Road vehicle driver behaviour analysis method

• US 8,260,491 B2
• Filed: 07/30/2010
• Issued: 09/04/2012
• Est. Priority Date: 07/31/2009
• Status: Active Grant

• Current Assignee: S.A.T.E. - Systems And Advanced Technologies Engineering Srl
• Original Assignee: Systems and Advances Technologies Engineering SRI
• Inventors: Brighenti, Attilio, Biancat, Jacopo
• Primary Examiner(s): Nguyen, Kim T
• Application Number:
  US12/847,229
• Publication Number:
  US 20110029184A1
• Time in Patent Office: 767 Days
• Field of Search: 701/29.1, 701/34.1, 701/53, 701/58, 701/65
• US Class Current: 701/34.1
• CPC Class Codes: B60W 2520/105 Longitudinal acceleration
• CPC Class Codes: B60W 2520/125 Lateral acceleration
• CPC Class Codes: B60W 2520/14 Yaw
• CPC Class Codes: B60W 2520/28 Wheel speed
• CPC Class Codes: B60W 2540/12 Brake pedal position
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/0953 the prediction being responsive to vehicle dynamic parameters
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention

Abstract

A road vehicle (1) driver behavior analysis method, the analysis method including the steps of determining and memorizing the instantaneous position of the vehicle (1) expressed in geographic coordinates; determining and memorizing at least one dynamic characteristic characterizing motion of the vehicle (1); classifying a current road section just travelled by the vehicle (1); determining the space-dependent pattern of the dynamic characteristic along the current road section; determining a deviation between the space-dependent pattern of the dynamic characteristic along the current road section, and a space-dependent mean pattern or statistical distribution of the dynamic characteristic along the same or a similar road section and determined in previous runs of the vehicle (1); and identifying anomalous driver behavior if the absolute value of the deviation is above a given threshold.

Claims

1. A road vehicle (1) driver behaviour analysis method, the analysis method comprising the steps of:

determining and memorizing an instantaneous position of the vehicle (1) expressed in geographic coordinates;

determining and memorizing at least one dynamic characteristic characterizing motion of the vehicle (1);

classifying a current road section just travelled by the vehicle (1) and defined by a start point and an end point having respective geographic coordinates;

determining a space-dependent pattern of the dynamic characteristic along and from the start point to the end point of the current road section;

determining a deviation between the space-dependent pattern of the dynamic characteristic along the current road section, and a space-dependent mean pattern or statistical distribution of the dynamic characteristic along the same or a similar road section and determined in previous runs of the vehicle (1);

updating, only using the space-dependent pattern of the dynamic characteristic along the current road section, the space-dependent mean pattern or statistical distribution of the dynamic characteristic along the same or similar road section, if an absolute value of the deviation is below a first threshold; and

identifying anomalous driver behaviour, and not using the space-dependent pattern of the dynamic characteristic along the current road section to update the space-dependent mean pattern or statistical distribution of the dynamic characteristic along the same or similar road section, if the absolute value of the deviation is above a second threshold;

wherein an analysis unit is utilized to perform at least the classifying, determining the space-dependent pattern, determining a deviation, updating and identifying steps.

2. An analysis method as claimed in claim 1, and comprising the further step of classifying the current road section as a function of a pattern of at least one directional dynamic characteristic of the vehicle (1), defined by a steering angle of the vehicle (1), a yaw angle of the vehicle (1), or a lateral acceleration of the vehicle (1).

3. An analysis method as claimed in claim 2, and comprising the further steps of:

classifying the current road section as a straight, if the absolute value of the directional dynamic characteristic remains below a third threshold along the whole of the current road section; and

classifying the current road section as a curve, if the absolute value of the directional dynamic characteristic remains above a fourth threshold along the whole of the current road section.

4. An analysis method as claimed in claim 2, and comprising the further step of only classifying the current road section if the pattern of the directional dynamic characteristic remains within a given range for a travelled space above a fifth threshold;

otherwise the current road section is eliminated with no further analysis, on the grounds of not being sufficiently stable.

