Adaptive driver identification fusion

• US 9,663,112 B2
• Filed: 03/23/2015
• Issued: 05/30/2017
• Est. Priority Date: 10/09/2014
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Kristinsson, Johannes Geir, Abou-Nasr, Mahmoud A., Dutta, Arun, Feldkamp, Timothy Mark, Baker, Ryan Lee
• Primary Examiner(s): HOLLOWAY III, EDWIN C
• Application Number:
  US14/665,302
• Publication Number:
  US 20160101783A1
• Time in Patent Office: 799 Days
• Field of Search: 340 58
• CPC Class Codes: B60R 16/037 for occupant comfort , e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
• CPC Class Codes: B60W 2040/0809 Driver authorisation; Driver identity check
• CPC Class Codes: B60W 2540/043 Identity of occupants
• CPC Class Codes: B60W 40/08 related to drivers or passengers

Abstract

A vehicle system includes a driver identification fusion module programmed to receive a confidence level from a plurality of identification modules. Each confidence level indicates the likelihood that a driver of a vehicle is a particular person. The driver identification fusion module is programmed to aggregate the confidences levels received from the plurality of identification modules and output an aggregated confidence level signal representing an identity of the driver based at least in part on the confidence levels received from the plurality of identification modules.

Claims

1. A vehicle system comprising:

a controller including a driver identification fusion module programmed to receive an individual confidence level from each of a plurality of identification modules, each individual confidence level indicating a likelihood that a driver of a vehicle is a particular person, wherein the driver identification fusion module is programmed to aggregate the individual confidence levels received from the plurality of identification modules and output an aggregated confidence level signal representing an identity of the driver based at least in part on the individual confidence levels received from the plurality of identification modules, and

wherein the controller further includes a prediction module programmed to determine a common setting with regard to at least two known drivers, and when the aggregate confidence level is below a predetermined threshold, the prediction module is programmed to output a signal to the driver identification fusion module identifying the common setting and wherein the controller controls at least one vehicle subsystem according to the common setting.

2. The vehicle system of claim 1, wherein the driver identification fusion module is programmed to identify the driver based at least in part on a driver profile stored in a driver database.

3. The vehicle system of claim 1, wherein the plurality of identification modules includes at least one of a voice recognition module, a face recognition module, a fingerprint recognition module, a phone detection module, and a wireless device detection module.

4. The vehicle system of claim 1, further comprising a training module programmed to generate a driver profile, wherein the training module is programmed to perform supervised training when the aggregate confidence level is below the predetermined threshold and unsupervised training when the aggregate confidence level is above the predetermined threshold.

5. The vehicle system of claim 4, wherein the training module is programmed to store the driver profile in a driver database.

6. The vehicle system of claim 4, wherein the training module is programmed to continuously update the driver profile based at least in part on signals generated by at least one of the plurality of identification modules.

7. The vehicle system of claim 1, wherein the driver identification module is programmed to output a control signal to control at least one vehicle subsystem based on the signal output by the prediction module.

8. The vehicle system of claim 1, wherein the driver identification fusion module is programmed to output a control signal to at least one vehicle subsystem.

9. The vehicle system of claim 8, wherein the control signal includes a setting associated with the identity of the driver determined by the driver identification fusion module when the aggregate confidence level is above the predetermined threshold.

10. A method comprising:

collecting, via a plurality of identification modules, driver information associated with a driver of a vehicle;

determining a likely identity of the driver based at least in part on the driver information;

generating, via each of the plurality of identification modules, an individual confidence level associated with the driver, wherein the individual confidence level represents a likelihood that the driver of the vehicle is a particular person;

aggregating the individual confidence levels received from the plurality of identification modules at a driver identification fusion module;

generating an aggregated confidence level signal representing an identity of the driver based at least in part on the plurality of individual confidence levels;

detecting that the aggregate confidence level is below a predetermined threshold; and

when the aggregate confidence level is below the predetermined threshold, determining a common setting with regard to at least two known drivers and controlling at least one vehicle subsystem according to the common setting.

11. The method of claim 10, further comprising:

when the aggregate confidence level is above the predetermined threshold, generating a control signal to control the at least one vehicle subsystem, wherein the control signal represents a setting associated with the driver identified different from the common setting and applying the setting associated with the driver identified instead of the common setting.

12. The method of claim 10, wherein determining the identity of the driver includes accessing a driver profile stored in a driver database.

13. The method of claim 10, further comprising:

detecting an unknown driver;

generating a driver profile associated with the unknown driver; and

storing the driver profile in a driver database.

14. The method of claim 12, further comprising continuously updating the driver profile based at least in part on signals generated by at least one of the plurality of identification modules by performing supervised training when the aggregate confidence level is below the predetermined threshold and unsupervised training when the aggregate confidence level is above the predetermined threshold.

15. The method of claim 10, further comprising:

generating, via the driver identification fusion module, a control signal to control at least one vehicle subsystem based on the signal identifying the common setting.

16. The method of claim 10, further comprising:

generating, via the driver identification fusion module, a control signal; and

transmitting the control signal to at least one vehicle subsystem.

17. The method of claim 16, wherein the control signal is generated to represent a setting, different from the common setting, associated with the identity of the driver determined by the driver identification fusion module when the aggregate confidence level exceeds the predetermined threshold.

18. A vehicle system comprising:

a controller having a plurality of identification modules including;

a driver identification fusion module programmed to receive an individual confidence level from each of at least one of the plurality of identification modules, each individual confidence level indicating a likelihood that a driver of a vehicle is a particular person, wherein the driver identification fusion module is programmed to aggregate the confidence levels received from the plurality of identification modules and output an aggregated confidence level signal representing an identity of the driver based at least in part on the individual confidence levels received from at least one of the plurality of identification modules;

a prediction module programmed to determine a common setting with regard to at least two known drivers, and when the aggregate confidence level is below a predetermined threshold, the prediction module is programmed to output a signal to the driver identification fusion module identifying the common setting and wherein the controller controls at least one vehicle subsystem according to the common setting; and

a training module programmed to generate a driver profile and store the driver profile in a driver database.

19. The vehicle system of claim 18, wherein the training module is programmed to continuously update the driver profile based at least in part on signals generated by at least one of the plurality of identification modules, wherein the training module is programmed to perform supervised training when the aggregate confidence level is below the predetermined threshold and unsupervised training when the aggregate confidence level is above the predetermined threshold.