Augmented Driving Scenario Validation Using Reference Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current simulation methods for validating environmental sensing functions in automated driving systems lack sufficient realism and are inefficient due to reliance on uncontrollable real-world data acquisition, which is complex and dependent on weather and lighting conditions.
Innovation Solution
A method for digitally recording and manipulating real-world scenarios to create augmented test scenarios by altering specific parameters, such as weather and road conditions, using sensors like cameras and LiDAR, to generate realistic and reproducible test data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-world data acquisition is used for validating environmental sensing functions, then the realism of test data is improved, but the complexity and controllability of the testing process deteriorates due to dependence on uncontrollable parameters such as weather and lighting conditions
Solution Approach 1:
The patent creates digital copies of real-world scenarios by recording base scenarios with real vehicles and then digitally manipulating these recordings to generate multiple test scenarios. This copying approach preserves the realism of real-world data while eliminating the need for repeated real-world acquisitions under varying conditions.
Solution Approach 2:
The patent systematically changes parameters such as weather conditions (precipitation, fog, rain), lighting conditions, and road conditions by digitally manipulating the recorded base scenario. This allows generation of diverse test scenarios from a single real-world recording, improving reliability while controlling complexity.
2Reliability
If real-world data acquisition is used for validating environmental sensing functions, then the realism of test data is improved, but the efficiency of the testing process deteriorates due to uncontrollable parameters requiring extensive field testing
Solution Approach 1:
The patent performs preliminary action by recording comprehensive base scenarios once in the real world, which then serve as the foundation for generating multiple manipulated test scenarios. This preliminary real-world recording eliminates the need for repeated field testing under different conditions, significantly improving efficiency.
Solution Approach 2:
By creating and manipulating digital copies of the base scenario, the system can generate unlimited test variations without returning to the field, thereby dramatically improving productivity while maintaining the realism inherent in the original real-world recording.
3Productivity
If simulations are used for testing automated driving systems, then the efficiency and controllability of testing is improved, but the realism and representativeness of test data deteriorates
Solution Approach 1:
The patent uses real-world recordings as the base for simulations rather than purely synthetic data. This copying of real-world scenarios into the digital domain preserves representativeness while enabling the efficiency and controllability of simulated testing environments.
Solution Approach 2:
The system maintains realism by applying parameter changes to real-world recordings rather than generating entirely synthetic scenarios. This approach preserves the authentic characteristics of real traffic conditions while allowing controlled manipulation for comprehensive testing.
4Quantity of substance
If digitally manipulated test scenarios are created by augmenting real-world data, then the quantity of available test data is improved, but the complexity of data manipulation processes increases
Solution Approach 1:
The patent segments the manipulation process into distinct, manageable steps: recording base scenarios, applying specific manipulations for different weather and lighting conditions, and validating results. This segmentation makes the overall complex process more controllable and systematic.
Solution Approach 2:
The system focuses manipulation on specific, well-defined parameters such as precipitation effects, lighting conditions, and road conditions. By concentrating on key parameters rather than attempting to manipulate all aspects simultaneously, the process complexity is managed while still generating diverse test data.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a method 100 for validating digitally manipulated (augmented) test scenarios 120, comprising the steps of digitally recording a base scenario 110 with at least one real vehicle 200, 210 moving on a real road under defined real traffic conditions; digitally recording the base scenario 110 manipulated by selected traffic conditions 310 to create a reference scenario 130; manipulating the data of the digitally recorded base scenario 110 by selected traffic conditions 310 to create an augmented test scenario 120; and acquiring data of the traffic conditions in the augmented test scenario 120 and data in the reference scenario 130 with at least one sensor.The invention relates to an analysis 140 of the relationship between the test and reference data acquired by the at least one sensor, and an evaluation 150 of the validity of the data of the test scenario based on a result of the analysis 140 of the relationship. The invention further relates to a corresponding computer-implemented method and preferred uses of the method.