Vehicle rollover detection and method of anticipating vehicle rollover

• US 7,162,340 B2
• Filed: 01/08/2004
• Issued: 01/09/2007
• Est. Priority Date: 01/08/2004
• Status: Expired due to Fees

• Current Assignee: Delphi Technologies, Inc. (BorgWarner Incorporated)
• Original Assignee: Delphi Technologies, Inc. (BorgWarner Incorporated)
• Inventors: Schiffmann, Jan K., Schubert, Peter J.
• Primary Examiner(s): Jeanglaude; Gertrude A.
• Application Number:
  US10/754,113
• Publication Number:
  US 20050154512A1
• Time in Patent Office: 1,097 Days
• Field of Search: 701/36, 701/38, 701/45, 701/35, 701 65- 66, 701/72, 280/756, 180/252, 180/282, 340/440
• US Class Current: 701/38
• CPC Class Codes: B60G 2800/9124 Roll-over protection systems, e.g. for warning or control
• CPC Class Codes: B60R 2021/0018 Roll-over
• CPC Class Codes: B60R 2021/01313 monitoring the vehicle steering system or the dynamic control system
• CPC Class Codes: B60R 2021/01327 Angular velocity or angular acceleration
• CPC Class Codes: B60R 21/0132 responsive to vehicle motion parameters , e.g. to vehicle longitudinal or transversal deceleration or speed value
• CPC Class Codes: B60R 21/01332 by frequency or waveform analysis
• CPC Class Codes: B60T 2230/03 Overturn, rollover
• CPC Class Codes: B60T 8/17551 determining control parameters related to vehicle stability used in the regulation, e.g. by calculations involving measured or detected parameters
• CPC Class Codes: B60W 2030/043 about the roll axis
• CPC Class Codes: B60W 30/02 Control of vehicle driving stability
• CPC Class Codes: B60W 30/04 related to roll-over prevention

Abstract

A rollover detection apparatus and method are provided for anticipating a potential vehicle rollover event. The apparatus includes an input for receiving a plurality of input signals including sensed parameters of the vehicle. A first memory buffer stores data representative of one or more predetermined driving scenarios that represent possible rollover scenarios. A second memory buffer stores data representative of a history of recent conditions of the vehicle based on the plurality of sensed vehicle parameters. The apparatus further includes a processor for comparing the data representative of a history of recent driving events to the data representative of one or more predetermined driving scenarios. The processor further determines a possible rollover event of the vehicle based on the comparison and generates an output signal indicative thereof.

Claims

1. A rollover detection apparatus for detecting a potential rollover event for a vehicle, said apparatus comprising:

an input for receiving a plurality of sensed input signals;

a processor for deriving time-separated values of at least one variable parameter of the vehicle from the input signals;

a first memory buffer storing at least one first data set representative of a predetermined plurality of time-separated values of the at least one variable parameter of the vehicle known to indicate a high probability of a vehicle rollover event;

a second memory buffer storing a second data set representative of a recently derived plurality of the time-separated values of the at least one variable parameter of the vehicle over a predetermined time duration; and

said processor further comparing the first and second data sets to determine a predetermined degree of data matching therebetween over the predetermined time duration, determining a possible rollover event of the vehicle based on the comparison and generating an output signal indicative thereof.

2. The rollover detection apparatus as defined in claim 1, wherein the input signals comprise acceleration and rate signals.

3. The rollover detection apparatus as defined in claim 2, wherein the input signals further comprise a sensed attitude angle of the vehicle.

4. The rollover detection apparatus as defined in claim 1, wherein the plurality of input signals comprise a plurality of vehicle parameters including vehicle speed and steering angle.

5. The rollover detection apparatus as defined in claim 1, wherein said processor employs a data difference measurement algorithm to compare the first and second data sets to determine a predetermined degree of data matching therebetween.

6. The rollover detection apparatus as defined in claim 1, wherein the processor comprises a Hidden Markov Model to compare the first and second data sets to determine a predetermined degree of data matching therebetween.

7. The rollover detection apparatus as defined in claim 1, wherein the processor comprises a Support Vector Machine for comparing the first and second data sets to determine a predetermined degree of data matching therebetween.

8. A method of anticipating a possible rollover event of a vehicle, said method comprising the steps of:

storing in memory a first data set representative of a predetermined plurality of time-separated values of at least one variable parameter of the vehicle, the first data set known to indicate a high probability of a vehicle rollover event;

receiving a plurality of input signals from which the at least one variable vehicle parameter may be derived and deriving therefrom a plurality of time-separated values of the at least one variable vehicle parameter for the vehicle;

storing in memory a second data set representative of the plurality of time-separated values of the at least one variable vehicle parameter for the vehicle over a predetermined time period derived from the input signals of recent driving events;

comparing the first data set to the second data set to determine if a predetermined degree of data matching exists between the first and second data sets over the predetermined time period;

determining a possible vehicle rollover event based on the comparison; and

generating an output signal indicative of a possible vehicle rollover event.

9. The method as defined in claim 8 wherein the at least one variable vehicle parameter comprises at least one of vehicle acceleration and rate.

10. The method as defined in claim 9, wherein the at least one variable vehicle parameter comprises an attitude angle of the vehicle.

11. The method as defined in claim 8, wherein the input signals comprise vehicle speed and steering angle.

12. The method as defined in claim 8, wherein the step of comparing employs a data difference measurement algorithm to compare the first and second data sets to determine a predetermined degree of data matching therebetween.

13. The method as defined in claim 8, wherein the step of comparing is performed with a Hidden Markov Model.

14. The method as defined in claim 8, wherein the step of comparing is performed with a Support Vector Machine.