Automotive occupant sensor system and method of operation by sensor fusion

• US 6,026,340 A
• Filed: 09/30/1998
• Issued: 02/15/2000
• Est. Priority Date: 09/30/1998
• Status: Expired due to Term

• Current Assignee: Robert Bosch Corporation (Robert Bosch GmbH)
• Original Assignee: Robert Bosch Corporation (Robert Bosch GmbH)
• Inventors: Corrado, Anthony P., Decker, Stephen W., Benbow, Paul K.
• Primary Examiner(s): Cuchlinski, Jr., William A.
• Assistant Examiner(s): PIPALA, EDWARD J
• Application Number:
  US09/164,404
• Time in Patent Office: 503 Days
• Field of Search: 701/45, 701/47, 280/734, 280/735, 180/271
• US Class Current: 701/47
• CPC Class Codes: B60N 2/002 Seats provided with an occupancy detection means mounted therein or thereon detection means responsive to presence or absence of children B60N2/266
• CPC Class Codes: B60R 21/01534 using electromagneticwaves, e.g. infrared
• CPC Class Codes: B60R 21/01536 using ultrasonic waves
• CPC Class Codes: B60R 25/1004 Alarm systems characterised by the type of sensor, e.g. current sensing means using door lock sensors B60R25/1001

Abstract

A system for sensing the presence, position and type classification of an occupant in a passenger seat of a vehicle, as well as for sensing the presence of a rear-facing child seat therein, for use in controlling a related air bag activator control system to enable, disable or control inflation rate or amount of inflation of an air bag. The sensor system employs sensor fusion, a process of combining information provided by two or more sensors (24, 26), each of which "sees" the world in a unique sense. In a preferred embodiment, infrared sensor inputs (78) and ultrasonic sensor inputs (79) are combined in a microprocessor by a sensor fusion algorithm (80) to produce an occupancy state output signal (85) to the air bag controller.

Claims

1. An automotive occupancy state history database assembly comprising:

(a) memory media having data encoded thereon in computer useable form; and

(b) said data comprising a plurality of data sets characteristic of aspects of known occupancy states representing a plurality of features extracted from a plurality of raw sensor data signals from a plurality of different empty and preselected known occupant type and occupant position combinations.

2. An article of manufacture comprising:

(a) a computer useable medium having computer readable code means embodied thereon; and

(b) said code means comprising a plurality of features extracted from a plurality of raw automotive occupancy sensor data signals from a plurality of different empty and preselected known occupant type and occupant position combinations.

3. A computer program product comprising:

(a) a computer useable medium having computer readable program code means embodied thereon for determining occupancy states of an automotive passenger seat and producing an output signal for an airbag control system for certain preselected occupancy scenarios; and

(b) said computer readable program code means in said medium comprising computer readable program code means for causing a computer to;

(i) effect comparison of occupancy state values to a matrix of stored occupancy state confidence levels;

(ii) determine if the occupancy state corresponds to a preselected occupancy state criteria; and

(iii) output a signal upon correspondence being determined.

4. A computer program as in claim 3 wherein said code means causes said computer to effect;

(a) extraction of features from raw sensor signals;

(b) fusion of features; and

(c) determination values associated with characteristics of the occupancy state.

5. A computer program as in claim 4 wherein said code means causes said computer to effect determination of an occupancy state at high confidence level by neural net evaluation of said characteristic values.

6. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for determining the occupancy states of an automotive passenger seat disposed in a vehicle space from signals from at least two types of sensors which signals are characteristic of said space;

said method steps comprising;

(a) processing said signals to generate a plurality of signal features;

(b) combining selected ones of said signal features with other signal features or raw signals to obtain a plurality of fused features;

(c) comparing at least some of said signal features or said fused features with a stored set of weighted confidence values and empirical relationships representing a matrix of occupancy scenarios and a set of state change criteria to determine a feature state value; and

(d) generating a state signal if said feature state value is determined by said comparison to meet a subset of state value criteria.