Method and system for identifying vehicle collisions using sensor data

• US 9,925,940 B1
• Filed: 05/23/2016
• Issued: 03/27/2018
• Est. Priority Date: 07/13/2015
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Christensen, Scott T., Dosher, David J., Menon, Sunish Shreenarayan, Dunham, Susan M.
• Primary Examiner(s): Lin, Abby Y
• Application Number:
  US15/161,524
• Time in Patent Office: 673 Days
• CPC Class Codes: B60Q 5/006 indicating risk of collision between vehicles or with pedestrians
• CPC Class Codes: B60R 2021/0027 Post collision measures, e.g. notifying emergency services
• CPC Class Codes: B60R 2021/01322 comprising variable thresholds, e.g. depending from other collision parameters
• CPC Class Codes: B60R 21/0132 responsive to vehicle motion parameters , e.g. to vehicle longitudinal or transversal deceleration or speed value
• CPC Class Codes: B60R 21/0136 responsive to actual contact with an obstacle , e.g. to vehicle deformation, bumper displacement or bumper velocity relative to the vehicle monitoring crash strength in combination with passenger seat detection B60R21/01558
• CPC Class Codes: B60W 2040/0818 Inactivity or incapacity of driver
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G08G 1/205 Indicating the location of the monitored vehicles as destination, e.g. accidents, stolen, rental
• CPC Class Codes: H04L 51/046 Interoperability with other network applications or services
• CPC Class Codes: H04W 4/90 Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
• CPC Class Codes: H04W 76/50 for emergency connections

Abstract

A method and system may identify vehicle collisions in real-time or at least near real-time based on statistical data collected from previous vehicle collisions. A user'"'"'s portable computing device may obtain sensor data from sensors in the portable computing device and compare the sensor data to a statistical model indicative of a vehicle collision, where the statistical model includes sensor data characteristics which correspond to the vehicle collision. The sensor data characteristics may include several threshold sample rate ranges at which another sensor data characteristic is measured and for each of the threshold sample rate ranges, a different threshold value for the other sensor data characteristic. If the portable computing device identifies a vehicle collision based on the comparison, notifications may be sent to emergency contacts and/or emergency personnel to provide assistance to the user.

Claims

1. A portable computing device for automatically identifying vehicle collisions using sensor data, the portable computing device comprising:

one or more processors;

one or more sensors for receiving sensor data including at least one of;

acceleration data, speed data, position data, pressure data, or rotation data; and

a non-transitory computer-readable memory coupled to the one or more processors, and the one or more sensors, and storing thereon instructions that, when executed by the one or more processors, cause the portable computing device to;

obtain the sensor data from the one or more sensors, wherein a user of the portable computing device is travelling in a vehicle;

obtain statistical data indicative of a vehicle collision including (i) a sensor data characteristic which corresponds to the vehicle collision, wherein the sensor data characteristic is one of;

acceleration, change in speed, change in pressure, or rotation, (ii) a plurality of threshold sample rate ranges for measuring the sensor data characteristic, and (iii) threshold values for the sensor data characteristic which correspond to each of the plurality of threshold sample rate ranges;

identify one of the plurality of threshold sample rate ranges corresponding to a sample rate included in the obtained sensor data;

determine whether a value for the sensor data characteristic included in the obtained sensor data exceeds the threshold value corresponding to the identified threshold sample rate range; and

when the value for the sensor data characteristic included in the obtained sensor data exceeds the threshold value corresponding to the identified threshold sample rate range, determine that a collision has occurred involving the vehicle.

2. The portable computing device of claim 1, wherein the instructions further cause the portable computing device to transmit an emergency notification to one or more emergency contacts for the user.

3. The portable computing device of claim 1, further comprising a user interface, wherein the instructions further cause the portable computing device to:

cause a collision request to be displayed on the user interface asking the user to verify that a vehicle collision occurred; and

in response to receiving an indication from the user that the collision occurred or when the user does not respond within a predetermined amount of time, transmit an emergency notification to emergency personnel, wherein the emergency notification includes a location of the user and at least some of the sensor data.

4. The portable computing device of claim 1, wherein the obtained sensor data is a first set of sensor data, and to obtain statistical data indicative of a vehicle collision, the instructions cause the portable computing device to, during a training period:

obtain a plurality of second sets of sensor data, wherein at least one of the plurality of second sets of sensor data corresponds to the vehicle collision and wherein at least one of the plurality of second sets of sensor data does not correspond to the vehicle collision; and

determine a value for the sensor data characteristic of the at least one second set of sensor data which corresponds to the vehicle collision.

5. The portable computing device of claim 4, wherein the at least one second set of sensor data which does not correspond to the vehicle collision includes sensor data indicative of the portable computing device being manipulated by the user, and the instructions cause the portable device to adjust the value for the sensor data characteristic which corresponds to the vehicle collision based on the sensor data indicative of the portable computing device being manipulated by the user.

6. The portable computing device of claim 1, wherein the plurality of threshold sample rate ranges at which the sensor data characteristic is measured includes a plurality of threshold sample rate ranges at which acceleration is measured and the different threshold value for the sensor data characteristic which corresponds to each of the plurality of threshold sample rate ranges includes a different threshold acceleration corresponding to each of the plurality of threshold sample rate ranges;

and

wherein the statistical data further includes a threshold change in speed and when the acceleration included in the obtained sensor data does not exceed the threshold acceleration, the instructions cause the portable computing device to;

determine whether a change in speed included in the obtained sensor data exceeds the threshold change in speed; and

when the change in speed included in the obtained sensor data exceeds the threshold change in speed, determine whether a collision has occurred involving the vehicle based on the acceleration and the change in speed.

