Vehicle Environment Sensor Evaluation Using False-Negative Time Classes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating the performance of vehicle environment sensors, particularly in automated driving systems, do not effectively account for false negatives and their duration, which can impact the safety and reliability of autonomous operations.
Innovation Solution
A method and device that continuously record false negatives of environment sensors, classify them by chronological length, determine false negative rates for each time class, set thresholds for these rates, and evaluate sensor performance as impaired if the thresholds are exceeded, ensuring that only sensors meeting predetermined requirements are used for automated driving operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If environment sensors are used for automated driving operations, then the vehicle can perform autonomous driving functions, but the safety and reliability are compromised due to undetected false negatives in sensor performance
Solution Approach 1:
The system performs preliminary evaluation of sensor performance by continuously monitoring false negatives and classifying them by duration before automated driving operations commence. This advance assessment ensures that sensors meet reliability requirements prior to use, preventing safety compromises while enabling automation.
Solution Approach 2:
The system implements continuous feedback monitoring of sensor performance by recording false negatives, calculating false negative rates for different time classes, and comparing these rates against predetermined thresholds. This feedback mechanism dynamically assesses sensor reliability and prevents use of degraded sensors, maintaining safety while enabling automated operations.
2Ease of operation
If simple detection methods are used for sensor evaluation, then the evaluation process is straightforward, but false negatives and their durations are not properly accounted for, compromising safety
Solution Approach 1:
The evaluation process segments false negatives into different time classes based on their duration. By dividing the assessment into discrete categories (time classes with thresholds), the system maintains operational simplicity while accurately capturing the impact of different false negative durations on safety, resolving the contradiction between ease of operation and assessment accuracy.
3Reliability
If continuous monitoring of false negatives is implemented, then sensor performance reliability is improved, but the complexity of the evaluation device increases
Solution Approach 1:
The evaluation device is designed to perform multiple functions: recording false negatives, classifying them by time duration, calculating false negative rates for each time class, and comparing against thresholds. This multi-functional approach consolidates complex monitoring tasks into a single integrated system, improving reliability while managing device complexity through functional consolidation.
4Ease of operation
If all false negatives are treated equally regardless of duration, then the evaluation process is simple, but the distinction between temporary and persistent sensor failures is lost, reducing safety
Solution Approach 1:
The system applies different evaluation criteria to different time classes of false negatives. By assigning specific thresholds to different duration categories (local quality assessment), the system distinguishes between temporary and persistent failures, improving failure detection accuracy while maintaining a structured, manageable evaluation process.
Data Source
AI summary
Performance of at least one environment sensor of a vehicle is evaluated by recording false negatives of the environment sensor regarding a reference object, classifying the false negatives recorded according to chronological length and respectively assigning the false negatives to one of several pre-determined time classes. A false negative rate for each of the time classes is determined specifying how often false negatives of the respective time class occur during the evaluation period. A false negative threshold is predetermined for each of the time classes. For each time class it is determined how often the false negative rate of the time class exceeds the false negative threshold pre-determined for the time class. The performance of the environment sensor is evaluated as impaired if the number of instances in which the false negative threshold for the respective time class is exceeded by the false negative rate is higher than a value for the respective time class.