Computer-implemented system and method for monitoring the functionality of an automated driving function

Patent metadata

Field	Value
Publication number	US-12554477-B2
Application number	US-202318185806-A
Country	US
Kind code	B2
Filing date	Mar 17, 2023
Priority date	Mar 30, 2022
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

A computer-implemented system for monitoring the functionality of an automated driving function of a vehicle using sensor information from at least one sensor includes a software model of the automated driving function, a sensor performance model for the at least one sensor, a sensor monitoring module, which determines performance parameters and monitors the performance of the at least one sensor, an update module for updating the at least one sensor performance model based on the performance parameters determined, and a model checking module for analyzing an overall model comprising a combination of the software model and the at least one sensor performance model.

First claim

The invention claimed is:

1 . A system for monitoring a functionality of an automated driving function of a vehicle in which the system uses sensor information from at least one sensor, the system comprising:
a processing system having at least one processor configured to:
determine current performance parameters of the at least one sensor and continuously monitor a current performance of the at least one sensor;
update at least one current sensor performance model for the at least one sensor based on the current performance parameters depending on a comparison between the current performance parameters of the at least one sensor and prior performance parameters of the at least one sensor at an earlier time when the current performance model was derived, the at least one current sensor performance model describing a probability or distribution of performance errors of the at least one sensor;
generate an overall model by combining the at least one updated sensor performance model with a software model of the automated driving function, the software model of the automated driving function describing the functionality of the automated driving function;
analyze the overall model using a model checking process to verify that the automated driving function can provide error-free results with the current performance parameters of the at least one sensor, including at least one of (i) verifying that the automated driving function satisfies predefined criteria or (ii) identifying at least one violation of the predefined criteria by the automated driving function; and
control, immediately, at least one of a display device and at least one vehicle function based on determining that the automated driving function cannot provide error-free results with the current performance parameters of the at least one sensor.

2 . The system according to claim 1 , wherein the at least one processor includes at least one of (i) a processor in the vehicle and (ii) a processor of a server.

3 . The system according to claim 2 , wherein the processor in the vehicle is configured to determine the current performance parameters of the at least one sensor and monitor the current performance of the at least one sensor.

4 . The system according to claim 2 , wherein the processor of the server is configured to at least one of (i) implement at least one of the software model of the automated driving function, (ii) implement the at least one current sensor performance model, (iii) update the at least one sensor performance model, and (iv) analyze the overall model using the model checking process.

5 . The system according to claim 1 , wherein the software model is at least one of a finite state model, a timed automaton, a probable state machine, a Markov chain, a Markov decision process, or a Petri net.

6 . A computer-implemented method for monitoring a functionality of an automated driving function of a vehicle in which the method uses sensor information from at least one sensor, the method comprising:
determining current performance parameters of the at least one sensor and continuously monitoring a current performance of the at least one sensor; updating at least one current sensor performance model for the at least one sensor based on the current performance parameters depending on a comparison between the current performance parameters of the at least one sensor and prior performance parameters of the at least one sensor at an earlier time when the current performance model was derived, the at least one current sensor performance model describing a probability or distribution of performance errors of the at least one sensor; generating an overall model by combining the at least one updated sensor performance model with a software model of the automated driving function, the software model of the automated driving function describing the functionality of the automated driving function; analyzing the overall model using a model checking process to verify that the automated driving function can provide error-free results with the current performance parameters of the at least one sensor, including at least one of (i) verifying that the automated driving function satisfies predefined criteria or (ii) identifying at least one violation of the predefined criteria by the automated driving function; and controlling, immediately, at least one of a display device and at least one vehicle function based on determining that the automated driving function cannot provide error-free results with the current performance parameters of the at least one sensor.

7 . The method according to claim 6 , wherein the analyzing of the overall model includes using a probabilistic model checking method that comprises determining probabilities that the automated driving function is meeting the predefined criteria.

8 . The method according to claim 6 , wherein the software model is at least one of a finite state model, a timed automaton, a probable state machine, a Markov chain, a Markov decision process, or a Petri net.

Assignees

• Bosch Gmbh Robert

Inventors

• Heinzemann Christian
• Koenig Lukas
• Hanselmann Michael

Classifications

• G06F8/35 Primary

  model driven · CPC title

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• G06F8/65 Primary

  Updates (security arrangements therefor G06F21/57) · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title

• G06F11/302

  where the computing system component is a software system · CPC title