ADAS Scenario-Based Calibration With Adaptive Simulation Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The calibration and validation of Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) face challenges due to the complexity of the driving environment and the numerous scenarios that need to be considered, leading to a functional specification deficit and inefficiencies in the testing and validation processes.
Innovation Solution
A method and system for virtual calibration and validation of ADAS/ADS that selects specific traffic scenarios, using a modular simulation approach with interchangeable sub-modules, artificial intelligence algorithms, and performance indicators to adapt test strategies and generate calibration parameters, allowing for efficient simulation and evaluation of driving tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional requirement-based test processes are used for ADAS/ADS calibration and validation, then testing can be structured and documented, but the entire operational design domain (ODD) cannot be captured due to the large number of driving scenarios and influencing variables
Solution Approach 1:
The patent segments the operational design domain (ODD) into multiple scenario categories (e.g., highway driving, urban driving, weather conditions, traffic situations) and further divides scenarios into test cases with specific parameters. This hierarchical segmentation allows comprehensive coverage of the ODD while maintaining manageable complexity through structured organization of test requirements.
Solution Approach 2:
The patent creates a universal test framework that can handle diverse driving scenarios through parameterized test cases. The same test infrastructure can evaluate different ADAS/ADS functions across multiple scenario types by adjusting test parameters, making the testing system multi-functional and adaptable to various driving conditions without requiring separate testing procedures for each scenario.
2Reliability
If comprehensive testing of all driving scenarios is performed to ensure ADAS/ADS safety, then system reliability improves, but time and resources required for calibration and validation increase significantly
Solution Approach 1:
The patent performs preliminary actions by pre-defining scenario categories, test case templates, and parameter sets before actual calibration and validation. Test requirements are prepared in advance with structured hierarchies of scenarios and parameters, allowing the testing process to proceed efficiently without ad-hoc analysis during execution, thus reducing overall calibration and validation time while maintaining comprehensive coverage.
Solution Approach 2:
The patent utilizes parameter changes to efficiently test multiple scenarios by varying test parameters (e.g., weather conditions, traffic density, speed limits) within a unified test framework. Instead of creating entirely separate test procedures for each scenario, the system maintains a core test structure and modifies parameters to adapt to different driving conditions, significantly reducing the time and resources needed for comprehensive testing.
3Measurement precision
If detailed functional specifications are created for all possible driving scenarios, then test coverage improves, but the complexity of creating and maintaining these specifications becomes unmanageable
Solution Approach 1:
The patent segments functional specifications into a hierarchical structure with scenario categories at the top level, specific scenarios in the middle level, and test cases with parameters at the bottom level. This segmentation allows detailed test coverage at each level while reducing overall specification complexity through organized modularity, making creation and maintenance of comprehensive specifications manageable.
Solution Approach 2:
The patent implements dynamic specifications where test cases and parameters can be easily added, modified, or removed based on changing requirements. The structured framework allows flexible adaptation to new driving scenarios or regulatory requirements without redesigning the entire specification system, reducing long-term maintenance complexity while preserving detailed test coverage.
Data Source
AI summary
A method calibrates and validates a driver assistance system (ADAS) and/or an automated driving system (ADS) for a driving task in at least one scenario. The scenario represents a traffic event in a time sequence and is defined by selected parameters and associated parameter values. The method includes: creating first test cases by selecting scenarios, scenario parameters and calibration parameters using a test strategy for the driving task. The method proceeds by performing a simulation to determine simulation results; evaluating of the simulation results; adapting the test strategy to the evaluation results; creating second test cases using the adapted test strategy; starting a new simulation cycle; repeating the adaptation of the test strategy if an evaluation criterion is not met; or passing on the test cases of the last simulation cycle to an output module; outputting results of the test cases from the output module for calibration and validation.