Vehicle rollover detection and method of anticipating vehicle rollover

• US 20050154512A1
• Filed: 01/08/2004
• Published: 07/14/2005
• Est. Priority Date: 01/08/2004
• Status: Active Grant

• Current Assignee: Delphi Technologies, Inc. (BorgWarner Incorporated)
• Original Assignee: Delphi Technologies, Inc. (BorgWarner Incorporated)
• Inventors: Schiffmann, Jan K., Schubert, Peter J.
• Granted Patent: US 7,162,340 B2
• Time in Patent Office: Days
• 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 input signals including sensed parameters of the vehicle;

a first memory buffer storing data representative of one or more predetermined driving scenarios that represent possible rollover scenarios;

a second memory buffer storing data representative of a history of recent conditions of the vehicle based on the plurality of sensed vehicle parameters; and

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, said processor further 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 plurality of input signals comprise vehicle dynamics sensed signals generated by dynamics sensors.

3. The rollover detection apparatus as defined in claim 2, wherein the vehicle dynamics sensed signals comprise acceleration and rate signals.

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

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

6. The rollover detection apparatus as defined in claim 1, wherein said processor employs a distance measurement algorithm to compare the data representative of a history of recent driving events to the data representative of one or more predetermined driving scenarios.

7. The rollover detection apparatus as defined in claim 1, wherein the processor comprises a Hidden Markov Model to compare the data representative of a history of recent driving events to the data representative of one or more predetermined driving scenarios.

8. The rollover detection apparatus as defined in claim 1, wherein the processor comprises a Support Vector Machine for comparing the data representative of a history of recent driving events to the data representative of one or more predetermined driving scenarios.

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

storing in memory data representative of one or more predetermined driving scenarios that represent possible vehicle rollover scenarios;

receiving a plurality of vehicle parameters indicative of the driving condition of the vehicle;

storing in memory data representative of a history of recent driving events;

comparing the data representative of a history of recent driving events to the data representative of one or more predetermined driving scenarios;

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

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

10. The method as defined in claim 9 further comprising the step of sensing vehicle dynamics as the plurality of vehicle parameters.

11. The method as defined in claim 10, wherein the step of sensing vehicle dynamics comprises sensing vehicle acceleration and rate.

12. The method as defined in claim 11, wherein the step of sensing vehicle dynamics further comprises sensing an attitude angle of the vehicle.

13. The method as defined in claim 9, wherein the step of receiving a plurality of vehicle parameters comprises vehicle speed and steering angle.

14. The method as defined in claim 9, wherein the step of comparing comprises determining a distance measurement between the data representative of a history of recent driving events and the data representative of one or more predetermined driving scenarios.

15. The method as defined in claim 9, wherein the step of comparing is performed with a Hidden Markov Model.

16. The method as defined in claim 9, wherein the step of comparing is performed with a Support Vector Machine.

17. A method of anticipating a possible roll event of a vehicle, said method comprising the steps of:

storing in memory data representative of one or more predetermined driving scenarios that represent possible vehicle roll scenarios;

sensing vehicle dynamics and generating data indicative thereof;

storing in memory data representative of a history of recent driving events of the vehicle;

comparing the data representative of a history of recent driving events to the data representative of one or more predetermined driving scenarios;

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

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

18. The method as defined in claim 17 further comprising the step of receiving a plurality of input signals indicative of parameters of the vehicle, wherein the data representative of a history of recent driving events is determined as a function of the vehicle parameters and sensed signals.

19. The method as defined in claim 18, wherein the vehicle parameters include vehicle speed and steering angle.

20. The method as defined in claim 17, wherein the sensed. signals include acceleration and rate of the vehicle.

21. The method as defined in claim 17, wherein the step of comparing comprises measuring distance between the data representative of a history of recent driving events and the data representative of one or more predetermined driving scenarios.

22. The method as defined in claim 17, wherein the method of comparing performs a Hidden Markov Model.

23. The method as defined in claim 17, wherein the method of comparing uses a Support Vector Machine.