Driver Assistance Test Termination Using Critical Case Distance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high cost and time-consuming nature of testing driver assistance systems using existing methods, which require extensive simulation and test trips to validate various driving scenarios.
Innovation Solution
A computer-implemented method for terminating a scenario-based test process of a driver assistance system, which involves determining critical test cases through parameter combinations of driving situation parameters, and using a distance metric, such as the Hausdorff distance, as an abort condition to efficiently cycle through the test process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If extensive simulation and test trips are conducted to validate driving scenarios, then the verification and validation of driver assistance systems is improved, but the time spent and costs involved increase significantly
Solution Approach 1:
The patent segments the parameter space into discrete metric points that can be independently evaluated. Instead of conducting exhaustive simulations across continuous parameter ranges, the method divides the testing into specific metric points representing critical driving situations, allowing targeted validation without comprehensive testing of all possible scenarios.
Solution Approach 2:
The patent performs preliminary identification of critical metric points in the parameter space before conducting actual simulations. By pre-determining which parameter combinations represent critical test cases based on distance metrics and geometric relationships, the system prepares a focused test plan that avoids unnecessary simulations while ensuring coverage of critical scenarios.
2Reliability
If extensive simulation and test trips are conducted to validate driving scenarios, then the verification and validation of driver assistance systems is improved, but the costs involved increase significantly
Solution Approach 1:
The patent extracts only the critical metric points from the full parameter space that represent critical test cases. By identifying and isolating specific parameter combinations that pose critical driving situations using geometric distance metrics, the method extracts the essential test cases needed for validation while discarding unnecessary simulations, thereby reducing computational resource requirements and costs.
Solution Approach 2:
The patent applies partial action by conducting simulations only at critical metric points rather than across the entire parameter space. This selective approach performs fewer simulations than exhaustive testing would require, yet achieves sufficient validation by focusing computational resources on the most critical scenarios that directly impact system safety and performance.
3Reliability
If a large number of possible driving situations are tested, then the comprehensive validation is improved, but the productivity of the test process decreases
Solution Approach 1:
The patent applies local quality by concentrating testing efforts on specific critical regions of the parameter space rather than uniform coverage. By identifying metric points where geometric relationships indicate critical driving situations (such as when distance metrics fall below thresholds), the method focuses validation on locally critical areas that have disproportionate impact on system safety, thereby improving productivity without compromising comprehensive validation.
Data Source
AI summary
A computer-implemented method provides for terminating a scenario-based test process of a driver assistance system. The test process comprises a cycle and includes determining critical test cases and parameter combinations thereof. The method includes: performing at least one test of the driver assistance system after each iteration n of the cycle and determining a set of critical test cases; establishing, on that basis, a distance between a first set of critical test cases in the iteration n and a second set of critical test cases from the iteration n−1 or a distance between the first set of critical test cases in the iteration n and a predefined set of critical test cases; and terminating or continuing the cycle of the test process on the basis of a difference between the distance between the first set and the second set and a preset limit.