ADAPTIVE VEHICLE CONTROL SYSTEM WITH DRIVING STYLE RECOGNITION BASED ON VEHICLE ACCELERATING AND DECELERATING

• US 20100152951A1
• Filed: 12/15/2008
• Published: 06/17/2010
• Est. Priority Date: 12/15/2008
• Status: Abandoned Application

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations Incorporated (Motors Liquidation Co. GUC Trust)
• Inventors: Huang, Jihua, Chin, Yuen-Kwok, Lin, William C.
• Application Number:
  US12/335,263
• Publication Number:
  US 20100152951A1
• Time in Patent Office: Days
• US Class Current: 701/29
• CPC Class Codes: B60W 40/09 Driving style or behaviour

Abstract

An adaptive vehicle control system that classifies a driver'"'"'s driving style based on vehicle stopping maneuvers. The system reads sensor signals to provide a vehicle speed and determines whether the vehicle is currently in straight line driving or curve driving. If the vehicle is in straight line or curve driving and the vehicle speed is less than a speed threshold, the system determines that the vehicle is in an accelerating or decelerating maneuver. The system then determines that the accelerating and decelerating maneuver has ended if the vehicle is not in straight line or curve driving or the vehicle speed signal is less than the speed threshold. The system can then classify the vehicle accelerating and decelerating maneuver using select discriminate features.

Claims

1. A method for identifying whether a vehicle maneuver is a vehicle accelerating and decelerating maneuver, said method comprising:

determining a speed of the vehicle;

determining whether the vehicle is driving in a straight line;

determining whether the vehicle is driving on a curve;

determining whether the vehicle speed is greater than a vehicle speed threshold during a first time window;

determining that the vehicle is in the vehicle accelerating and decelerating maneuver if the vehicle is driving in a straight line or driving on a curve and the vehicle speed is less than the speed threshold during the first time window; and

determining that the vehicle accelerating and decelerating maneuver has ended if the vehicle is not driving in a straight line, is not driving on a curve or the vehicle speed is less than the vehicle speed threshold during a second time window.

2. The method according to claim 1 further comprising classifying the maneuver to determine a driver'"'"'s driving style if the maneuver is a vehicle accelerating and decelerating maneuver.

3. The method according to claim 2 wherein classifying the vehicle accelerating and decelerating maneuver includes using selected discriminant features obtained or derived from the vehicle accelerating and decelerating maneuver.

4. The method according to claim 3 wherein the discriminant features are obtained or derived by the group comprising average and range of speed, average and range of acceleration and deceleration, maximum average acceleration and deceleration, average of the difference between the vehicle speed and a posted speed and an array of throttle/brake indices.

5. The method according to claim 2 wherein classifying the maneuver includes using a classification technique selected from the group comprising fuzzy logic, clustering, neural networks, self-organizing maps and threshold-based logic.

6. The method according to claim 2 wherein classifying the vehicle accelerating and decelerating maneuver includes using a neural network.

7. The method according to claim 2 wherein classifying the accelerating and decelerating maneuver includes classifying the vehicle accelerating and decelerating maneuver as either a straight-line accelerating and decelerating maneuver or a accelerating and decelerating and turning maneuver.

8. A method for identifying whether a vehicle maneuver is a vehicle accelerating and decelerating maneuver, said method comprising:

determining a speed of the vehicle;

determining whether the vehicle is driving in a straight line;

determining whether the vehicle is driving on a curve;

determining whether the vehicle speed is greater than a vehicle speed threshold during a first time window;

determining that the vehicle is in the vehicle accelerating and decelerating maneuver if the vehicle is driving in a straight line or driving on a curve and the vehicle speed is less than the speed threshold during the first time window;

determining that the vehicle accelerating and decelerating maneuver has ended if the vehicle is not driving in a straight line, is not driving on a curve or the vehicle speed is less than the vehicle speed threshold during a second time window; and

classifying the vehicle accelerating and decelerating maneuver to determine a driver'"'"'s driving style by using selected discriminant features obtained or derived from the vehicle accelerating and decelerating maneuver.

9. The method according to claim 8 wherein classifying the vehicle accelerating and decelerating maneuver includes using selected discriminant features derived from the vehicle accelerating and decelerating maneuver.

10. The method according to claim 9 wherein the discriminant features are obtained or derived by the group comprising average and range of speed, average and range of acceleration and deceleration, maximum average acceleration and deceleration, average of the difference between the vehicle speed and a posted speed and an array of throttle/brake indices.

11. The method according to claim 8 wherein classifying the maneuver includes using a classification technique selected from the group comprising fuzzy logic, clustering, neural networks, self-organizing maps and threshold-based logic.

12. The method according to claim 8 wherein classifying the vehicle accelerating and decelerating maneuver includes using a neural network.

13. The method according to claim 8 wherein classifying the maneuver includes classifying the vehicle accelerating and decelerating maneuver as either a straight-line stopping maneuver or a accelerating and decelerating and turning maneuver.

14. A system for identifying whether a vehicle maneuver is a vehicle accelerating and decelerating maneuver, said system comprising:

means for determining a speed of the vehicle;

means for determining whether the vehicle is driving in a straight line;

means for determining whether the vehicle is driving on a curve;

means for determining whether the vehicle speed is greater than a vehicle speed threshold during a first time window;

means for determining that the vehicle is in the vehicle accelerating and decelerating maneuver if the vehicle is driving in a straight line or driving on a curve and the vehicle speed is less than the speed threshold during the first time window; and

means for determining that the vehicle accelerating and decelerating maneuver has ended if the vehicle is not driving in a straight line, is not driving on a curve or the vehicle speed is less than the vehicle speed threshold during a second time window.

15. The system according to claim 14 further comprising means for classifying the maneuver to determine a driver'"'"'s driving style if the maneuver is a vehicle accelerating and decelerating maneuver.

16. The system according to claim 15 wherein the means for classifying the vehicle accelerating and decelerating maneuver includes using selected discriminant features obtained or derived from the vehicle accelerating and decelerating maneuver.

17. The system according to claim 16 wherein the discriminant features are obtained or derived from the group comprising average and range of speed, average and range of acceleration and deceleration, maximum average acceleration and deceleration, average of the difference between the vehicle speed and a posted speed and an array of throttle/brake indices.

18. The system according to claim 15 wherein the means for classifying the maneuver includes using a classification technique selected form the group comprising fuzzy logic, clustering, neural networks, self-organizing maps and threshold-based logic.

19. The system according to claim 15 wherein the means for classifying the vehicle accelerating and decelerating maneuver includes using a neural network.