Accurately determining real time parameters describing vehicle motion based on multiple data sources

• US 10,373,077 B2
• Filed: 10/12/2016
• Issued: 08/06/2019
• Est. Priority Date: 10/13/2015
• Status: Active Grant

• Current Assignee: Athena Vision, LLC
• Original Assignee: Athena Vision, LLC
• Inventors: Rajani, Purshotam, Nukala, Gaurav R., Kannan, Gokulnath Coimbatore, Essy, Blair R.
• Primary Examiner(s): Nguyen, Lam S
• Application Number:
  US15/291,455
• Publication Number:
  US 20170103588A1
• Time in Patent Office: 1,028 Days
• Field of Search: 701 37
• CPC Class Codes: B60R 16/0231 Circuits relating to the driving or the functioning of the vehicle monitoring tyres B60C23/00; indicating overspeed B60K31/00; for dash boards B60K37/00, B60Q3/10; for indicating emergencies B60Q1/52; brake control systems B60T; registering or indicating the working of vehicles G07C5/00; measuring distance G01C, e.g. combinations of speed and distance G01C23/00; engine indicators G01L; measuring speed or acceleration G01P
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G07B 13/00 Taximeters measuring distance travelled G01C; measuring time G04
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005

Abstract

A multi-modal meter of a vehicle obtains information from multiple sources to determine the most accurate values of motion parameters of the vehicle. The multi-modal meter obtains data describing motion of a vehicle from various sources including an on-board diagnostics (OBD) and global positioning system (GPS.) The dynamically evaluates the signal sources for their accuracy as the vehicle travels. The multi-modal meter selects different signal sources for different portions of a ride and uses the data from the selected signal sources to determine the most accurate motion parameters. The multi-modal meter use machine learning techniques to generate metadata used by an engine configured to determine the most accurate values of motion parameters of the vehicle.

Claims

1. An apparatus, comprising:

a processor;

one or more local signal sources;

an interface for communicating with external signal sources; and

a non-transitory computer readable storage medium comprising stored instructions, the instructions when executed cause the processor to;

collect data from a plurality of signal sources, the data comprising motion parameters for a portion of a ride of a vehicle, wherein the plurality of signal sources comprises one or more of local signal sources or external signal sources;

for each of a plurality of portions of the ride;

evaluate accuracy of each signal source from the plurality of signal sources by executing a machine learning model on at least a portion of the motion parameters for the portion of the ride to generate metadata for the portion of the ride, wherein the metadata comprises an accuracy threshold value for each signal source from the plurality of signal sources for the portion of the ride;

execute a rule engine to dynamically select one or more signal sources based on the accuracy threshold value of the corresponding signal sources for the portion of the ride;

determine a set of accurate motion parameters describing the portion of the ride based on data received from the one or more selected signal sources, the set of accurate motion parameters comprising one or more of;

speed of the vehicle, time duration of the portion of ride, acceleration of the vehicle, and location of the vehicle.

2. The apparatus of claim 1, further comprising stored instructions that when executed cause the processor to:

dynamically select a signal source for the portion of the ride based on availability of data from the signal source.

3. The apparatus of claim 1, further comprising stored instructions that when executed cause the processor to:

determine a measure of accuracy of data received from one or more signal sources; and

select the signal source for the portion of ride based on the measures of accuracy of the one or more signal sources.

4. The apparatus of claim 1, further comprising stored instructions that when executed cause the processor to:

evaluate an expression based on ride parameters describing the portion of the ride.

5. The apparatus of claim 4, wherein a ride parameter represents one or more of:

make and model of the vehicle,

make and model of the apparatus,

location of the vehicle,

acceleration of the vehicle,

speed of the vehicle,

the time of day,

a day of the week, or

time of at least a portion of the ride.

6. The apparatus of claim 1, further comprising stored instructions that when executed cause the processor to:

determine that the accuracy of a first signal source is below a threshold value;

identify a second signal source having a high measure of accuracy compared to the first signal source; and

calibrate the first signal source based on the data received from the second signal source.

7. The apparatus of claim 1, further comprising stored instructions that when executed cause the processor to:

select a first signal source for receiving parameters of a first portion of a ride of the vehicle;

receive motion parameters describing the first portion of the ride of the vehicle based on data received from the first signal source;

select a second signal source for a second portion of the ride, responsive to determining that the accuracy of the first signal source is below a threshold; and

receive motion parameters describing the second portion of the ride of the vehicle based on data received from the second signal source.

