Driver identification based on driving maneuver signature
View Patent ↗A system for driver identification comprises a processor and a memory. The processor is configured to receive a driving maneuver signature and to determine a driver identification based at least in part on the driving maneuver signature. The memory is coupled to the processor and is configured to provide the processor with instructions.
1. A system for driver identification, comprising:
a processor configured to:
receive driving data captured during vehicle operation comprising at least a GPS location data;
determine a driving maneuver signature at a specific location from the driving data and the GPS location data, wherein the specific location is common to a plurality of trips in a database of previously stored set of driving maneuver signatures associated with known drivers; and
determine a driver identification based at least in part on the driving maneuver signature at the specific location by comparing the driving maneuver signature with the previously stored set of driving maneuver signatures associated with known drivers at the specific location and determining a known driver with a highest similarity; and
a memory coupled to the processor configured to provide the processor with instructions.
2. The system of claim 1 , wherein the driving maneuver signature comprises a set of vehicle sensor data.
3. The system of claim 2 , wherein the set of sensor data comprises one or more of the following: a longitudinal velocity time profile, a lateral velocity time profile, an angular velocity profile, a steering wheel angle time profile, a steering wheel angle, a gas pedal position, a brake pedal position, a yaw rate, a pitch rate, or a roll rate.
4. The system of claim 1 , wherein the driving maneuver signature is associated with a specific trip.
5. The system of claim 1 , wherein a similarity metric is used to measure similarity between the driving maneuver signature and the previously stored set of driving maneuver signatures.
6. The system of claim 1 , wherein the driving data is segmented into driving maneuvers based on defined periods of time during which vehicle sensor data is active.
7. The system of claim 1 , wherein the driving maneuver signature comprises one or more of the following driving maneuvers: a right/left turn maneuver, a highway on/off ramp maneuver, a U-turn maneuver, a lane change maneuver, a vehicle launching from stop maneuver, a vehicle braking maneuver, a curve-handling maneuver, and a car following maneuver.
8. A method for driver identification, comprising:
receiving driving data captured during vehicle operation comprising at least a GPS location data and a vehicle sensor data;
determining a driving maneuver signature at a specific location from the driving data and the GPS location data, wherein the specific location is common to a plurality of trips in a database of previously stored set of driving maneuver signatures associated with known drivers; and
determining, using a processor, a driver identification based at least in part on the driving maneuver signature at the specific location by comparing the driving maneuver signature with the previously stored set of driving maneuver signatures associated with known drivers at the specific location and determining a known driver with a highest similarity.
9. The method of claim 8 , wherein the driving maneuver signature comprises a set of vehicle sensor data.
10. The method of claim 9 , wherein the set of sensor data comprises one or more of the following: a longitudinal velocity time profile, a lateral velocity time profile, an angular velocity profile, a steering wheel angle time profile, a steering wheel angle, a gas pedal position, a brake pedal position, a yaw rate, a pitch rate, or a roll rate.
11. The method of claim 8 , wherein the driving maneuver signature is associated with a specific trip.
12. The method of claim 8 , wherein a similarity metric is used to measure the similarity between the driving maneuver signature and the previously stored set of driving maneuver signatures.
13. The method of claim 8 , wherein the driving data is segmented into driving maneuvers based on defined periods of time during which vehicle sensor data is active.
14. The method of claim 8 , wherein the driving maneuver signature comprises one or more of the following driving maneuvers: a right/left turn maneuver, a highway on/off ramp maneuver, a U-turn maneuver, a lane change maneuver, a vehicle launching from stop maneuver, a vehicle braking maneuver, a curve-handling maneuver, and a car following maneuver.
15. A computer program product for driver identification, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving driving data captured during vehicle operation comprising at least a GPS location data and a vehicle sensor data;
determining a driving maneuver signature at a specific location from the driving data and the GPS location data, wherein the specific location is common to a plurality of trips in a database of previously stored set of driving maneuver signatures associated with known drivers; and
determining a driver identification based at least in part on the driving maneuver signature at the specific location by comparing the driving maneuver signature with the previously stored set of driving maneuver signatures associated with known drivers at the specific location and determining a known driver with a highest similarity.
16. The computer program product of claim 15 , wherein the driving maneuver signature comprises a set of vehicle sensor data.
17. The computer program product of claim 16 , wherein the set of sensor data comprises one or more of the following: a longitudinal velocity time profile, a lateral a velocity time profile, an angular velocity profile, a steering wheel angle time profile, a steering wheel angle, a gas pedal position, a brake pedal position, a yaw rate, a pitch rate, or a roll rate.
18. The computer program product of claim 15 , wherein the driving maneuver signature is associated with a specific trip.
19. The computer program product of claim 15 , wherein a similarity metric is used to measure the similarity between the driving maneuver signature and the previously stored set of driving maneuver signatures.
20. The computer program product of claim 15 , wherein the driving data is segmented into driving maneuvers based on defined periods of time during which vehicle sensor data is active.
21. The computer program product of claim 15 , wherein the driving maneuver signature comprises one or more of the following driving maneuvers: a right/left turn maneuver, a highway on/off ramp maneuver, a U-turn maneuver, a lane change maneuver, a vehicle launching from stop maneuver, a vehicle braking maneuver, a curve-handling maneuver, and a car following maneuver.