the current classification,

determining a substantially consecutive period of time that the occupant has been classified or re-classified as the current classification;

when the consecutive period of time exceeds a predetermined maximum time value, fixing the consecutive period of time that the occupant has been classified or re-classified as the current classification as the predetermined maximum time value; and

after each re-classification in which the tentative re-classification of the occupant is not the same as the current classification,

determining a substantially consecutive period of time that the occupant has been classified as the tentative re-classification, and

changing the current classification to the tentative re-classification of the occupant only when the consecutive period of time that the occupant has been classified as the tentative re-classification is greater than the consecutive period of time that the occupant has been classified as the current classification.

22. The method of claim 21, wherein the step of classifying the occupant comprises obtaining data about weight of the occupant and classifying the occupant using weight data, the occupant being re-classified using weight data.

23. The method of claim 21, wherein the step of classifying the occupant comprises arranging a spatial sensor system to generate a field over a bottom cushion of the seat and in which the occupant is expected to be situated, obtaining data about the occupant from the spatial sensor system and classifying the occupant using data about the occupant from the spatial sensor system, the occupant being re-classified using data about the occupant from the spatial sensor system.