Method and system to assess abnormal driving behaviour of vehicles travelling on road

• US 9,881,498 B2
• Filed: 03/12/2014
• Issued: 01/30/2018
• Est. Priority Date: 03/12/2013
• Status: Active Grant

• Current Assignee: Inria Institut National de Recherche EN Informatique et EN Automatique
• Original Assignee: Inria Institut National de Recherche EN Informatique et EN Automatique
• Inventors: Paromtchik, Igor Evguenyevitch, Laugier, Christian
• Primary Examiner(s): Nguyen, Bao Long T
• Application Number:
  US14/774,605
• Publication Number:
  US 20160035220A1
• Time in Patent Office: 1,420 Days
• Field of Search: 701117, 701 93, 701 96, 701 98, 701301
• CPC Class Codes: B60W 2040/0818 Inactivity or incapacity of driver
• CPC Class Codes: B60W 2050/146 Display means
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2554/801 Lateral distance
• CPC Class Codes: B60W 2554/804 Relative longitudinal speed
• CPC Class Codes: B60W 2555/60 Traffic rules, e.g. speed limits or right of way
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 30/146 Speed limiting
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/12 Limiting control by the driver depending on vehicle state, e.g. interlocking means for the control input for preventing unsafe operation
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: G08G 1/0125 Traffic data processing
• CPC Class Codes: G08G 1/0137 for specific applications
• CPC Class Codes: G08G 1/052 with provision for determining speed or overspeed speed measuring in general G01P

Abstract

The invention concerns a method for assessment of abnormal driving behavior to improve driving safety of a vehicle travelling on a road, using position information and motion information about said vehicle and/or at least one neighboring vehicle travelling in the proximity of said vehicle on said road. The method comprises a step of obtaining and memorizing (40, 42) a plurality of position information items and motion information items, each information item corresponding to a measuring time instant of an observation time interval and a step of obtaining (44) at least one estimate of the reference value for said vehicle and/or its at least one neighboring vehicles travelling on said road during the observation time interval. Next, the sets of deviation values are computed (46), each deviation value being computed using a memorized information item corresponding to a measuring time instant and the at least one estimate of the reference value and the quantities of deviation are obtained from the corresponding sets of deviation values. If a quantity of deviation among said quantities of deviation is greater than a predetermined threshold for the corresponding driving behavior, the method implements (52) a measure for safety improvement.

Claims

1. A method for assessment of abnormal driving behaviour of a vehicle travelling on a road, using position information and motion information about said vehicle, the method being characterized in that it comprises the following steps:

obtaining and memorizing a plurality of position information items and motion information items, wherein the plurality of position information items and motion information items are measured by at least one sensor, each position information item and motion information item corresponding to a measuring time instant of an observation time interval, and wherein each motion information item is an instant speed value at the corresponding measuring time instant,

obtaining at least one estimate of a reference value for said vehicle travelling on said road during the observation time interval, wherein said at least one estimate of a reference value is a reference speed value during the observation time interval,

calculating, with a computer, a set of deviation values, each deviation value being computed using a memorized motion information item at a corresponding measuring time instant and the at least one estimate of a reference value, and wherein each deviation value at a given measuring time instant being equal to a difference between the instant speed value at said given measuring time instant and the reference speed value at said given measuring time instant if the instant speed value at said given measuring time instant is greater than the reference speed value, and the deviation value at said given measuring time instant being equal to zero otherwise,

obtaining a quantity of deviation from the set of deviation values to quantify a corresponding abnormal driving behaviour,

repeating the steps of obtaining and memorizing, obtaining at least one estimate, calculating a set of deviation values, and obtaining a quantity of deviation iteratively for monitoring the quantity of deviation for the corresponding abnormal driving behaviour, and

deciding, based on said quantity of deviation, whether a predetermined threshold for the corresponding abnormal driving behaviour has been exceeded and in case of affirmative result, implementing a measure for safety improvement.

2. A method according to claim 1, wherein said quantity of deviation is computed as a sample variance.

3. A method according to claim 1, wherein the obtaining of a quantity of deviation comprises the calculation of skewness or kurtosis of the set of deviation values.

