Inference of vehicular trajectory characteristics with personal mobile devices

• US 9,228,836 B2
• Filed: 03/15/2013
• Issued: 01/05/2016
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Cambridge Mobile Telematics, Inc.
• Original Assignee: Cambridge Mobile Telematics, Inc.
• Inventors: Girod, Lewis D., Balakrishnan, Hari, Madden, Samuel Ross
• Primary Examiner(s): Lee, Paul D
• Application Number:
  US13/832,456
• Publication Number:
  US 20140278206A1
• Time in Patent Office: 1,026 Days
• Field of Search: 702/94, 702/141, 702/150
• US Class Current: 1/1
• CPC Class Codes: G01C 15/00 Surveying instruments or accessories not provided for in groups G01C1/00 - G01C13/00
• CPC Class Codes: G01C 21/10 by using measurements of speed or acceleration G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/165 combined with non-inertial navigation instruments
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01P 15/0891 with indication of predetermined acceleration values G01P15/135 takes precedence

Abstract

Accurate longitudinal acceleration, lateral acceleration (perpendicular to the principal direction of motion, and velocity, is inferred by processing raw data from a commodity three-axis accelerometer that may be oriented arbitrarily in a moving vehicle (or carried by a moving user), and whose orientation and position may change arbitrarily during the motion. The approach is applicable to a range of applications, including insurance telematics, driver behavior and risk assessment, and road surface quality assessment.

Claims

1. A method comprising inferring vehicular trajectory characteristics, said inferring comprising:

acquiring using a machine-implemented processor data representing a sequence of measurements of acceleration of a device traveling in a vehicle traversing a road network, the device being in an unknown and changeable orientation relative to the frame of reference of the vehicle in which the device is traveling;

forming during traversal of the road network by the vehicle using a machine-implemented processor associated with the device in the vehicle a plurality of time segments of the measurements of acceleration, wherein the orientation of the device relative to the vehicle when acquiring the data differs between at least some of the time segments and wherein forming the plurality of time segments comprises detecting times of substantial relative motion of the device relative to the vehicle, and forming the time segments between said detected times;

for each time segment of a plurality of time segments, using a machine-implemented processor,

determining data characterizing an orientation of the device relative to a frame of reference of the vehicle during that time segment,

forming motion-related data in the frame of reference of the vehicle during the time segment, and

determining data characterizing trajectory characteristics of the vehicle in the time segment; and

providing data characterizing trajectory characteristic of the vehicle determined from the data characterizing the trajectory characteristics in multiple of the time segments.

2. The method of claim 1 wherein determining data characterizing an orientation of the device comprises determining a time varying orientation within at least one of the time segments of the device relative to the frame of reference of the vehicle.

3. The method of claim 1 wherein determining data characterizing an orientation of the device in a time segment comprises determining a vertical direction.

4. The method of claim 3 further comprising using a distribution of sensed motion in a plane orthogonal to the vertical direction to determine a direction of travel of the vehicle.

5. The method of claim 1 wherein the device comprises a personal mobile device that is held or is on the person of a driver or passenger of the vehicle.

6. The method of claim 1 wherein the data characterizing trajectory characteristics of a vehicle comprise at least one of longitudinal acceleration, lateral acceleration, longitudinal velocity, and distance travelled of the vehicle.

7. The method of claim 1 wherein acquiring the data representing the sequence of measurements of acceleration of the device comprises measuring acceleration values on multiple axes using accelerometers in the device.

8. The method of claim 1 wherein the inferring further comprises:

accessing map data characterizing a road network;

processing the data characterizing the trajectory characteristics of the vehicle according to the map data to determine data characterizing traversal of the road network by the vehicle.

9. The method of claim 1 further comprising applying map traversal data in determining the data characterizing the trajectory characteristics of the vehicle.

10. The method of claim 1 wherein the inferring further comprises:

acquiring data representing environmental characteristics of the device; and

wherein determining the trajectory characteristic of the vehicle includes using the data representing the environmental characteristics.

11. The method of claim 10 wherein the data representing environmental characteristics includes data representing an acoustic environment of the vehicle, where said data provides information related to velocity of the vehicle.

12. The method of claim 1 wherein the inferring further comprises:

acquiring data from a gyroscope on the device; and

wherein determining the trajectory characteristic of the vehicle includes using the gyroscope data.

13. The method of claim 12 wherein the use of the gyroscope data is in the forming of the time segments.

14. The method of claim 12 wherein the use of the gyroscope data is in the forming of the motion-related data in the frame of reference of the vehicle during the time segment.

