System And Method For Rule-Based Operation Of A Motor Vehicle

Patent metadata

Field	Value
Publication number	US-2026054741-A1
Application number	US-202519295871-A
Country	US
Kind code	A1
Filing date	Aug 11, 2025
Priority date	Aug 26, 2024
Publication date	Feb 26, 2026
Grant date	—

Abstract

A system for rule-based operation of a vehicle is provided, comprising one or more sensors configured to monitor an interior and/or an exterior of the vehicle and/or receive a user input, and to thereby collect data related to a state of the vehicle and/or a state of the surrounding of the vehicle, and an action of the user of the vehicle and/or the user input. The system comprises a processor configured to use a machine learning model, preferably a large language model, with input data based on the collected data to generate a rule for operating the vehicle. The rule includes at least one action associated with at least one condition and/or at least one event. The processor is configured to analyze the collected data to validate that the condition is met and/or that the event has occurred, and cause the vehicle to perform the action.

First claim

1 . A system for rule-based operation of a vehicle, the system comprising:
one or more sensors configured to:
monitor an interior and/or an exterior of the vehicle and/or receive a user input and thereby collect data related to:
a state of the vehicle and/or a state of the surrounding of the vehicle, and
an action of the user of the vehicle and/or the user input; and
a processor configured to:
receive the collected data from the one or more sensors,
use a machine learning model with input data based on the collected data to generate a rule for operating the vehicle, the rule including at least one action associated with at least one condition and/or at least one event, wherein the machine learning model is a large language model or a neural network with multi-modal capabilities,
analyze the collected data to validate that the at least one condition is met and/or that the at least one event has occurred, and
cause the vehicle to perform the action.

2 . The system of claim 1 , wherein the input data includes data of multiple data types selected from a group including audio-, text- and image-based data types.

3 . The system of claim 1 , wherein causing the vehicle to perform the action includes:
associating the action to one or more instructions for one or more components of the vehicle, and requesting the one or more components of the vehicle to execute the one or more instructions.

4 . The system of claim 1 , wherein the processor is further configured to send one or more instructions associated with the action to a remote device that executes the received one or more instructions.

5 . The system of claim 1 , wherein the system further includes a database storing a list of rules, wherein the processor is further configured to save the generated rule in the list of rules stored in the database.

6 . The system of claim 1 , wherein generating the rule includes applying a user-specific constraint.

7 . The system of claim 1 , wherein the system further includes another database configured to accumulate the collected data related to the action of the user and the state of the vehicle and/or the state of the surrounding of the vehicle, and wherein the processor is further configured to recognize a pattern in the accumulated data by use of another machine learning model, wherein generating the rule is initiated upon recognizing the pattern and/or wherein the recognized pattern is inputted to the machine learning model for generating the rule.

8 . The system of claim 1 , wherein the input data for the machine learning algorithm is based on:
the recognized pattern, and/or collected data related to the action of the user and collected data related to the state of the vehicle and/or collected data related to the state of the surrounding of the vehicle.

9 . The system of claim 1 , wherein the input data for the machine learning algorithm is not based on collected data related to the user input.

10 . The system of claim 1 , wherein the system further comprises a user interface, and wherein the processor is further configured to:
cause the user interface to provide a representation of the generated rule to the user, and use the generated rule for operating the vehicle upon receipt of a user input including a confirmation of the generated rule, or adapt the generated rule upon receipt of and according to a user input including an adaption of the rule and use the adapted rule for operating the vehicle.

11 . A vehicle having in-built the system according to claim 1 .

12 . A method comprising using the system of claim 1 for operating the vehicle.

13 . A method for rule-based operation of a vehicle, the method comprising:
monitoring an interior and/or an exterior of the vehicle and/or receiving a user input and thereby collecting data related to a state of the vehicle and/or a state of the surrounding of the vehicle, and an action of the user of the vehicle and/or the user input; using a machine learning model with input data based on the collected data to generate a rule for operating the vehicle, the rule including at least one action associated with at least one condition and/or at least one event, wherein the machine learning model is a large language model or a neural network with multi-modal capabilities; analyzing the collected data to validate that the at least one condition is met and/or that the at least one event has occurred; and causing the vehicle to perform the action.

14 . The method of claim 13 , wherein the method further comprises:
accumulating the collected data related to the action of the user and the state of the vehicle and/or the state of the surrounding of the vehicle; and recognizing a pattern in the accumulated data by use of another machine learning model, wherein the recognized pattern is inputted to the machine learning model for generating the rule.

15 . The method of claim 13 , wherein the input data for the machine learning algorithm is based only on data that consists of
the recognized pattern, and/or collected data related to the action of the user of the vehicle and collected data related to the state of the vehicle and/or collected data related to the state of the surrounding of the vehicle.

Assignees

• Aptiv Technologies AG

Inventors

• Barth Alexander
• Nunn Christian

Classifications

• B60K35/10

  Input arrangements, i.e. from user to vehicle, associated with vehicle functions or specially adapted therefor · CPC title

• B60W2540/215

  Selection or confirmation of options · CPC title

• B60W50/085 Primary

  Changing the parameters of the control units, e.g. changing limit values, working points by control input · CPC title

• B60W2540/21

  Voice · CPC title

• B60W2556/10

  Historical data · CPC title