Granted Patent B2

US 12,565,220 · App. 18/562,495 · Granted Mar 3, 2026

Inventors: Jens Kastens (Tettnang, DE); Heidi Rathgeb (Lindenberg, DE); Alexander Graf (Immenstaad, DE); Nicolas Blum (Julbach, DE); Andrea Agostinelli (Munich, DE); Dominic Schmidt (Karlsruhe, DE)

Assignee: ZF Friedrichshafen AG

B60W50/0098B60W40/09H04W4/025B60W2050/0083B60W2540/215

Abstract

Claims (35)

1 . A method for determining a vehicle configuration ( 24 ) adapted to driving behavior of a person, comprising:

determining a driving profile ( 20 ) of the person, the driving profile ( 20 ) comprising one or both of a speed profile and an acceleration profile of a vehicle ( 10 ) controlled by the person;

determining category values ( 28 ) of the driving profile ( 20 ) for each of a plurality of vehicle configurations ( 24 ), the category values ( 28 ) comprising one or both of an energy consumption and carbon dioxide emissions of each of the plurality of vehicle configurations ( 24 ), wherein the one or both of the energy consumption and the carbon dioxide emissions are calculated from one or both of the speed profile and the acceleration profile of the driving profile ( 20 ); and

determining an optimal vehicle configuration ( 24 ) by ascertaining vehicle configuration values ( 30 ) for each of the plurality of vehicle configurations by weighting the category values ( 28 ) for each of the plurality of vehicle configurations ( 24 ) and selecting an optimal vehicle configuration value ( 30 ) from the vehicle configuration values ( 30 ), the optimal vehicle configuration value ( 30 ) being associated with the optimal vehicle configuration ( 24 ) of the plurality of vehicle configurations ( 24 ).

2 . The method of claim 1 , wherein:

determining the driving profile ( 20 ) comprises using a mobile device ( 14 ) of the person, the mobile device ( 14 ) recording movement data using internal sensors ( 18 ), and the driving profile ( 20 ) is determined based at least in part on the movement data; and

the mobile device ( 14 ) is carried along in the vehicle ( 10 ) controlled by the person.

3 . The method of claim 2 , wherein the mobile device ( 14 ) detects whether the mobile device ( 14 ) is located in the vehicle ( 10 ) based on the movement data, and determining the driving profile ( 20 ) comprises generating the driving profile ( 20 ) from movement data recorded in the vehicle ( 10 ).

4 . The method of claim 1 , wherein:

the driving profile ( 20 ) comprises a plurality of routes ( 22 );

the method further comprises receiving, via a mobile device ( 14 ), selection by the person of one or more of the plurality of routes ( 22 ); and

the category values ( 28 ) of the driving profile ( 20 ) for each of the plurality of vehicle configurations ( 24 ) are determined based at least in part on the one or more of the plurality of routes ( 22 ) selected.

5 . The method of claim 1 , wherein each of the plurality of vehicle configurations comprises one or more of:

a vehicle drivetrain;

an average fuel or energy consumption;

a vehicle mass; or

a vehicle drag coefficient.

6 . The method of claim 1 , wherein one or more of the weightings ( 26 ) for the category values ( 28 ) are selected by the person.

7 . The method of claim 1 , wherein:

the driving profile ( 20 ) comprises positions of a route ( 22 ) driven by the person; and

determining the category values ( 28 ) comprises determining a category value ( 28 ) that considers charging stations for electrically operated vehicles and/or filling stations along the route ( 22 ).

8 . The method of claim 1 , wherein determining the category values ( 28 ) for the driving profile ( 20 ) comprises determining a respective category value by simulating following the driving profile ( 20 ) using a vehicle having each of the plurality of vehicle configurations ( 24 ).

9 . The method of claim 1 , wherein determining the category values ( 28 ) for the driving profile ( 20 ) comprises determining each category value ( 28 ) by a machine learning algorithm into which the driving profile ( 20 ) is entered.

10 . The method of claim 1 , wherein the one or both of the energy consumption and the carbon dioxide emissions are determined by a machine learning algorithm as a function of the one or both of the speed profile and the acceleration profile.

11 . The method of claim 10 , wherein:

a respective machine learning algorithm is trained for each vehicle configuration ( 24 ); or

the vehicle configuration ( 24 ) is additionally entered into the machine learning algorithm.

12 . A computer program which, when run on a computer system ( 12 ), instructs the computer system ( 12 ) to carry out the method of claim 1 .

13 . A non-transitory computer-readable medium, in which a computer program of claim 12 is stored.

14 . A system ( 12 ) for determining a vehicle configuration ( 24 ) for driving behavior of a person, the system configured for implementing the method of claim 1 .

15 . The method of claim 4 , wherein the one or more routes ( 22 ) includes a route to a workplace of the person.

16 . The method of claim 1 , further comprising:

receiving, via a mobile device ( 14 ), an input by the person indicating which one of the category values ( 28 ) is more important to the person than other ones of the category values ( 28 ); and

changing one or more of the weightings ( 26 ) associated with the one of the category values ( 28 ) based on the input.

17 . The method of claim 1 , wherein the optimal vehicle configuration value ( 30 ) is the highest or lowest of the vehicle configuration values ( 30 ).

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (14)