KPI Plug-In Evaluation for Autonomous Driving Scenario Testing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for testing and validating autonomous driving functions are resource-intensive and time-consuming, often requiring extensive real-world testing that is impractical due to cost and time constraints, and fail to adequately simulate critical driving scenarios.
Innovation Solution
A computer-implemented method using KPI plug-ins for scenario-based testing, allowing dynamic and reusable selection of key performance indicators (KPIs) to evaluate simulations and test cases, with automatic execution and management by a KPI plug-in mechanism, enabling optimized test case generation and parameter configuration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If extensive real-world testing is conducted to validate autonomous driving functions, then testing coverage and reliability are improved, but time consumption and cost increase significantly
Solution Approach 1:
The patent creates virtual copies of real-world driving scenarios through simulation environments. These simulated scenarios replicate critical driving situations, road conditions, and traffic patterns without requiring physical test vehicles on actual roads. The virtual test environments allow comprehensive coverage of billions of kilometers equivalent testing while consuming minimal real time and resources.
Solution Approach 2:
The patent performs preliminary validation of autonomous driving functions through simulation-based testing before deploying to real-world conditions. By pre-testing various scenarios including edge cases and critical situations in virtual environments, the system identifies and resolves issues beforehand, reducing the need for extensive iterative real-world testing and accelerating the validation process.
2Reliability
If traditional testing methods are used to cover all potential driving situations, then testing completeness is improved, but resource requirements and testing effort increase
Solution Approach 1:
The patent implements dynamic scenario generation and selection mechanisms that adaptively create and prioritize test scenarios based on predefined criteria such as safety criticality, scenario frequency, and validation progress. The system dynamically adjusts testing focus, intensifying resources on high-priority scenarios while reducing effort on low-risk situations, thereby achieving comprehensive coverage with optimized resource allocation.
Solution Approach 2:
The patent systematically varies key parameters such as weather conditions, road surfaces, traffic density, vehicle speeds, and sensor configurations to generate diverse test scenarios. By methodically changing these parameters across simulated environments, the system achieves comprehensive coverage of potential driving situations without manually designing each scenario, significantly improving testing efficiency while maintaining completeness.
3Productivity
If simulation-based testing is used to reduce real-world testing requirements, then time and cost are reduced, but scenario coverage and critical situation detection may be insufficient
Solution Approach 1:
The patent segments the overall testing process into distinct simulation phases including unit testing of individual sensors and actuators, integration testing of subsystems, and system-level validation. Each phase uses appropriately tailored simulated scenarios focused on specific aspects of autonomous driving functionality, ensuring comprehensive coverage while maintaining efficient resource utilization across different testing levels.
Solution Approach 2:
The patent implements feedback mechanisms where simulation results are automatically analyzed and used to refine and generate subsequent test scenarios. The system learns from simulated test outcomes, identifying gaps in scenario coverage and automatically creating new test cases that target uncovered situations. This iterative feedback loop ensures progressively improving scenario coverage while maintaining efficient simulation-based testing.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
Computer-implemented method for evaluating simulations and/or test cases in scenario-based testing and/or homologation of at least partially autonomous driving functions to be tested by means of Key Performance Indicators (KPIs), wherein KPIs are represented by KPI plug-ins and KPI plug-ins are selected dynamically and reusable for simulations and/or test cases, and wherein at least one KPI plug-in is selected by a KPI plug-in mechanism during the simulation and/or test definition and is automatically executed by the KPI plug-in mechanism during execution.