Detecting vehicle collisions based on moble computing device data

• US 9,934,625 B1
• Filed: 01/31/2017
• Issued: 04/03/2018
• Est. Priority Date: 01/31/2017
• Status: Active Grant

• Current Assignee: Uber Technologies, Inc.
• Original Assignee: Uber Technologies, Inc.
• Inventors: Wahba, Karim, Tyagi, Dhruv, Beinstein, Andrew, Prasad, Amritha, Lawrence, Audrey, Alvarez, Jose, Pennington, Steve, Trachtman, Corin
• Primary Examiner(s): Zimmerman, Brian
• Assistant Examiner(s): Tran, Thang
• Application Number:
  US15/421,417
• Time in Patent Office: 427 Days
• Field of Search: 340436, 340439
• CPC Class Codes: B60R 2021/0027 Post collision measures, e.g. notifying emergency services
• CPC Class Codes: B60R 21/00 Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks safety belts or body harnesses in vehicles B60R22/00; seats constructed to protect the occupant from the effect of abnormal g-forces, e.g. crash or safety seats, B60N2/42; energy-absorbing arrangements for hand wheels for steering vehicles B62D1/11; energy-absorbing arrangements for vehicle steering columns B62D1/19
• CPC Class Codes: G06Q 10/00 Administration; Management
• 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 network computing system receives local device data from a mobile computing device of a person within a vehicle. The local device data may include sensor data from one or more sensors of the mobile computing device, and location data determined from a position-determination resource of the mobile computing device. The network computing system may detect a vehicle collision event based on the local device data. Additionally, the network computing system may determine a classification of the vehicle collision event based on the local device data.

Claims

1. A method for remotely evaluating collision events of vehicles, the method being implemented by one or more processors of a network computing system and comprising:

maintaining, on the network computing system, profile information for each of a plurality of users, the profile information associating each user with an account identifier of a network service;

arranging a transport to be provided in which multiple occupants of a transport vehicle are users of the network service;

while the transport is in progress, receiving local device data transmitted from a mobile computing device of at least one of multiple occupants of the transport vehicle, the local device data including (i) sensor data from one or more sensors of the mobile computing device, and (ii) location data determined from a position-determination resource of the mobile computing device;

detecting a vehicle collision event based on the local device data;

determining a classification of the vehicle collision event based on the local device data, the classification including at least one of (i) a first level in which a likelihood of injury is below a first threshold probability, and (ii) a second level in which a likelihood of injury is above a second threshold probability;

automatically initiating performance of an action for each of the multiple occupants of the transport vehicle, to mitigate a consequence of the vehicle collision event to that occupant;

wherein automatically initiating performance of the action for each of the multiple occupants of the transport vehicle includes;

retrieving profile information that is specific to each of the multiple occupants of the transport vehicle based on the account identifier associated with that occupant; and

for each of the multiple occupants, determining the action to perform based on the classification of the vehicle collision event and the retrieved profile information that is specific to that occupant.

2. The method of claim 1, wherein the sensor data includes movement data obtained from at least one of an accelerometer or gyroscope of the mobile computing device.

3. The method of claim 1, wherein at least one of detecting the vehicle collision event or determining the classification of the vehicle collision event includes determining at least one of a velocity or acceleration profile of the transport vehicle over position and/or time.

4. The method of claim 1, wherein determining the classification of the vehicle collision event includes comparing a feature set of the detected vehicle collision event to a collection of models which define multiple classes of vehicle collisions.

5. The method of claim 1, wherein the sensor data includes environmental sensor data obtained from at least one of a barometer, thermometer or microphone of the mobile computing device.

6. The method of claim 5, wherein at least one of detecting the vehicle collision event or determining a classification of the vehicle collision event includes processing the environmental sensor data to detect one or more of (i) an airbag deployment, (ii) a glass within the transport vehicle breaking, and/or (iii) an utterance for assistance from a human.

7. The method of claim 1, further comprising initiating one or more operations to corroborate at least one of the vehicle collision event or the classification of the vehicle collision event.

8. The method of claim 7, wherein initiating one or more operations includes monitoring the mobile computing device of each of the multiple occupants of the transport vehicle to detect a user interaction that is indicative of a health of an occupant or a state of the transport vehicle.

9. The method of claim 8, wherein initiating one or more operations includes monitoring the mobile computing device of each of the multiple occupants of the transport vehicle for placement of a phone call.

