# US 2026/0084715 A1 · Method and Apparatus for Specializing a Trained Machine Learning Model

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0084715 A1
- Document ID: US20260084715A1
- Status: Published application
- Kind: A1
- Application number: 19/334,892
- Filed: 2025-09-21
- Published: 2026-03-26
- Earliest claimed: 2024-09-24
- Assignees: Robert Bosch GmbH
- Applicants: Robert Bosch GmbH
- Inventors: Houssem Boulahbal
- Web page: https://patentgrep.com/patent/US20260084715A1

## CPC

- B60W 60/001: {Planning or execution of driving tasks}
- G06N 20/00: Machine learning
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method is disclosed for specializing a trained machine learning model for providing a driving function of a vehicle or a control function of a machine. The method includes (i) providing the trained machine learning model, which is trained on the basis of driving data from the vehicle or control data from the machine to perform the driving function or the control function, and which is extended by a storage module, wherein the storage module stores driving data from repetitive journeys of travel routes or control data from repetitive workflows and can be retrieved based on a query input, (ii) providing a query input to the storage module regarding a predetermined travel route or a predetermined workflow, and (iii) specializing the trained machine learning model by retraining it based on the driving data stored in the storage module for the predetermined travel route or based on the control data stored in the storage module for the predetermined workflow.

## Claims

### Claim 1

A method for specializing a trained machine learning model for providing a driving function of a vehicle or a control function of a machine, the method comprising:
providing the trained machine learning model, which is trained on the basis of driving data from the vehicle or control data from the machine to perform the driving function or the control function, and which is extended by a storage module, wherein the storage module stores driving data from repetitive journeys of travel routes or control data from repetitive workflows and can be retrieved based on a query input;
providing a query input to the storage module regarding a predetermined travel route or a predetermined workflow;
specializing the trained machine learning model by retraining it based on the driving data stored in the storage module for the predetermined travel route or based on the control data stored in the storage module for the predetermined workflow, and
providing the specialized machine learning model for providing a driving function of the vehicle specialized based on the predetermined travel route or a control function of the machine specified based on the predetermined workflow.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the storage module comprises a neural storage.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the query input comprises geographic information about the predetermined travel route or geographic or temporal or other information about the predetermined workflow.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the machine learning model comprises several submodules.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the driving data and/or the control data comprise geographical information and/or sensor data.

### Claim 6 (depends on 1)

A computer program having program code to execute at least portions of a method according to claim 1 if the computer program is executed on a computer.

### Claim 7 (depends on 1)

A computer-readable data carrier having program code of a computer program to execute at least portions of a method according to claim 1 if the computer program is executed on a computer.

### Claim 8 (depends on 1)

A control unit of a vehicle or a machine, which is designed to execute the specialized machine learning model that has been specialized according to the method of claim 1 in order to provide the driving function of the vehicle specialized on the basis of the predetermined travel route or the control function of the machine specified on the basis of the predetermined workflow, and which is configured to retrain the specialized machine learning model based on real-time data of the predetermined travel route or the predetermined workflow, continuously or at intervals.

### Claim 9 (depends on 1)

A cloud for a vehicle or machine that is designed to receive real-time data of the predetermined travel route or the predetermined workflow from the vehicle or machine, execute the specialized machine learning model that has been specialized according to the method of claim 1, and retrain it based on the real-time data, continuously or at intervals, and to provide the retrained, specialized machine learning model to the vehicle or machine for providing the driving function specialized based on the predetermined travel route or the control function specified based on the predetermined workflow.

### Claim 10

An apparatus for specializing a trained machine learning model for providing a driving function of a vehicle or a control function of a machine, wherein the apparatus comprises an evaluation and calculation unit that is designed to perform the following:
providing the trained machine learning model, which is trained on the basis of driving data from the vehicle or control data from the machine to perform the driving function or the control function, and which is extended by a storage module, wherein the storage module stores driving data from repetitive journeys of travel routes or control data from repetitive workflows and can be retrieved based on a query input;
providing a query input to the storage module regarding a predetermined travel route or a predetermined workflow;
specializing the trained machine learning model by retraining it based on the driving data stored in the storage module for the predetermined travel route or based on the control data stored in the storage module for the predetermined workflow; and
providing the specialized machine learning model for providing a driving function of the vehicle specialized based on the predetermined travel route or a control function of the machine specified based on the predetermined workflow.

### Claim 11 (depends on 2)

The method according to claim 2, wherein the neural storage is a neural storage network.

### Claim 12 (depends on 4)

The method according to claim 4, wherein the several submodules include a detection submodule, an estimation submodule, and a planning submodule.

### Claim 13 (depends on 5)

The method according to claim 5, wherein the sensor data includes lidar sensor data and/or radar sensor data and/or camera sensor data and/or SD card sensor data and/or ultrasonic sensor data.
