Autonomous Vehicle Rulebook Scenario Generation for Control Testing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-driving vehicles face challenges in navigating complex driving scenarios due to varying traffic laws, cultural expectations, and safety considerations, making it difficult to execute decisions effectively.
Innovation Solution
A signal processing system generates simulated scenarios using a hierarchical plurality of rules to test and train control systems, identifying trajectories that violate high-priority rules, thereby improving automated vehicle testing and driving behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional testing methods are used for control systems, then the testing process is simple, but the testing coverage and quality are insufficient
Solution Approach 1:
The patent creates virtual copies of driving scenarios through simulated environments that replicate real-world conditions. These digital twins allow comprehensive testing of control systems without physical vehicle deployment, enabling thorough validation of edge cases and rare events while reducing testing costs and complexity.
Solution Approach 2:
The system performs preliminary generation and validation of test scenarios before actual control system testing. Scenarios are pre-processed to ensure they meet quality criteria, and the testing framework is established in advance, allowing systematic exploration of the decision space before execution.
2Adaptability or versatility
If comprehensive scenario generation is performed to cover all driving cases, then testing coverage improves, but computational resources and time are consumed
Solution Approach 1:
The patent systematically varies scenario parameters such as environmental conditions, traffic participant behaviors, and road configurations to generate diverse test cases. By changing key parameters within defined ranges, the system achieves comprehensive coverage of driving scenarios while avoiding redundant generation of identical cases.
Solution Approach 2:
The testing framework employs a hierarchical structure where general driving scenarios contain specific edge cases, which in turn contain particular test conditions. This nested organization allows the system to manage complexity by breaking down comprehensive scenario generation into manageable layers, from broad scenario categories to specific test instances.
3Adaptability or versatility
If the control system is tested with diverse scenarios, then the system's adaptability improves, but the complexity of managing test cases increases
Solution Approach 1:
The patent divides the comprehensive test scenario space into segmented categories based on driving contexts, environmental conditions, and traffic situations. Each segment can be independently generated, tested, and managed, allowing systematic organization of diverse test cases while maintaining overall test coverage.
Solution Approach 2:
The system incorporates feedback mechanisms where test results inform subsequent scenario generation and refinement. Performance data from controlled tests feeds back into the scenario generation process, allowing automatic adjustment of test parameters and identification of gaps in scenario coverage, thereby reducing manual test management complexity.
Data Source
AI summary
Provided are methods for testing of a control system of a vehicle using generated rulebook based scenarios, which can include determining a simulated environment, receiving a hierarchical plurality of autonomous vehicle rules, determining a trajectory of a simulated vehicle within the simulated environment, generating a plurality of simulated scenarios for the simulated vehicle, identifying at least one violation of at least one autonomous vehicle rule by the simulated vehicle in a set of the simulated scenarios, determining a scenario score for each simulated scenario based on the violations, and identifying at least one simulated scenario for a trained neural network of a vehicle based on the scenario scores.