Virtual Test Signal Observers for ODD Coverage Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining operational design domain (ODD) coverage in virtual tests for automated driving systems face challenges in efficiently and reliably measuring coverage in large test spaces with numerous ODD elements, leading to computationally intensive extraction of scene elements.
Innovation Solution
A computer-implemented method and system generate observers for each element of the ODD, automatically monitoring virtual test signals linked to these elements, allowing efficient and automated collection and recording of ODD coverage data during runtime, and determining the required test coverage and parameters for missing areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to determine ODD coverage in virtual tests, then measurement of coverage is possible, but the process becomes computationally intensive and difficult to implement in large test spaces
Solution Approach 1:
The patent segments the ODD coverage determination process by creating separate observer functions for different ODD elements. Each observer independently monitors specific signals related to particular ODD elements, dividing the complex extraction task into manageable, parallel components that reduce overall computational burden
Solution Approach 2:
The patent applies preliminary action by generating and configuring observers before the virtual test execution. The observers are pre-programmed with knowledge of ODD element conditions and associated signals, so during test execution they can directly monitor and record coverage data without performing complex real-time extraction operations
2Reliability
If comprehensive ODD coverage is achieved by testing all areas, then validation reliability is improved, but the test space becomes excessively large and computationally intensive
Solution Approach 1:
The patent implements feedback mechanisms where observers continuously monitor virtual test signals and provide real-time information about ODD element satisfaction. This feedback enables dynamic tracking of coverage status, allowing the system to identify which ODD areas have been tested and which remain uncovered, optimizing the test execution process
Solution Approach 2:
The patent replaces the traditional mechanical approach of exhaustively testing all possible scenarios with a computational system of observers that mathematically track and determine coverage. Instead of physically executing every test case, the observer system uses signal monitoring and condition evaluation to compute coverage metrics efficiently
Data Source
AI summary
A computer-implemented method and system for generating at least one observer of at least one signal of a virtual test for validating a predefined function of a motor vehicle. A data set is provided having a plurality of elements of an operational design domain of the predefined function of the motor vehicle. Each element of the operational design domain is defined by a condition of the at least one signal of the virtual test. A system is also provided for generating at least one observer of at least one signal of a virtual test for validating a predefined function of a motor vehicle.