IP Library › Granted Patent US 12,314,686
Granted Patent B2
US 12,314,686 · App. 18/337,167 · Granted May 27, 2025

Method and validation system for validating a software component for highly automated driving

Inventor: Christian Schilling (Leinfelden-Echterdingen, DE)
Assignee: Robert Bosch GmbH
G06F8/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,314,686
App. No.
18/337,167
Granted
May 27, 2025
Kind
B2
Abstract

A method for validating a software component for highly automated driving is disclosed, wherein unprocessed video data, which depict at least one driving situation recorded from a vehicle perspective by a recording vehicle are read by a data processing system and processed into preprocessed video data using a vehicle processor connected to the data processing system for video preprocessing, wherein the vehicle processor is arranged on an adapter board and is connected to the data processing system via standard interfaces, wherein the preprocessed video data are used by the data processing system as input variables for the software component to be validated, and a reaction of the software component to the driving situation depicted in the preprocessed video data as output variables for the software component to be validated are compared by the data processing system with an expected reaction in order to validate the software component.

Claims (31)

1. A method for validating a software component for highly automated driving, comprising:

reading with a data processing system unprocessed video data which depict at least one driving situation recorded from a vehicle perspective by a recording vehicle, the data processing system being outside of the recording vehicle;

processing the unprocessed video data into preprocessed video data using a vehicle processor connected to the data processing system for video preprocessing, wherein the vehicle processor is arranged on an adapter board, the adapter board being outside of the recording vehicle and connected to the data processing system via at least one interface of the data processing system, wherein the vehicle processor is configured to be installed within a vehicle;

using, with the data processing system, the preprocessed video data as input variables for the software component; and

validating the software component with the data processing system by comparing output variables of the software component associated with a reaction of the software component to the recorded at least one driving situation with an expected reaction.

2. The method according to claim 1 , the processing further comprising:

calculating an optical flow of the unprocessed video data using the vehicle processor; and

embedding the optical flow in the preprocessed video data.

3. The method according to claim 1 , the processing further comprising:

calculating depth information from the video data using the vehicle processor; and

embedding the depth information in the preprocessed video data.

4. The method according to claim 1 , the processing further comprising:

rectifying, using the vehicle processor, the unprocessed video data.

5. The method according to claim 1 , further comprising:

reading progress information from the software component;

generating control signals using the progress information; and

providing at least one of (i) the unprocessed video data or (ii) the preprocessed video data to the vehicle processor step-by-step in response to the control signals.

6. The method according to claim 1 , further comprising:

transferring the unprocessed video data in bulk to the adapter board.

7. The method according to claim 1 , wherein the method is performed by executing computer program instructions stored on a non-transitory machine-readable storage medium.

8. The method according to claim 1 , wherein the at least one interface of the data processing system includes at least one of a PCIe interface or an Ethernet interface.

9. A validation system for validating a software component for highly automated driving, the validation system comprising:

a storage device configured to store unprocessed video data which depict at least one driving situation recorded from a vehicle perspective by a recording vehicle;

a data processing system that is arranged outside of the recording vehicle; and

an adapter board that is arranged outside of the recording vehicle, the adapter board being connected to the data processing system via at least one interface of the data processing system, a vehicle processor being arranged on the adapter board, the vehicle processor being configured to be installed within a vehicle,

wherein the data processing system is configured to:

read the unprocessed video data from the storage device;

process the unprocessed video data into preprocessed video data using the vehicle processor that is connected via the adapter board;

use the preprocessed video data as input variables for the software component; and

validate the software component by comparing output variables of the software component associated with a reaction of the software component to the recorded at least one driving situation with an expected reaction.

10. The method according to claim 9 , wherein the data processing system executes computer program instructions stored on a non-transitory machine-readable storage medium.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 18, 2023
From: SCHILLING, CHRISTIAN
To: ROBERT BOSCH GMBH
Reel/Frame 064631/0458 →
Priority Claims (1)
DE 10 2022 206 326.0 · Jun 23, 2022 · national
Continuity (1)
Related Publication 20230418561A1 · Dec 28, 2023
References Cited (18)
US 6080207A · Kroening · 2000 [cited by examiner]
US 7330967B1 · Pujare · 2008 [cited by examiner]
US 7813822B1 · Hoffberg · 2010 [cited by examiner]
US 10007675B2 · Marti · 2018 [cited by examiner]
US 10102687B1 · Sampigethaya · 2018 [cited by examiner]
US 10479303B2 · Koehler · 2019 [cited by examiner]
US 11039737B2 · Kohler · 2021 [cited by examiner]
US 11640467B2 · Zarakas · 2023 [cited by examiner]
US 11681811B1 · Dixit · 2023 [cited by examiner]
US 12182694B2 · Farabet · 2024 [cited by examiner]
US 20170178498A1 · Mcerlean · 2017 [cited by examiner]
US 20230393833A1 · Cain, Jr. · 2023 [cited by examiner]
Rajabali et al, “Software Verification and Validation of Safe Autonomous Cars: A Systematic Literature Review”, IEEE, pp. 4797-4819 (Year: 2023). [cited by examiner]
Schmidt et al, “Methods for Virtual Validation of Automotive Powertrain Systems in Terms of Vehicle Drivability—A Systematic Literature Review”, IEEE, pp. 27043-27065 (Year: 2023). [cited by examiner]
Rajbali et al, “Software Verification and Validation of Safe Autonomous Cars: A Systematic Literature Review”, IEEE, pp. 1-23 (Year: 2020). [cited by examiner]
Venkitachalam et al, “Metrics for Verification and Validation of Architecture in Powertrain Software Development”, ACM pp. 1-7 (Year: 2015). [cited by examiner]
Ghammam et al, “Efficient Management of Containers for Software Defined Vehicles”, ACM, pp. 1-36 (Year: 2024). [cited by examiner]
Siebinga et al, “A Human Factors Approach to Validating Driver Models for Interaction-aware Automated Vehicles”, ACM, pp. 1-21 (Year: 2022). [cited by examiner]