10. The method of claim 1, wherein receiving local device data includes:

causing the mobile computing device to obtain and/or transmit the local device data in accordance with one or more timing parameters.

11. The method of claim 10, wherein receiving local device data includes:

causing the mobile computing device to change the one or more timing parameters in order to provide the network computing system with more sensor data and/or location data in a lesser amount of time.

12. The method of claim 10, wherein the one or more timing parameters include a sampling rate by which the mobile computing device obtains the sensor data and/or the location data from a respective sensor and/or position-determination resource.

13. The method of claim 10, wherein the one or more timing parameters include a transmission or data rate by which the mobile computing device transmits the local device data to the network computing system.

14. The method of claim 10, wherein the one or more timing parameters include a time until a next transmission, and wherein the method further comprises:

in response to detecting the vehicle collision event, causing the time until next transmission of at least one of the sensor data and the local device data to be reduced on the mobile computing.

15. The method of claim 10, further comprising:

detecting, on the mobile computing device, one or more predetermined conditions which are indicative of an imminent or immediate vehicle collision; and

changing, on the mobile computing device, the one or more timing parameters in order to provide the network computing system with more sensor data and/or location data in a lesser amount of time.

16. The method of claim 15, further comprising processing, on the network computing system, the local device data on a dedicated or configured computing resource when the one or more timing parameters are changed.

19. The method of claim 1, wherein automatically initiating performance of the action includes:

automatically arranging additional transport for at least one of the multiple occupants to complete that occupant'"'"'s trip.

20. The method of claim 1, further comprising:

corroborating the classification of the vehicle collision event by identifying another use of the network service that is near the detected vehicle collision event, and sending a communication to the mobile computing device of that user to obtain information about the vehicle collision event.

17. A non-transitory computer readable medium that stores instructions, which when executed by one or more processors of a network computing system, cause the network computing system to perform operations that include:

maintaining, on the network computing system, profile information for each of a plurality of users, the profile information associating each user with an account identifier of a network service;

arranging a transport to be provided in which multiple occupants of a transport vehicle are users of the network service;

while the transport is in progress, receiving local device data transmitted from a mobile computing device of at least one of multiple occupants of the transport vehicle, the local device data including (i) sensor data from one or more sensors of the mobile computing device, and (ii) location data determined from a position-determination resource of the mobile computing device;

detecting a vehicle collision event based on the local device data;

determining a classification of the vehicle collision event based on the local device data, the classification including at least one of (i) a first level in which a likelihood of injury is below a first threshold probability, and (ii) a second level in which a likelihood of injury is above a second threshold probability;

automatically initiating performance of an action for each of the multiple occupants of the transport vehicle, to mitigate a consequence of the vehicle collision event to that occupant;

wherein automatically initiating performance of the action for each of the multiple occupants of the transport vehicle includes;

retrieving profile information that is specific to each of the multiple occupants of the transport vehicle based on the account identifier associated with that occupant; and

for each of the multiple occupants, determining the action to perform based on the classification of the vehicle collision event and the retrieved profile information that is specific to that occupant.

18. A network computer system comprising:

a memory to store a set of instructions;

one or more processors to access the set of instructions to;

maintain, on a network computing system, profile information for each of a plurality of users, the profile information associating each user with an account identifier of a network service;

arrange a transport to be provided in which multiple occupants of a transport vehicle are users of the network service;

while the transport is in progress, receive local device data transmitted from a mobile computing device of at least one of multiple occupants of the transport vehicle, the local device data including (i) sensor data from one or more sensors of the mobile computing device, and (ii) location data determined from a position-determination resource of the mobile computing device;

detect a vehicle collision event based on the local device data;

determine a classification of the vehicle collision event based on the local device data, the classification including at least one of (i) a first level in which a likelihood of injury is below a first threshold probability, and (ii) a second level in which a likelihood of injury is above a second threshold probability;

automatically initiate performance of an action for each of the multiple occupants of the transport vehicle, to mitigate a consequence of the vehicle collision event to that occupant;

wherein the one or more processors automatically initiate performance of the action for each of the multiple occupants of the transport vehicle by;

retrieving profile information that is specific to each of the multiple occupants of the transport vehicle based on the account identifier associated with that occupant; and

for each of the multiple occupants, determining the action to perform based on the classification of the vehicle collision event and the retrieved profile information that is specific to that occupant.