Method and system to control vehicle based on predicting destination

• US 10,584,976 B2
• Filed: 06/06/2017
• Issued: 03/10/2020
• Est. Priority Date: 12/20/2016
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Motors Corporation (Kia Corp.)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Kim, Bogeun, Bang, Sung Hoon
• Primary Examiner(s): Almatrahi, Faris S
• Assistant Examiner(s): Testardi, David A
• Application Number:
  US15/615,616
• Publication Number:
  US 20180172467A1
• Time in Patent Office: 1,008 Days
• CPC Class Codes: F02D 41/027 to purge or regenerate the exhaust gas treating apparatus
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3605 Destination input or retrieval
• CPC Class Codes: G01C 21/3617 using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
• CPC Class Codes: G01C 21/3697 Output of additional, non-guidance related information, e.g. low fuel level G01C21/3679 takes precedence
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/096888 where input information is obtained using learning systems, e.g. history databases
• CPC Class Codes: G08G 1/096894 where input is assisted by the navigation device, i.e. the user does not type the complete name of the destination, e.g. using zip codes, telephone numbers, progressively selecting from initial letters
• CPC Class Codes: G08G 1/20 Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles

Abstract

Provided are a method and a system for controlling at least one feature of a vehicle based on a destination predicted when a driver of the vehicle does not input a specific destination to a navigation system of the vehicle. A driving pattern is determined using driving information of a vehicle. A driving model corresponding to the driving pattern among pre-stored driving models is determined. A destination of the determined driving model is identified as a prediction destination. Control signal corresponding to the prediction destination for controlling at least one feature of the vehicle is generated for performing a vehicle operation according to the vehicle control information.

Claims

1. A method of controlling a vehicle based on predicting a destination, the method comprising:

determining a driving pattern by using driving information received from a vehicle of a user;

determining a user driving model corresponding to the driving pattern among pre-stored driving models;

determining a destination of the determined user driving model as a predicted destination;

generating vehicle control information corresponding to the predicted destination;

performing a vehicle operation according to the vehicle control information by providing the vehicle control information to the vehicle;

applying, when the vehicle arrives at the predicted destination, driving pattern information of the vehicle while driving to the predicted destination and the destination to the pre-stored user driving model;

learning the user driving model at least by determining a destination of which the number of visiting times is equal to or larger than the number of setting times for a set period as a first destination, determining a destination of which the number of visiting times is smaller than the number of setting times for the set period as a second destination, and distinguishing whether the destination included in the user driving model is the first destination or the second destination; and

maintaining or changing the pre-stored user driving model corresponding to the driving pattern,

wherein the vehicle control information includes DPF regeneration prohibition in the case of the first destination and includes DPF regeneration permission in the case of the second destination.

2. The method of claim 1, wherein:

the number of the setting times used as a criterion for judging whether the destination is the living destination or the activity destination is varied based on previous visiting records.

3. The method of claim 1, wherein:

the vehicle control information has different control items in the case of the first destination and in the case of the second destination.

4. The method of claim 1, wherein:

the pre-stored driving models include the user driving model generated by using the driving information of the user and an external driving model generated by using driving information of each of other drivers.

5. The method of claim 4, further comprising:

determining an external model group that matches personal information received from the user and registering the user as the corresponding external model group,

wherein the external driving model among the pre-stored driving models is a user driving model of at least one group member among group members of the external model group in which the corresponding user is registered.

6. The method of claim 5, wherein:

the personal information used for judging the external model group includes residence (area), age, and gender and further includes hobby and family members.

7. A system for controlling a vehicle based on predicting a destination, the system comprising:

a receiving unit configured to receive driving information from each vehicle;

a driver identifying unit configured to identify a vehicle or a driver transmitting the driving information;

a destination predicting unit configured to determine a driving pattern through driving information which is currently received from a vehicle of a first driver, find a user driving model corresponding to the determined driving pattern among pre-stored driving models, and judge the destination included in the found user driving model as a predicted destination;

a vehicle control information generating unit configured to generate vehicle control information corresponding to the destination predicted by the destination predicting unit; and

a user model learning unit configured to apply, when the vehicle arrives at the predicted destination, driving pattern information of the vehicle while driving to the predicted destination and the destination to the user driving model, learn the user driving model, and maintain or change the user driving model corresponding to the driving pattern,

wherein the user model learning unit judges a destination of which the number of visiting times is equal to or larger than the number of setting times for the set period as a first destination, determines a destination of which the number of visiting times is smaller than the number of setting times for the set period as a second destination, and distinguishes whether the destination included in the user driving model is the first destination or the second destination, when learning the user driving model,

wherein the vehicle control information has different control items in the case of the first destination and in the case of the second destination, and

wherein the vehicle control information includes DPF regeneration prohibition in the case of the first destination and includes DPF regeneration permission in the case of the second destination.

8. The system of claim 7, wherein:

the pre-stored driving models include the user driving model generated by using the driving information of the user and an external driving model generated by using each of other drivers.

9. The system of claim 7, further comprising:

an external model managing unit configured to register the user as a group member in an external model group having the highest association with personal information received from the user, and manage the registered external model group to be changed when the personal information is changed,

wherein the external driving model is a user driving model of at least one group member among group members in the external model group in which the corresponding user is registered.

10. The system of claim 9, wherein:

the user model learning unit reflects the changed user driving model to the external driving model of the external model group to which the corresponding member belongs, when the user driving model is changed by learning.