Automated Vehicle Function Self-Analysis for ODD Extension
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating automated vehicle functions are limited to analyzing their performance within predefined operational design domains (ODDs) and cannot assess novel functions or extensions outside these domains due to the lack of continuous data streaming and analysis capabilities.
Innovation Solution
Implementing a self-analysis function as a software module in vehicles to determine predefined variables from input and output data, which are then transmitted to a backend for continuous evaluation and aggregation, creating a digital map that assesses the quality and potential extensions of automated functions across various conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If continuous data streaming and self-analysis functions are implemented, then the evaluation capability for automated functions outside ODD is improved, but the device complexity and cost increase
Solution Approach 1:
The automated function performs self-analysis by determining predefined variables about its own input and output data quality. This self-service mechanism enables the system to evaluate its own performance without requiring complex external analysis infrastructure, thus improving adaptability while controlling device complexity.
Solution Approach 2:
The system continuously determines predefined variables about data quality in advance before formal evaluation is needed. This preliminary action of continuously monitoring and storing quality metrics enables rapid evaluation when novel functions or ODD extensions are introduced, avoiding the need for complex real-time analysis infrastructure.
2Loss of information
If only few signals are sent at low frequency for cost reasons, then the cost is reduced, but the analysis capability for novel functions outside ODD is lost
Solution Approach 1:
The system extracts only the essential predefined variables related to data quality from the continuous data stream. By selecting and transmitting only these specific quality metrics rather than all raw data, the system maintains analysis capability for novel functions while minimizing data transmission volume and associated costs.
Solution Approach 2:
The system changes the parameter being transmitted from raw data to processed quality metrics (predefined variables). This parameter transformation enables effective analysis of novel functions with much smaller data volumes, reducing transmission costs while preserving analytical capability.
Data Source
AI summary
A method for evaluating a quality of an automated function of a motor vehicle includes providing at least one self-analysis function as a software module for the automated function. The method further includes determining a predefined variable based on input data and/or output data of the automated function by means of the self-analysis function. The method further includes transmitting the predefined variable from the motor vehicle to a backend system.