4. A method according to claim 1, wherein the step of implementing a measure of safety improvement comprises raising an audio alarm and/or a visual alarm to assist the driver of said vehicle implementing the method.

5. A method according to claim 1, wherein the step of implementing a measure of safety improvement comprises triggering a driver assistance system to take control of said vehicle implementing the method.

6. A method according to claim 1, wherein the plurality of position information items and motion information items are provided at measuring instants being approximately regularly sampled, and wherein said observation time interval is dependent on the vehicle'"'"'s speed, and wherein said observation time interval is set to contain a number of information items greater than predetermined minimum number.

13. A method according to claim 5, further comprising a step of calculating a matrix representative of a meandering of said vehicle and of said at least one neighbouring vehicle, and a step of implementing the measure for safety improvement if at least one value of said meandering matrix is greater than a predetermined threshold corresponding to an abnormal meandering behaviour.

14. A method according to claim 5, wherein speed information relative to said vehicle and range distance information relative to at least one neighbouring vehicle are available, and wherein said estimate of a second reference value is a minimum safe range distance value computed for each corresponding measuring time instant depending on instant speed information at said corresponding measuring time instant, and wherein a deviation value of the second set of deviation values at a given measuring time instant being equal to the difference between the minimum safe range distance value computed for said given measuring time instant and the measured range distance between said vehicle and said neighbouring vehicle at said given measuring time instant if said measured range distance is smaller than said minimum safe range distance at said given measuring time instant, and the deviation value of the second set of deviation values at the given measuring time instant being equal to zero otherwise.

7. A method for assessment of abnormal driving behaviour of a vehicle travelling on a road, using position information and motion information about said vehicle, the method being characterized in that it comprises the following steps:

obtaining and memorizing a plurality of position information items and motion information items, wherein the plurality of position information items and motion information items are measured by at least one sensor, each position information item and motion information item corresponding to a measuring time instant of an observation time interval,

obtaining at least one estimate of a reference value for said vehicle travelling on said road during the observation time interval,

calculating, with a computer, a set of deviation values, each deviation value being computed using a memorized position information item at a corresponding measuring time instant and the at least one estimate of a reference value,

obtaining a quantity of deviation from the set of deviation values to quantify a corresponding abnormal driving behaviour,

repeating the steps of obtaining and memorizing, obtaining at least one estimate, calculating a set of deviation values, and obtaining a quantity of deviation iteratively for monitoring the quantity of deviation for the corresponding abnormal driving behaviour,

deciding, based on said quantity of deviation, whether a predetermined threshold for the corresponding abnormal driving behaviour has been exceeded and in case of affirmative result, implementing a measure for safety improvement, and

wherein the step of obtaining at least one estimate of a reference value comprises obtaining a plurality of coefficient values defining an estimate of a reference path travelled during said observation time interval, said plurality of coefficient values being computed using a subset of the memorized plurality of position information items and motion information items.

8. A method according to claim 7, wherein a deviation value at an associated measuring time instant is equal to a distance between the corresponding memorized position information item and a reference position corresponding to said associated measuring time instant on the estimated reference path, so as to obtain the set of deviation values.

9. A method according to claim 7, wherein the observation time interval is defined by a starting time instant and an ending time instant, and wherein said estimated reference path is modelled by a curve, and wherein the step of obtaining a plurality of coefficient values comprising a curve fitting using the vehicle position and motion information at the starting time instant and the vehicle position and motion information at the ending time instant.

10. A method according to claim 7, wherein said quantity of deviation is computed as a sample variance.

11. A method according to claim 7, wherein the obtaining of a quantity of deviation comprises the calculation of skewness or kurtosis of the set of deviation values.

