Scenario Similarity Retrieval for Autonomous Driving Test Coverage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing validation methods for autonomous vehicles with Level 4 or higher autonomous driving systems struggle to efficiently generate and assess scenarios that cover all possible driving situations, including operational design domains and criticality phenomena, due to the complexity and uncertainty of real-world environments.
Innovation Solution
A scenario retrieval-based automatic generation method that retrieves similar scenarios from a database, filters and modifies them to meet target conditions, and concretizes them for use in testing, ensuring alignment with operational design domains and criticality phenomena.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If scenario-based testing is used to validate autonomous driving systems, then the ability to test various driving situations is improved, but the complexity of generating and managing comprehensive scenarios increases
Solution Approach 1:
The system pre-stores a large number of driving scenarios in a database before actual testing begins. These scenarios are organized and structured in advance, allowing the testing system to efficiently retrieve and utilize them during validation processes without needing to generate scenarios on-demand, thus reducing real-time complexity while maintaining comprehensive coverage
Solution Approach 2:
The system creates and stores copies of various driving scenarios in a database. These scenario copies can be retrieved, modified, and reused multiple times for different testing purposes. This allows the system to validate multiple aspects of autonomous driving without recreating scenarios from scratch each time, reducing computational complexity while maintaining validation thoroughness
2Adaptability or versatility
If manual scenario creation is used to cover all driving situations, then scenario relevance is improved, but the time and resources required increase significantly
Solution Approach 1:
The system automatically generates scenario data by copying and adapting existing scenario templates and real-world driving data. This automated copying and transformation process replaces manual scenario creation, significantly reducing the time and human resources required while maintaining comprehensive scenario coverage across various driving situations
Solution Approach 2:
The system uses parameter-based scenario generation where base scenario templates are automatically modified by changing parameters such as environmental conditions, vehicle states, and traffic patterns. This automated parameter adjustment allows comprehensive scenario coverage to be achieved quickly without manual intervention for each scenario variation
Data Source
AI summary
There are provided a scenario similarity retrieval-based automatic scenario generation system and method. According to an embodiment, a scenario retrieval-based automatic scenario generation method includes: retrieving scenarios similar to a query scenario from a scenario DB for an autonomous driving test; filtering only scenarios that meet a selection condition from the retrieved scenarios; and converting components of the filtered scenarios to suit a target condition. Accordingly, a desired scenario may be automatically generated by retrieving a scenario similar to a targeted scenario, converting the retrieved scenario, and concretizing the scenario.