15. The method of claim 1 wherein the inferring further comprises:

acquiring position or velocity data of the device using a radio or positioning sensor in the device; and

wherein determining the trajectory characteristic of the vehicle includes using the position data.

16. The method of claim 15 further comprising determining when to acquire the position or velocity data at least in part according to the determined trajectory characteristics determined from the measurements of acceleration of the device.

17. The method of claim 15 further comprising determining when to acquire the position or velocity data at least in part according to the determined motion state of the device in the frame of reference of the vehicle.

18. The method of claim 15 further comprising:

accessing map data characterizing a road network;

processing the data characterizing the trajectory characteristics of the vehicle according to the map data to determine data characterizing traversal of the road network by the vehicle.

19. The method of claim 1 further comprising providing software to the device for execution on the device for causing a processor in the device to perform the inferring.

20. The method of claim 1 further comprising providing the data characterizing trajectory characteristic of the vehicle via a radio interface of the device.

21. The method of claim 20 wherein providing the data includes providing the data to a server computer and at least some of the steps of claim 1 are performed at said server.

22. The method of claim 1 further comprising providing the data characterizing the trajectory characteristics from the device for use in an insurance application.

23. The method of claim 1 further comprising providing the data characterizing the trajectory characteristics to a second party with a contractual relationship with a first party comprising at least one of a user of the device and party in control of the vehicle.

24. The method of claim 23 wherein the contractual relationship is governed at least in part according to trajectory characteristics of the vehicle.

25. The method of claim 23 further comprising forming the contractual relationship between the first party and the second party.

26. The method of claim 1 wherein forming the plurality of time segments comprises determining said segments such that the orientation of the device relative to the vehicle is relatively fixed as compared to changes of the orientation at transitions between said segments.

27. The method of claim 1 wherein, for each time segment of a plurality of time segments, the method further comprises

determining whether there is a time interval in the time segment in which the vehicle is stationary.

28. The method of claim 27 wherein determining a time interval in which the vehicle is stationary uses a threshold picked from statistics of the measurements of acceleration of the device.

29. The method of claim 1 wherein the data characterizing trajectory characteristics includes at least one of (a) a path on a road network followed by the vehicle, (b) a velocity of the vehicle, and (c) an acceleration of the vehicle.

30. The method of claim 29 wherein measurements of acceleration of the device include measurements from at least one of an accelerometer and gyroscope fixed in the device.

31. A non-transitory machine-readable medium, storing software comprising instructions for causing a processor of a device to:

acquire data representing a sequence of measurements of acceleration of the device traveling in a vehicle traversing a road network;

form during traversal of the road network a plurality of time segments of the measurements of acceleration, such that the orientation of the device relative to the vehicle when acquiring the data differs between at least some of the formed time segments and wherein forming the plurality of time segments comprises detecting times of substantial relative motion of the device relative to the vehicle, and

forming the time segments between said detected times;

for each of a plurality of the time segments,

determine data characterizing an orientation of the device relative to a frame of reference of the vehicle,

form motion-related data in the frame of reference of the vehicle during the time segment, and

determine data characterizing trajectory characteristics of the vehicle in the time segment; and

provide data characterizing trajectory characteristic of the vehicle determined from the data characterizing the trajectory characteristics in multiple of the time segments.

32. A method comprising inferring vehicular trajectory characteristics, said inferring comprising:

acquiring using a machine-implemented processor data representing a sequence of measurements of acceleration of a device travelling in a vehicle traversing a road network, the device being in an unknown orientation within the vehicle in which the device is traveling;

determining using the machine-implemented processor associated with the device times at which the device changes orientation within the vehicle, at least some of the determined times being during motion of the vehicle;

forming during traversal of the road network time segments of the measurements of acceleration by bounding the segments based on the determined times at which the device changes orientation within the vehicle; and

for each segment of a plurality of the formed time segments, estimating an orientation of the device within the vehicle, and inferring the vehicular trajectory characteristics using the estimated orientation of the device and the acceleration-related measurements for the segment.

33. The method of claim 32 wherein determining the times at which the device changes orientation within the vehicle includes using at least one of (a) a change in a manifestation of gravity in the measurements of acceleration, (b) presence of a predetermined pattern of acceleration-related data, (c) presence of a predetermined pattern of gyroscope-related data, and (d) detection of sudden change in orientation in an orientation-related signal associated with the device.