12. A method for assessment of abnormal driving behaviour of a vehicle travelling on a road, using position information and motion information about said vehicle and position information and motion information about at least one neighbouring vehicle of said vehicle implementing the method, travelling on said road, the method comprising the following steps:

obtaining and memorizing a plurality of position information items and motion information items, each position information item and motion information item corresponding to a measuring time instant of an observation time interval,

obtaining and memorizing a plurality of items of information relative to the position and speed of at least one neighbouring vehicle during the observation time interval,

obtaining at least one estimate of a first reference value for said vehicle travelling on said road during the observation time interval,

obtaining at least one estimate of a second reference value for said at least one neighbouring vehicle during the observation time interval,

calculating, with a computer, a first set of deviation values, each deviation value of the first set of deviation values being computed using a memorized position information item at a corresponding measuring time instant and the at least one estimate of a first reference value,

calculating, with a computer, a second set of deviation values, each deviation value of the second set of deviation values being computed using a memorized item of information relative to the position of said at least one neighbouring vehicle at a corresponding measuring time instant and the at least one estimate of a second reference value,

obtaining a first quantity of deviation from the first set of deviation values to quantify a corresponding abnormal driving behaviour,

obtaining a second quantity of deviation from the second set of deviation values to quantify a corresponding abnormal driving behaviour of said at least one neighbouring vehicle,

repeating the steps of obtaining and memorizing a plurality of position information items and motion information item, obtaining at least one estimate of a first reference value, calculating a first set of deviation values, and obtaining a first quantity of deviation iteratively for monitoring the first quantity of deviation for the corresponding abnormal driving behaviour,

repeating the steps of obtaining and memorizing a plurality of items of information relative to the position and speed of said neighbouring vehicle, obtaining at least one estimate of a second reference value, calculating a second set of deviation values and obtaining a second quantity of deviation iteratively for monitoring the second quantity of deviation for the corresponding abnormal driving behaviour of said at least one neighbouring vehicle,

deciding, based on said first quantity of deviation, whether a first predetermined threshold for the corresponding abnormal driving behaviour has been exceeded and in case of affirmative result, implementing a measure for safety improvement, and

deciding, based on said second quantity of deviation, whether a second predetermined threshold for the corresponding abnormal driving behaviour of said neighbouring vehicle has been exceeded and in case of affirmative result, implementing the measure for safety improvement.

15. A method according to claim 12, wherein said first quantity of deviation and said second quantity of deviation are computed as a sample variance.

16. A method according to claim 15, wherein the obtaining of the first quantity of deviation comprises calculation of skewness or kurtosis of the first set of deviation values, and wherein the obtaining of the second quantity of deviation comprises calculation of skewness or kurtosis of the second set of deviation values.

17. A system for assessment of abnormal driving behaviour of a vehicle travelling on a road, the system being characterized in that it comprises:

a processing unit for obtaining a plurality of first position information items and first motion information items from on-board sensors of said vehicle about said vehicle, each first position information item and first motion information item corresponding to a measuring time instant of an observation time interval,

a processing unit for obtaining a plurality of second position information items and second motion information items from on-board sensors of said vehicle about at least one neighbouring travelling vehicle on said road, each second position information item and second motion information item corresponding to a measuring time instant of an observation time interval,

a memorizing unit for memorizing the plurality of first position information items and first motion information items and the plurality of second position items and second motion items,

a reference values obtaining unit for obtaining at least one estimate of a first reference value for said vehicle and at least one estimate of a second reference value for said at least one neighbouring vehicle travelling on said road during the observation time interval,

a calculation unit adapted to calculate a first set of deviation values and a second set of deviation values, each deviation value of the first set of deviation values being computed using a memorized first position information item at a corresponding measuring time instant and the at least one estimate of a first reference value corresponding to the memorized first position information item, each deviation value of the second set of deviation values being computed using a memorized second position information item at a corresponding measuring time instant and the at least one estimate of a second reference value corresponding to the memorized second position information item,

an assessment unit adapted to obtain a first quantity of deviation for the first set of deviation values and a second quantity of deviation for the second set of deviation values, and

a decision making unit, adapted to decide, based on at least one of said first quantity of deviation or said second quantity of deviation, whether a predetermined threshold for a corresponding abnormal driving behaviour has been exceeded to trigger the implementation of a measure for safety improvement.

18. A system for assessment of abnormal driving behaviour of a vehicle travelling on a road according to claim 17, further comprising a meandering matrix calculation unit for obtaining a matrix containing quantities of deviation representative of a meandering of said vehicle and of said at least one neighbouring vehicle.