Digital Map Verification for Automated Vehicle Feature Disparities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Highly automated vehicles face challenges in accurately updating their digital maps to account for short-term changes such as construction sites or accidents, leading to potential safety issues due to outdated map data.
Innovation Solution
A method involving the comparison of target feature properties with actual feature properties detected by sensors, with a classification system that determines the map's up-to-dateness based on deviation thresholds, and an automated process to request updates from a central server when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If digital map data is updated frequently to reflect short-term changes, then map accuracy is improved, but system complexity and resource consumption increase
Solution Approach 1:
The system pre-defines expected feature properties (target feature properties) based on the digital map before verification. This preliminary preparation allows the system to efficiently compare actual sensor data against known expectations without requiring complex real-time processing of all possible map changes, thus improving map accuracy while controlling system complexity.
Solution Approach 2:
The system performs partial verification by focusing only on specific features and their properties that are relevant to safety and navigation. Rather than verifying entire map sections or all possible features, the system selectively verifies critical features (e.g., road markings, traffic signs, obstacles), achieving sufficient map accuracy without excessive computational resources.
2Reliability
If the vehicle reacts quickly to short-term changes in the environment, then road safety is improved, but the driver takeover time increases
Solution Approach 1:
The system pre-loads target feature properties from the digital map into the driver assistance system before the vehicle reaches those locations. This preliminary preparation enables immediate comparison with actual sensor data when features are detected, allowing the system to react quickly to changes without requiring time-consuming data retrieval or processing during critical moments.
Solution Approach 2:
The system continuously compares actual feature properties detected by sensors against target feature properties from the digital map, generating difference values that provide immediate feedback on map accuracy. This real-time feedback mechanism enables the system to detect discrepancies (such as construction sites or accidents) instantly and trigger appropriate responses, improving road safety while maintaining fast reaction times.
3Measurement precision
If the search area for feature detection is expanded to cover all possible changes, then detection completeness is improved, but processing time increases
Solution Approach 1:
The system applies local quality by focusing detection efforts on specific features and their relevant properties based on the digital map data. Rather than scanning the entire environment for all possible changes, the system selectively detects features at expected locations (e.g., road markings at lane boundaries, traffic signs at intersections) with properties matching the target feature properties. This localized approach ensures detection completeness for critical features while minimizing processing time.
Data Source
Figure 1
AI summary
The invention relates to a method for verifying a digital map of a more highly automated vehicle (HAF), in particular of a highly automated vehicle, comprising the steps of: S1 providing a digital map, preferably a highly accurate digital map, in a driver assistance system of the HAF; S2 determining a present vehicle position and locating the vehicle position in the digital map; S3 providing at least one setpoint feature property of at least one feature in an environment of the HAF; S4 detecting at least one actual feature property of a feature in the environment of the HAF at least in part on the basis of the setpoint feature property, the detecting being performed by means of at least one sensor; S5 comparing the actual feature property with the setpoint feature property and ascertaining at least one difference value as the result of the comparison; S6 verifying the digital map at least in part on the basis of the difference value, the digital map being classified as not up-to-date if the difference value reaches or exceeds a stipulated threshold value for a disparity and being classified as up-to-date if the difference value remains below the stipulated threshold value for the disparity. The invention further relates to a corresponding system and to a computer program.