Driving Model Scenario Redundancy Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing methods for testing Autonomous Driving systems require a vast number of driving scenarios, leading to redundancy and inefficiency, as many scenarios are similar, which increases testing time and memory usage.
Innovation Solution
A computer-implemented method that uses the Microscope Driving model to identify and discard redundant driving scenarios by comparing vehicle dynamics time series data, creating a new test set that reduces redundancy and focuses on unique scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a vast number of driving scenarios are used for testing Autonomous Driving systems, then testing coverage is improved, but testing time and memory usage increase
Solution Approach 1:
The patent merges similar driving scenarios by comparing their vehicle dynamics time series data and identifying similarities. Scenarios that produce similar vehicle responses are grouped together and represented by a single test case, reducing the total number of tests needed while maintaining coverage of unique driving behaviors
Solution Approach 2:
The patent transforms the testing approach by changing from testing individual scenarios to testing scenario similarity through parameter comparison. By analyzing vehicle dynamics parameters (position, speed, acceleration) and identifying patterns, the system determines which scenarios can be represented by others, fundamentally changing how test coverage is achieved
2Reliability
If a vast number of driving scenarios are used for testing Autonomous Driving systems, then testing coverage is improved, but memory usage increases
Solution Approach 1:
The patent merges similar driving scenarios by comparing their vehicle dynamics time series data and identifying similarities. Scenarios that produce similar vehicle responses are grouped together and represented by a single test case, reducing the total number of tests needed while maintaining coverage of unique driving behaviors
Solution Approach 2:
Instead of storing and executing multiple copies of similar test scenarios, the patent creates a representative copy that captures the essential characteristics of similar scenarios. The similarity comparison logic effectively creates a virtual representation of scenario groups, reducing actual memory storage requirements
3Reliability
If many similar driving scenarios are included in the test set, then comprehensive testing is achieved, but redundancy increases
Solution Approach 1:
The patent extracts the essential characteristics of driving scenarios by comparing vehicle dynamics time series data. By identifying and removing redundant scenarios that don't add unique testing value, the system extracts only the necessary test cases needed to achieve comprehensive coverage, simplifying the overall test set structure
Data Source
AI summary
A computer-implemented method is provided for redundancy reduction for driving test scenarios. The method includes receiving an original test set of driving scenarios and a driving model which simulates a vehicle behavior under a driving scenario inputted to the driving model. The method includes, for each driving scenario of the original test set, obtaining vehicle dynamics timeseries data as an output of the driving model. The method includes determining similar driving scenarios by comparing driving model outputs. The method additionally includes creating a new test set of driving scenarios by discarding duplicated ones of the similar driving scenarios from the original test set.