Synthetic Driving Scenario Generation from Noisy Vehicle Log Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating accurate simulation scenarios for testing and validating autonomous vehicle systems is challenging due to noisy, inconsistent, and incomplete data, which can lead to inefficient testing and validation processes, especially when updating algorithms or simulating real-world scenarios.
Innovation Solution
A system and method for generating simulation scenarios using previously recorded log data from autonomous vehicles, where inconsistencies are identified and smoothed or replaced to create high-quality simulation instructions that accurately reflect real-world environments, allowing for efficient testing and validation of autonomous vehicle controllers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If simulation scenarios are created using raw log data, then the realism of simulated scenarios is improved, but the data quality and consistency deteriorate due to noisy and incomplete data
Solution Approach 1:
The system performs preliminary data processing by identifying inconsistencies in log data before generating simulation scenarios. It smooths or replaces inconsistent data to create high-quality simulation instructions, ensuring data quality is improved before the actual simulation creation process begins.
Solution Approach 2:
The system introduces an intermediary processing layer that transforms raw log data into refined simulation instructions. This intermediary process includes identifying and correcting inconsistent data, thereby mediating between the raw data and the final simulation scenarios to ensure both realism and consistency.
2Reliability
If detailed and accurate simulation data is generated, then the validation effectiveness is improved, but the computational resources required increase
Solution Approach 1:
The system extracts only the essential and consistent features from raw log data to create simulation scenarios. By removing noisy and inconsistent data elements, it generates simulation instructions that maintain validation effectiveness while reducing the overall data volume and associated computational requirements.
Solution Approach 2:
The system changes the parameter representation by transforming detailed raw log data into simplified simulation instructions. This parameter transformation maintains the critical information needed for validation while reducing data complexity and computational resource consumption.
3Ease of operation
If static data is used for testing, then the testing process is simplified, but the ability to test updated system algorithms deteriorates
Solution Approach 1:
The system introduces dynamics by generating simulation scenarios from processed log data that can represent updated system algorithms. Rather than using fixed static data, the system creates adaptable simulation instructions that can be regenerated to match algorithm updates, maintaining both process simplicity and testing versatility.
4Manufacturing precision
If extensive data processing is performed to clean log data, then the simulation accuracy is improved, but the processing time increases
Solution Approach 1:
The system performs preliminary identification of inconsistent data patterns in log data before full simulation generation. By detecting and marking inconsistent data early, it enables targeted processing that improves simulation accuracy without requiring extensive processing of all data points.
Data Source
AI summary
A vehicle can capture data that can be converted into a synthetic scenario for use in a simulator. Objects can be identified in the data and attributes associated with the objects can be determined. The data can be used to generate a synthetic scenario of a simulated environment. The scenarios can include simulated objects that traverse the simulated environment and perform actions based on the attributes associated with the objects, the captured data, and/or interactions within the simulated environment. In some instances, the simulated objects can be filtered from the scenario based on attributes associated with the simulated objects and can be instantiated and/or destroyed based on triggers within the simulated environment. The scenarios can be used for testing and validating interactions and responses of a vehicle controller within the simulated environment.