8. The apparatus of claim 1, further comprising, one or more of:

a clock; and

a wireless transceiver.

9. The apparatus of claim 1, wherein a local signal source represents one of:

a GPS chip,

a motion sensor,

an accelerometer,

a magnetometer,

a wireless transceiver, or

a camera.

10. A method for determining accurate motion parameters for a vehicle, the method comprising:

collecting data from a plurality of signal sources, the data comprising motion parameters for a portion of a ride of a vehicle, wherein the plurality of signal sources comprises one or more of local signal sources or external signal sources;

for each of a plurality of portions of the ride;

evaluating accuracy of each signal source from the plurality of signal sources by executing a machine learning model on at least a portion of the motion parameters for the portion of the ride to generate metadata for the portion of the ride, wherein the metadata comprises an accuracy threshold value for each signal source from the plurality of signal sources for the portion of the ride;

executing a rule engine to dynamically select one or more signal sources based on the accuracy threshold value of the corresponding signal sources for the portion of the ride;

determining a set of accurate motion parameters describing the portion of the ride based on data received from the one or more selected signal sources, the set of accurate motion parameters comprising one or more of;

speed of the vehicle, time duration of the portion of ride, acceleration of the vehicle, and location of the vehicle.

11. The method of claim 10, further comprising:

dynamically selecting a signal source for the portion of the ride based on availability of data from the signal source.

12. The method of claim 10, further comprising:

determining a measure of accuracy of data received from one or more signal sources; and

selecting the signal source for the portion of ride based on the measures of accuracy of the one or more signal sources.

13. The method of claim 10, wherein selecting one or more signal sources comprises:

evaluating an expression based on ride parameters describing the portion of the ride.

14. The method of claim 13, wherein a ride parameter represents one or more of:

make and model of the vehicle,

make and model of the apparatus,

location of the vehicle,

acceleration of the vehicle,

speed of the vehicle,

the time of day,

a day of the week, or

time of at least a portion of the ride.

15. The method of claim 10, further comprising:

determining that the accuracy of a first signal source is below a threshold value;

identifying a second signal source having a high measure of accuracy compared to the first signal source; and

calibrating the first signal source based on the data received from the second signal source.

16. The method of claim 10, further comprising:

selecting a first signal source for receiving parameters of a first portion of a ride of the vehicle;

receiving motion parameters describing the first portion of the ride of the vehicle based on data received from the first signal source;

selecting a second signal source for a second portion of the ride, responsive to determining that the accuracy of the first signal source is below a threshold; and

receiving motion parameters describing the second portion of the ride of the vehicle based on data received from the second signal source.

17. The method of claim 10, wherein a local signal source represents one of:

a GPS chip,

a motion sensor,

an accelerometer,

a magnetometer,

a wireless transceiver, or

a camera.

18. A non-transitory computer readable storage medium comprising stored instructions, the instructions when executed cause a processor to:

collect data from a plurality of signal sources, the data comprising motion parameters for a portion of a ride of a vehicle, wherein the plurality of signal sources comprises one or more of local signal sources or external signal sources;

for each of a plurality of portions of the ride;

evaluate accuracy of each signal source from the plurality of signal sources by executing a machine learning model on at least a portion of the motion parameters for the portion of the ride to generate metadata for the portion of the ride, wherein the metadata comprises an accuracy threshold value for each signal source from the plurality of signal sources for the portion of the ride;

execute a rule engine to dynamically select one or more signal sources based on the accuracy threshold value of the corresponding signal sources for the portion of the ride; and

determine a set of accurate motion parameters describing the portion of the ride based on data received from the one or more selected signal sources, the set of accurate motion parameters comprising one or more of;

speed of the vehicle, time duration of the portion of ride, acceleration of the vehicle, and location of the vehicle.

19. The non-transitory computer readable storage medium of claim 18, further comprising stored instructions that when executed cause the processor to:

dynamically select a signal source for the portion of the ride based on availability of data from the signal source.

20. The non-transitory computer readable storage medium of claim 18, further comprising stored instructions that when executed cause the processor to:

determine a measure of accuracy of data received from one or more signal sources; and

select the signal source for the portion of ride based on the measures of accuracy of the one or more signal sources.