5. An analysis method as claimed in claim 2, and comprising the further step of considering two road sections similar if, along both road sections, the pattern of the directional dynamic characteristic remains within the same given range, and if, along both road sections, the speed of the vehicle (1) or longitudinal acceleration/deceleration of the vehicle (1) remains within the same given range.

6. An analysis method as claimed in claim 1, and comprising the further step of considering two road sections identical if the distance between the respective start and end points of the two road sections is below a sixth threshold.

7. An analysis method as claimed in claim 1, wherein the step of determining a deviation comprises the further steps of:

interpolating the space-dependent pattern of the dynamic characteristic along the current road section, so that all the elements of the dynamic characteristic along the current road section assume values at the same points in space as the space-dependent mean pattern or statistical distribution of the dynamic characteristic along the same or similar road section and determined in previous runs of the vehicle (1); and

making a point-by-point comparison of the space-dependent pattern of the dynamic characteristic along the current road section, and the space-dependent mean pattern or statistical distribution of the dynamic characteristic along the same or similar road section and determined in previous runs of the vehicle (1).

8. An analysis method as claimed in claim 1, and comprising the further steps of:

determining as a function of time and memorizing the instantaneous position of the vehicle (1) expressed in geographic coordinates;

determining as a function of time and memorizing at least the dynamic characteristic characterizing motion of the vehicle (1); and

subsequently converting a space-dependent dynamic characteristic by combining a time-dependent dynamic characteristic with a time-dependent instantaneous position of the vehicle (1) expressed in geographic coordinates.

9. An analysis method as claimed in claim 1, wherein the dynamic characteristic characterizing motion of the vehicle (1) is defined by a steering angle of the vehicle (1), a rate of change in the steering angle of the vehicle (1), a yaw angle of the vehicle (1), a rate of change in the yaw angle of the vehicle (1), a lateral acceleration of the vehicle (1), a longitudinal acceleration of the vehicle (1), a speed of the vehicle (1), a rotation speed of individual wheels (2, 3) of the vehicle (1), or a hydraulic pressure of the brake circuit of the vehicle (1).

10. An analysis method as claimed in claim 1, and comprising the further step of determining a time trend in mean deviation values, to identify a positive trend towards more normal driving behaviour, or a negative trend towards less normal driving behaviour.

11. An analysis method as claimed in claim 10, and comprising the further steps of:

determining at least one performance index as a function of the recent dynamic characteristic pattern and independently of the instantaneous position of the vehicle (1); and

correlating a change in driving behaviour with the performance index.

12. An analysis method as claimed in claim 1, and comprising the further steps of:

determining at least one performance index as a function of the recent dynamic characteristic pattern and independently of the instantaneous position of the vehicle (1); and

also identifying anomalous driver behaviour as a function of the performance index.

13. An analysis method as claimed in claim 1, and comprising the further steps of:

memorizing the sequence of classified road sections in a “

source-destination”

structure;

determining from the “

source-destination”

structure a next road section after the current road section;

determining whether or not a current motion status of the vehicle (1) is compatible with negotiating the next road section; and

alerting the driver or an electronic central control unit (18, 19) of the vehicle (1) to a potential hazard situation, if the current motion status of the vehicle (1) is incompatible with negotiating the next road section.

14. An analysis method as claimed in claim 13, and comprising the further steps of:

determining a mean crossover speed to the next road section, by determining a mean speed at the start point of the next road section;

determining an acceleration/deceleration necessary to reach the mean crossover speed to the next road section smoothly by the start point of the next road section; and

judging the current motion status of the vehicle (1) incompatible with negotiating the next road section, if the acceleration/deceleration required is above a seventh threshold, or if a difference between the acceleration/deceleration required and a mean acceleration/deceleration along the current road section is above an eighth threshold.