Vehicle mode scheduling with learned user preferences

• US 9,919,715 B2
• Filed: 04/30/2016
• Issued: 03/20/2018
• Est. Priority Date: 04/30/2016
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Tseng, Fling Finn, Prakah-Asante, Kwaku O., Lu, Jianbo, Szwabowski, Steven Joseph, MacNeille, Perry Robinson, Wang, Xiaoming
• Primary Examiner(s): Marc, McDieunel
• Application Number:
  US15/143,558
• Publication Number:
  US 20170313323A1
• Time in Patent Office: 689 Days
• Field of Search: 701 36
• CPC Class Codes: B60K 35/00 Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
• CPC Class Codes: B60W 10/00 Conjoint control of vehicle sub-units of different type or different function for propulsion of purely electrically-propelled vehicles with power supplied within the vehicle B60L50/00 - B60L58/00
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2540/043 Identity of occupants
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 50/0097 Predicting future conditions
• CPC Class Codes: B60W 50/0098 Details of control systems ensuring comfort, safety or stability not otherwise provided for
• CPC Class Codes: B60W 50/082 Selecting or switching between different modes of propelling

Abstract

Systems and methods for vehicle mode scheduling with learned user preferences include monitoring vehicle data when a vehicle changes from a first mode to a second mode. The method also includes analyzing the vehicle data to identify a preference for the second mode during a driving context. Additionally, the method includes generating a recommendation on whether to switch to the second mode while traversing a route based on the vehicle data, and the driving context, and presenting the recommendation to the driver.

Claims

1. A vehicle comprising:

sensors to monitor vehicle data;

memory to store a plurality of classifiers received from a server, the classifiers to predict a preference to transition from a first mode to a second mode based on a subset of the vehicle data; and

a processor communicatively coupled to the memory and the sensors, the processor to;

select one of the plurality of classifiers based on a driving context;

apply the vehicle data to the selected one of the plurality of classifiers to generate a recommendation on whether to switch to the second mode while traversing a route; and

in response to generating the recommendation to switch to the second mode, display the recommendation on an infotainment head unit.

2. A method comprising:

monitoring, by a first processor, vehicle data when a vehicle changes from a first mode to a second mode;

analyzing, by a second processor, the vehicle data to identify a preference for the second mode during a driving context;

generating a recommendation on whether to switch to the second mode while traversing a route based on the vehicle data, and the driving context; and

presenting the recommendation to a driver.

3. The method of claim 2, including, in response to generating the recommendation to switch to the second driving mode, automatically switching the vehicle into the second mode.

4. The method of claim 2, wherein the driving context is at least one of a geographical area, a time of day, or a day of the week.

5. The method of claim 2, wherein to analyze the vehicle data to identify the preference for the second mode during the driving context, the method further includes generating a candidate classifier by applying design of experiment techniques and machine learning techniques to the vehicle data, the classifier to predict the preference to transition from the first mode to the second mode based on a subset of the vehicle data.

6. The method of claim 5, including rejecting the candidate classifier if the candidate classifier does not satisfy an attribute threshold.

7. The method of claim 5, including rejecting the candidate classifier if the candidate classifier does not satisfy a classification threshold.

8. The method of claim 2, wherein generating the recommendation on whether to switch to the second mode while traversing the route based on the vehicle data, and the driving context includes:

selecting a classifier from a plurality of classifiers based on the driving context; and

applying the vehicle data to the selected classifier.

9. A system comprising:

a server configured to analyze vehicle data to identify a preference of a driver to switch from a first mode to a second mode during a driving context;

a vehicle configured to;

monitor vehicle data when the vehicle changes from the first mode to the second mode;

generate a recommendation on whether to switch to the second mode while traversing a route based on a classifier received from the server; and

present the recommendation to the driver.

10. The system of claim 9, including, in response to generating the recommendation to switch to the second driving mode, the vehicle is configured to automatically switch into the second mode.

11. The system of claim 9, wherein the driving context is at least one of a geographical area, a time of day, or a day of a week.

12. The system of claim 9, wherein to analyze the vehicle data to identify the preference for the second mode during the driving context, the server is configured to generate a candidate classifier by applying design of experiment techniques and machine learning techniques to the vehicle data, the classifier to predict the preference to transition from the first mode to the second mode based on a subset of the vehicle data.

13. The system of claim 12, wherein the server is configured to reject the candidate classifier if the candidate classifier does not satisfy an attribute threshold.

14. The system of claim 12, wherein the server is configured to reject the candidate classifier if the candidate classifier does not satisfy a classification threshold.

15. The system of claim 9, wherein to generate the recommendation on whether to switch to the second mode while traversing the route based on the vehicle data, and the driving context, the vehicle is configured to:

select a classifier from a plurality of classifiers received from the server based on the driving context; and

apply the vehicle data to the selected classifier.

16. A method comprising:

by a server;

generating, based on historic vehicle data, a classifier modeling a preference to switch from a first mode to a second mode while the vehicle experiences a set of road conditions;

by a vehicle;

receiving the classifier;

generating a recommendation by applying current vehicle data to the classifier; and

adjusting settings of electronic control units to switch to the second mode while traversing a route based the recommendation.