Vehicle occupant weight classification system

• US 20030093249A1
• Filed: 12/17/2002
• Published: 05/15/2003
• Est. Priority Date: 07/12/2000
• Status: Active Grant

• Current Assignee: Continental Automotive GmbH (Continental AG)
• Original Assignee: Andreas Knueppel, Gerald Schicker, Gerd Winkler
• Inventors: Winkler, Gerd, Schicker, Gerald, Knueppel, Andreas
• Granted Patent: US 6,845,339 B2
• Time in Patent Office: Days
• US Class Current: 702/188
• CPC Class Codes: B60R 21/01516 using force or pressure sensing means
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: Y10T 74/18088 Rack and pinion type
• CPC Class Codes: Y10T 74/1967 Rack and pinion

Abstract

A vehicle occupant classification system categorizes vehicle occupants into various classes such as adult, child, infant, etc. to provide variable control for a vehicle restraint system such as an airbag. The classification system utilizes sensors that are installed in various locations in the vehicle. The sensors are used to generate a three-dimensional profile for the vehicle occupant. Various factors can affect the accuracy of this three-dimensional profile. Fuzzy logic is used to reduce some of the inaccuracies by providing multiple decision levels for various stages of the classification. Inaccuracies are also caused by sensors shifting within the system from their original position. This condition creates offset and the system evaluates this offset and generates a correction factor to provide a more accurate three-dimensional profile. Electrically erasable programmable read-only memory is used to reduce complications and inaccuracies associated with seat occupant weight sensors that have mounting configurations that vary depending upon the vehicle.

Claims

1. A method for classifying vehicle occupants comprising the steps of:

(a) mounting a plurality of sensors within the vehicle;

(b) generating a plurality of occupant measurement signals from the sensors in response to an occupant being present within the vehicle;

(c) generating an original three-dimensional profile based on the occupant measurement signals;

(d) comparing the original three-dimensional profile to an information factor;

(e) applying a correction factor if the original three-dimensional profile varies from the information factor by a pre-determined amount to generate a corrected three-dimensional profile; and

(f) classifying the occupant based on either the original or corrected three-dimensional profile.

2. The method according to claim 1 wherein step (f) include using fuzzy logic to classify the occupant.

3. The method according to claim 1 including the step of using fuzzy logic to generate the original three-dimensional profile, the corrected three-dimensional profile, and occupant classification.

4. The method according to claim 1 wherein step (a) includes mounting a plurality of weight sensors within a vehicle seat, step (b) includes generating a plurality of weight signals in response to a weight being applied to the seat, and step (c) includes generating at least a portion of the original three-dimensional profile based on the weight signals.

5. The method according to claim 4 wherein the information factor includes a virtual sensor matrix defining a predetermined number of virtual weight sensor positions and including the step of mapping the weight signals into the virtual weight sensor positions to determine seat occupant weight as part of the original three-dimensional profile.

6. The method according to claim 5 including applying the correction factor if the number of weight sensors is less than the predetermined number of virtual weight sensor positions.

7. The method according to claim 6 wherein applying the correction factor includes dividing the weight sensors into a plurality of zones with each zone defined as covering a subset of the virtual weight sensor positions, assigning each zone a reference cell for compiling the weight signals from that zone to form a weight zone signal representing data for the subset of the virtual weight sensor positions, mapping each weight zone signal into the virtual sensor matrix such that all virtual weight sensor positions are filled, and determining seat occupant weight from the virtual sensor matrix for use in generating the corrected three-dimensional profile.

8. The method according to claim 7 wherein the subset of virtual weight sensor positions for each zone includes a greater number of sensor positions than the number of sensors assigned to each zone.

9. The method according to claim 8 including using electrically erasable programmable read-only memory for generating the virtual matrix, assigning zones, and mapping signals into the matrix.

10. The method according to claim 1 wherein the original three-dimensional profile is based on an actual position of three-dimensional input values and the information factor includes a defined sensor arrangement and step (d) includes comparing the actual position to the defined sensor arrangement to determine if there is offset.

11. The method according to claim 10 wherein step (e) includes using a measuring function to evaluate the position of the offset and to generate the correction factor to adjust the input values to generate the corrected three-dimensional profile.

12. The method according to claim 11 including using the same system software for all offset values.

13. A system for classifying vehicle occupants including:

a plurality of sensors mounted within a vehicle to generate plurality of occupant measurement signals in response to an occupant being present within the vehicle;

a central processing unit for receiving said signals and generating an original three-dimensional profile based on said signals; and

a memory unit for storing an information factor for comparison to said original three-dimensional profile wherein said central processing unit generates a correction factor if said original three-dimensional profile varies from said information factor by a predetermined amount resulting in generation of a corrected three-dimensional profile and wherein said central processing unit classifies the occupant based on either the original or corrected three-dimensional profile.

14. The system according to claim 13 including an airbag system wherein restraint system deployment is controlled based on the classification of the occupant.

15. The system according to claim 14 wherein said central processing unit uses fuzzy logic.

16. The system according to claim 14 wherein said information factor includes a predefined sensor arrangement and said original three-dimensional profile is based on actual sensor position input values, said actual sensor position input values being compared to said predefined sensor arrangement to determine an offset.

17. The system of claim 16 wherein said central processing unit utilizes a measuring function to determine the amount of offset and to generate the correction factor to adjust the actual sensor position input values for the corrected three-dimensional profile.

18. The system of claim 14 wherein a predetermined number of sensors are mounted within a vehicle seat to generate a plurality of weight signals in response to occupant weight and wherein said information factor includes a virtual sensor matrix defining a predetermined number of virtual weight sensor positions that is greater than the predetermined number of sensors mounted within the seat.

19. The system of claim 18 wherein said central processor unit includes electrically erasable programmable read-only memory for applying said correction factor wherein said electrically erasable programmable read-only memory divides said weight sensors into a plurality of zones, each zone covering a subset of said virtual weight sensor positions, assigns each zone a reference cell for compiling said weight signals from that zone to generate weight zone signals representing data for said respective subset of said virtual weight sensor positions, and maps each weight zone signal into said virtual sensor matrix such that all of said virtual weight sensor positions are filled and wherein said central processing unit determines seat occupant weight based on said virtual sensor matrix to generate said corrected three-dimensional profile.