Lane Touch Root-Cause Analysis for Automated Driving Programs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the cause of lane touch events in autonomous vehicles are time-consuming and subjective, requiring manual engineering review, which hinders the improvement and redesign of guidance systems.
Innovation Solution
A system comprising sensors and a processor that detect lane touch events by analyzing external and internal parameters, identifying the failure domain, and adjusting the driving system's design to prevent future occurrences, including error detection in vehicle sensing, path planning, and vehicle control domains.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual engineering review is used to determine the cause of lane touch events, then detailed analysis can be performed, but the process becomes time-consuming and subjective
Solution Approach 1:
The system performs self-diagnosis by automatically analyzing sensor data to identify the root cause of lane touch events. The processor executes algorithms that compare sensor data against predefined criteria to autonomously determine whether lane touch events are caused by guidance system errors or vehicle dynamics characteristics, eliminating the need for manual engineering review.
Solution Approach 2:
The manual mechanical review process is replaced with an automated electronic analysis system. The processor uses computer algorithms to substitute human engineers in reviewing sensor data, automatically identifying failure domains and generating diagnostic reports, thereby reducing both time consumption and subjectivity in the analysis process.
2Measurement precision
If comprehensive sensor data collection is implemented to accurately determine lane touch causes, then analysis accuracy improves, but system complexity increases
Solution Approach 1:
The complex data processing task is segmented into distinct analytical modules. The system separately evaluates guidance system performance data and vehicle dynamics data using different assessment criteria. This segmentation allows the processor to handle each type of data with specialized algorithms, reducing overall processing complexity while maintaining high detection accuracy.
Solution Approach 2:
The system introduces an intermediary processing layer that standardizes sensor data from multiple sources before analysis. This intermediary layer normalizes data formats and filters irrelevant information, simplifying the subsequent causal analysis process while preserving the accuracy needed to distinguish between guidance system errors and vehicle dynamics characteristics.
Data Source
AI summary
A system for designing a driving system for a vehicle. The system includes a first sensor, a second sensor and a processor. The first sensor is configured to obtain an external parameter indicative of a lane marking during a time period in which an automated driving program is being operated at the vehicle. The second sensor is configured to obtain an internal parameter of the vehicle during the time period. The processor is configured to detect a lane touch event occurring during the time period, determine an error occurring in the driving system resulting in the lane touch event based on the internal parameter and the external parameter, identify a failure domain of the driving system in which the error occurs, and change a design of a program of the driving system related to the failure domain.