7. The portable computing device of claim 6, wherein to determine whether a collision has occurred based on the acceleration and the change in speed, the instructions cause the portable computing device to:

assign an acceleration score based on the acceleration and the sample rate;

assign a speed score based on the change in speed;

combine the acceleration score and the speed score into an overall collision likelihood score;

determine whether the overall collision likelihood score exceeds a threshold collision score; and

when the overall collision likelihood score exceeds the threshold collision score, determine that a collision has occurred involving the vehicle.

8. The portable computing device of claim 1, wherein the instructions further cause the portable computing device to:

obtain sensor data from a plurality of sets of sensors corresponding to a plurality of portable computing devices, wherein a plurality of users of the plurality of portable computing devices are travelling in the vehicle;

for each set of sensor data, compare the obtained sensor data to the statistical data indicative of the vehicle collision; and

determine that a collision has occurred involving the vehicle based on the comparison.

9. The portable computing device of claim 1, wherein the instructions further cause the portable computing device to:

determine at least one of (i) a severity of the vehicle collision or (ii) a type of the vehicle collision based on the comparison of the obtained sensor data to the statistical data.

10. A computer-implemented method for automatically identifying vehicle collisions using sensor data, the method executed by one or more processors programmed to perform the method, the method comprising:

sensing, at one or more sensors communicatively coupled to a portable computing device, information about the portable computing device;

obtaining, at one or more processors, sensor data from the one or more sensors communicatively coupled to the portable computing device, wherein a user of the portable computing device is travelling in a vehicle;

obtaining, at the one or more processors, statistical data indicative of a vehicle collision including (i) a sensor data characteristic which corresponds to the vehicle collision wherein the sensor data characteristic is one of;

acceleration, change in speed, change in pressure, or rotation, (ii) a plurality of threshold sample rate ranges for measuring the sensor data characteristic, and (iii) threshold values for the sensor data characteristic which correspond to each of the plurality of threshold sample rate ranges;

identifying, by the one or more processors, one of the plurality of threshold sample rate ranges corresponding to a sample rate included in the obtained sensor data;

determining, by the one or more processors, whether a value for the sensor data characteristic included in the obtained sensor data exceeds the threshold value corresponding to the identified threshold sample rate range; and

when the value for the sensor data characteristic included in the obtained sensor data exceeds the threshold value corresponding to the identified threshold sample rate range, determining, by the one or more processors, that a collision has occurred involving the vehicle.

11. The method of claim 10, further comprising:

causing, by the one or more processors, an emergency notification to be transmitted to one or more emergency contacts for the user.

12. The method of claim 10, further comprising:

causing, by the one or more processors, a collision request to be displayed on the portable computing device asking the user to verify that a vehicle collision occurred; and

in response to receiving an indication from the user that the collision occurred or when the user does not respond within a predetermined amount of time, causing, by the one or more processors, an emergency notification to be transmitted to emergency personnel, wherein the emergency notification includes a location of the user and at least some of the sensor data.

13. The method of claim 10, wherein the obtained sensor data is a first set of sensor data, and wherein obtaining statistical data indicative of a vehicle collision includes, during a training period:

obtaining, at the one or more processors, a plurality of second sets of sensor data, wherein at least one of the plurality of second sets of sensor data corresponds to the vehicle collision and wherein at least one of the plurality of second sets of sensor data does not correspond to the vehicle collision; and

determining, by the one or more processors, a value for the sensor data characteristic of the at least one second set of sensor data which corresponds to the vehicle collision.

14. The method of claim 13, wherein the at least one second set of sensor data which does not correspond to the vehicle collision includes sensor data indicative of the portable computing device being manipulated by the user, and the method further comprises:

adjusting, by the one or more processors, the value for the sensor data characteristic which corresponds to the vehicle collision based on the sensor data indicative of the portable computing device being manipulated by the user.

15. The method of claim 10, wherein the plurality of threshold sample rate ranges at which the sensor data characteristic is measured includes a plurality of threshold sample rate ranges at which the acceleration is measured and the different threshold value for the sensor data characteristic which corresponds to each of the plurality of threshold sample rate ranges includes a different threshold acceleration corresponding to each of the plurality of threshold sample rate ranges;

and

wherein the statistical data further includes a threshold change in speed and when the acceleration included in the obtained sensor data does not exceed the threshold acceleration, the method includes;

determining, by the one or more processors, whether a change in speed included in the obtained sensor data exceeds the threshold change in speed; and

when the change in speed included in the obtained sensor data exceeds the threshold change in speed, determining, by the one or more processors, whether a collision has occurred involving the vehicle based on the acceleration and the change in speed.

16. The method of claim 15, wherein determining whether a collision has occurred based on the acceleration and the change in speed includes:

assigning, by the one or more processors, an acceleration score based on the acceleration and the sample rate;

assigning, by the one or more processors, a speed score based on the change in speed;

combining, by the one or more processors, the acceleration score and the speed score into an overall collision likelihood score;

determining, by the one or more processors, whether the overall collision likelihood score exceeds a threshold collision score; and

when the overall collision likelihood score exceeds the threshold collision score, determining, by the one or more processors, that a collision has occurred involving the vehicle.

17. The method of claim 10, further comprising:

obtaining sensor data from a plurality of sets of sensors corresponding to a plurality of portable computing devices, wherein a plurality of users of the plurality of portable computing devices are travelling in the vehicle;

for each set of sensor data, comparing the obtained sensor data to the statistical data indicative of the vehicle collision; and

determining that a collision has occurred involving the vehicle based on the comparison.

18. The method of claim 10, further comprising:

determining, by the one or more processors, at least one of (i) a severity of the vehicle collision or (ii) a type of the vehicle collision based on the comparison of the obtained sensor data to the statistical data.