Enriching driving experience with cloud assistance

• US 9,092,984 B2
• Filed: 03/14/2013
• Issued: 07/28/2015
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Bahl, Paramvir, Kandula, Srikanth, Iyer, Anand Padmanabha
• Primary Examiner(s): Cheung, Mary
• Assistant Examiner(s): WONG, YUEN H
• Application Number:
  US13/830,732
• Publication Number:
  US 20140278047A1
• Time in Patent Office: 866 Days
• Field of Search: 701/301
• US Class Current: 1/1
• CPC Class Codes: G08G 1/161 Decentralised systems, e.g. inter-vehicle communication
• CPC Class Codes: G08G 1/164 Centralised systems, e.g. external to vehicles
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

Described is a technology by which driver safety technology such as collision detection is implemented via mobile device (e.g., smartphone) sensors and a cloud service that processes data received from vehicles associated with the devices. Trajectory-related data is received at the cloud service and used to predict collisions between vehicles and/or lane departures of vehicles. To operate the service in real-time with low latency, also described is dividing driving areas into grids, e.g., based upon traffic density, having parallel grid servers each responsible for only vehicles in or approaching its own grid, and other parallel/distributed mechanisms of the cloud service.

Claims

1. A method performed at least in part on at least one processor comprising:

receiving, at a service, a wireless communication that is sent from a mobile device related to a vehicle, the wireless communication comprising information detected via a sensor set coupled to the mobile device and corresponding to a trajectory of the vehicle and an identifier of the mobile device;

hashing, by the at least one processor, the identifier to determine a vehicle prediction component corresponding to the mobile device;

determining, by the at least one processor, from the information detected at least one grid server using the vehicle prediction component, each grid server corresponding to a location in which the vehicle is in or is projected to possibly be in before updated information from the mobile device is received;

determining, by the at least one processor, from the information detected whether the vehicle is at risk of a collision; and

responsive to a determination that the vehicle is at risk of the collision, sending alert-related data to the vehicle.

2. The method of claim 1 wherein determining from the information whether the vehicle is at risk of a collision comprises computing, based upon the information and other received information, whether the vehicle is too close to another vehicle.

3. The method of claim 1 wherein determining from the information whether the vehicle is at risk of a collision computing based upon the information whether the vehicle is in a state of lane departure.

4. The method of claim 1 wherein the information comprises coordinates and speed-related data obtained via sensor data of the mobile device, and further comprising computing the trajectory of the vehicle at the service based at least in part on the coordinates and speed-related data.

5. The method of claim 4 wherein computing the trajectory of the vehicle further comprises, using at least one of:

course data, acceleration data, rotation data or yaw data.

6. The method of claim 4 wherein computing the trajectory of the vehicle further comprises, using at least one of:

route history data, traffic estimate data, road segment data or roadway data.

7. The method of claim 1 further comprising:

dividing a set of locations into grids, including determining areas of the grids based at least in part on vehicle density within the areas.

8. The method of claim 1 further comprising:

performing map matching using known road segment information to place the vehicle in real time at a location based on current and previous information detected via the sensor set.

9. The method of claim 1 further comprising:

predicting whether a user of the vehicle is likely to continue along a same roadway or a direction in which the user will turn using prior trip data from the same user.

10. The method of claim 1 further comprising:

receiving a request from the mobile device at the service; and

responding to the request with data obtained at the service, including data related to at least one of generating a map, generating traffic information, or traffic planning.

11. A system comprising:

a service implemented on at least one server and configured to receive a communication from a mobile device related to a vehicle, the communication including information detected via a sensor set coupled to the mobile device and corresponding to a trajectory of the vehicle and an identifier of the mobile device, the service further configured to;

hash, by at least one processor, the identifier to determine a server associated with a predicted location of the vehicle;

determine, by the at least one processor, from the information detected at least one grid server using the vehicle prediction component, each grid server corresponding to a location in which the vehicle is in or is projected to possibly be in before updated information from the mobile device is received;

compute, by the at least one processor, whether the vehicle is at risk of collision, and responsive to a determination that the vehicle is at risk, to output alert-related data for communication to the vehicle.

12. The system of claim 11 wherein the service is further configured to output the alert-related data to a recipient, including a recipient not in the vehicle, or a recipient in the vehicle based upon a distance of the vehicle to a location.

13. The system of claim 11 wherein the mobile device comprises at least one of a smartphone or device built into the vehicle.

14. The system of claim 11 further comprising:

at least one other server comprising a spatial store and a query engine that share information in a common memory.

15. The system of claim 11 wherein the service is configured to determine whether the vehicle is in a state of lane departure based upon the information detected via the sensor set coupled to the mobile device.

16. The system of claim 11 wherein the service is configured to compensate for inaccuracies in the information detected via the sensor set, including by combining the information detected via the sensor set with at least one of:

information detected from one or more other sensors, information received from one or more other vehicles, or historical information associated with the vehicle or another mobile device.

17. The system of claim 11 wherein the service is configured to output the alert-related data for communication to a plurality of vehicles, in which the plurality of vehicles are determined based upon at least one of:

velocity, distance, location estimation error, cloud service latency, or server computing delay.

18. The system of claim 11 wherein the service is further configured to divide a set of locations into grids, and determine areas of the grids based at least in part on vehicle density within the areas.

19. The system of claim 11 wherein the service is further configured to compute the trajectory of the vehicle using at least one of route history data, traffic estimate data, road segment data or roadway data.

20. The system of claim 11 wherein the service is further configured to predict whether a user of the vehicle is likely to continue along a same roadway or a direction in which the user will turn using prior trip data from the user associated with the mobile device.