Methods and systems for driver identification

• US 9,398,423 B2
• Filed: 12/23/2013
• Issued: 07/19/2016
• Est. Priority Date: 12/26/2012
• Status: Active Grant

• Current Assignee: Cambridge Mobile Telematics, Inc.
• Original Assignee: Truemotion, Inc.
• Inventors: Cordova, Brad, Adelmann, Joe
• Primary Examiner(s): Johnson, Gregory
• Application Number:
  US14/139,510
• Publication Number:
  US 20140180730A1
• Time in Patent Office: 939 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: B60W 2420/905 the sensor being an xyz axis sensor
• CPC Class Codes: B60W 2520/14 Yaw
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07C 5/08 Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/38 for collecting sensor information
• CPC Class Codes: H04W 4/40 for vehicles, e.g. vehicle-to-pedestrians [V2P]

Abstract

A method of determining vehicle entry information for a user includes obtaining a yaw measurement using a mobile device, determining, using a processor, a first time span associated with a user entering a vehicle, and determining, using the processor, a second time span associated with a user exiting the vehicle. The method also includes determining that a change in magnitude over a portion of the yaw measurement is greater than a predetermined threshold over at least one of the first time span or the second time span and determining an angular change of the yaw measurement over the predetermined threshold. The method further includes associating right hand entry with the vehicle entry information if the angular orientation of the yaw measurement is clockwise and associating left hand entry with the vehicle entry information if the angular orientation of the yaw measurement is counter-clockwise.

Claims

1. A method of aligning a mobile device having an accelerometer, a gyroscope, and an alignment axis to a reference frame of a vehicle, the method comprising:

placing the mobile device in the vehicle;

obtaining data from the accelerometer of the mobile device;

detecting, one or more braking events and one or more forward acceleration events during a driving event;

determining, using the accelerometer of the mobile device, a direction of travel of the vehicle with respect to the reference frame of the vehicle;

obtaining angular measurement data from the gyroscope of the mobile device; and

during the driving event, aligning, using the angular measurement data, the alignment axis of the mobile device to the reference frame of the vehicle.

2. The method of claim 1 wherein the one or more braking events and the one or more forward acceleration events are characterized by at least one of a magnitude of acceleration projected onto an x-y plane having a normal aligned with acceleration due to gravity, a standard deviation, a mean, kurtosis, skew, a maximum value, a minimum value, wavelet coefficients, FFT coefficients, or features calculated using unsupervised feature selection methods including at least one of Sparse Auto-Encoders or Restricted Boltzmann Machines.

3. The method of claim 1 wherein the one or more braking events and the one or more forward acceleration events are characterized by a duration, a time stamp, and a magnitude of acceleration over a predetermined threshold.

4. The method of claim 1 wherein determining the direction of travel of the vehicle comprises:

projecting the data from the accelerometer onto each axis of an x-y plane having a normal aligned with acceleration due to gravity through an angle of 360 degrees in predetermined increments;

determining an angle at which acceleration along at least one of the x or y axes is a maximum; and

defining the direction of travel of the vehicle as the angle at which acceleration along at least one of the x or y axes is a maximum.

5. The method of claim 1 wherein placing the mobile device in the vehicle results from a user having the mobile device entering the vehicle or the user placing an item enclosing the mobile device inside the vehicle.

6. A method of determining a position of a mobile device in a vehicle, the method comprising:

obtaining accelerometer data collected using a accelerometer in the mobile device;

obtaining angular orientation data collected using a gyroscope in the mobile device;

determining a start time of a driving event;

determining an entry side for the mobile device using the angular orientation data;

detecting an acceleration event;

during the driving event, aligning the mobile device to a reference frame of the vehicle;

determining a front/back location of the mobile device;

detecting a braking event;

determining an end time of the driving event;

determining an exit side for the mobile device after the end time of the driving event; and

determining the position of the mobile device in the vehicle during at least a portion of the driving event.

