ADS Safety Policy Mapping for Targeted Road Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ensuring the safety requirements of Autonomous Driving Systems (ADS) are effectively proven, particularly in the absence and presence of faults, remains a significant challenge due to the complexity of modeling and predicting their behavior, which hinders widespread market adoption.
Innovation Solution
An ADS development system that derives parameter-specific safe driving policies based on safety requirements and operational parameters, identifies uncertainties that need further observation, and generates mappings associating geographical locations with operational parameters requiring further data collection to relax safety requirements, thereby optimizing performance and data collection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If more data collection and operational hours are gathered to improve ADS performance and safety proof, then safety requirement fulfilment is improved, but development time and complexity increase
Solution Approach 1:
The system performs preliminary actions by proactively identifying operational parameters with high uncertainty and their associated geographical locations before full-scale data collection begins. The mapping generation and uncertainty analysis are conducted in advance to guide targeted data collection efforts, rather than collecting data uniformly across all operational parameters.
Solution Approach 2:
The system segments the operational parameters into distinct categories based on their uncertainty levels and impact on safety requirements. By identifying specific parameters that need further observance and mapping them to particular geographical locations, the system divides the complex data collection task into manageable, targeted segments rather than treating all parameters uniformly.
2Reliability
If comprehensive modeling of ADS behavior is performed to prove safety, then safety proof reliability is improved, but system complexity increases
Solution Approach 1:
The system extracts and focuses only on the critical operational parameters that have high uncertainty and significant impact on safety requirements. By identifying and isolating these key parameters rather than modeling all possible ADS behaviors comprehensively, the system reduces modeling complexity while maintaining safety proof reliability.
Solution Approach 2:
The system applies local quality by treating different operational parameters differently based on their specific characteristics. Parameters with high uncertainty and high impact receive targeted attention and detailed modeling, while parameters with low uncertainty or low impact are handled more simply. The geographical mapping further localizes the analysis to specific areas where particular parameters need observance.
3Reliability
If uniform data collection across all operational parameters is performed, then completeness of safety proof is improved, but resource efficiency decreases
Solution Approach 1:
The system performs preliminary uncertainty analysis and parameter identification to determine which operational parameters require further observance before initiating data collection. This preliminary action enables resource-efficient targeted collection rather than uniform collection across all parameters.
Solution Approach 2:
The system segments operational parameters based on their uncertainty levels and safety impact, then maps them to specific geographical locations. This segmentation enables selective data collection focused on critical parameters in specific areas, improving resource efficiency while maintaining completeness of safety proof.
Data Source
AI summary
A method performed by an Automated Driving Systems (ADS) development system for supporting proving fulfilment of safety requirements imposed on ADSs. The ADS development system derives a corresponding set of parameter-specific ADS safe driving policies, each safe driving policy exhibiting a respective uncertainty. The ADS development system identifies at least a first parameter-specific ADS safe driving policy inflicted with an uncertainty fulfilling predeterminable criteria, which criteria filters out uncertainties indicating, respectively, that the corresponding operational parameter needs to be further observed in order to relax the ADS's currently allowed safety requirements-fulfilled ADS safe driving policy. The ADS development system identifies at least a first geographical location exhibiting conditions allowing the operational parameter(s) in need of further observance, to be observed. The ADS development system generates a mapping associating the identified at least first geographical location with the operational parameter(s) in need of further observance.