7. The method of claim 6 wherein determining at least one of the entry side for the mobile device or the exit side of for the mobile device comprises measuring a yaw value for the mobile device associated with the start time.

8. The method of claim 7 wherein measuring the yaw value comprises:

obtaining rotation data collected using the gyroscope in the mobile device, wherein the rotation data is with respect to a vector aligned with acceleration due to gravity; and

detecting a rotation in an x-y plane orthogonal to the vector aligned with acceleration due to gravity, wherein the rotation is greater than a predetermined threshold.

9. The method of claim 7 wherein measuring the yaw value comprises:

obtaining rotation data collected using the gyroscope in the mobile device, wherein the rotation data is with respect to a vector aligned with acceleration due to gravity; and

detecting a rotation in an x-y plane orthogonal to the vector aligned with acceleration due to gravity, wherein the rotation is characterized by a pattern associated with user entry.

10. The method of claim 6 wherein determining the entry side of the mobile device comprises:

providing acceleration data and yaw data, wherein a y-axis of the mobile device is aligned to a longitudinal axis of the vehicle and an x-axis of the mobile device is aligned to a transverse axis that is perpendicular to both the longitudinal axis of the vehicle and acceleration due to gravity;

selecting a subset of the provided acceleration data and yaw data, wherein the subset is associated with a predetermined time around a start time of a driving event;

predicting an entry side for the mobile device using at least one of a vector-product-based method, an integral method, or a seatbelt-based method;

selecting a second subset of the provided acceleration data and yaw data, wherein the second subset is associated with a driving time of the driving event; and

predicting a transverse position of the mobile device in the vehicle during the driving time using a centripetal acceleration method.

11. The method of claim 10 wherein predicting at least one of the entry side or the exit side comprises computing a weighted combination of predictions resulting from a plurality of at least one of a vector-product-based method, an integral method, or a seatbelt-based method.

12. The method of claim 10 wherein determining the transverse position comprising computing a weighted combination of at least a plurality of a yaw method, a centripetal acceleration method, a vector product method, or an integral method.

13. The method of claim 10 wherein the integral method comprises:

providing acceleration data and yaw data, wherein a y-axis of the mobile device is aligned to a longitudinal axis of the vehicle and an x-axis of the mobile device is aligned to a transverse axis that is perpendicular to both the longitudinal axis of the vehicle and acceleration due to gravity;

selecting a subset of the provided acceleration data and yaw data, wherein the subset is associated with a predetermined time around a start time of a driving event;

determining a sign of an integral of the subset projected onto the x-axis the mobile device phone and calculated over a predetermined time window surrounding the start time;

predicting that the mobile device enters on the right side of the vehicle if the sign of the integral of the subset is positive;

predicting that the phone enters on the left side of the vehicle if the sign of the integral of the subset is negative;

selecting a second subset of the provided acceleration data and yaw data, wherein the second subset is associated with a predetermined time around an end time of the driving event;

selecting a second subset of the provided acceleration data and yaw data, wherein the second subset is associated with a predetermined time around an end time of the driving event;

determining a sign of an integral of the second subset projected onto the x-axis the mobile device and calculated over a predetermined time window surrounding the end time;

predicting that the mobile device enters on the right side of the vehicle if the sign of the integral of the subset is positive;

predicting that the phone exits on the left side of the vehicle if the sign of the integral of the second subset is positive; and

predicting that the phone exits on the right side of the vehicle if the sign of the integral of the second subset is negative.

14. The method of claim 6 wherein determining the front/back location of the vehicle comprises:

obtaining acceleration data associated with a driving time of a driving event characterized by an initial entry signal and a terminal exit signal; and

determining a longitudinal position of the mobile device in the vehicle based on at least one of a bump detection method, paired Y,Z acceleration method.

15. The method of claim 14 wherein determining the longitudinal position of the mobile device in the vehicle comprises computing a weighted combination of the bump detection method and the paired Y,Z acceleration method.