Automated Vehicle Map Validation for Early Route Change Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current highly automated vehicle systems face challenges in accurately detecting short-term route changes due to outdated digital maps, which can lead to safety issues, as existing sensors have low resolution and are prone to noise, limiting their ability to react to distant environmental features effectively.
Innovation Solution
A method that provides a high-precision digital map with target feature properties for comparison with actual sensor data, allowing for the detection of differences and plausibility checks to validate the digital map's accuracy, thereby enabling robust and reliable long-distance sensor detection and early detection of route changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If sensors are used to detect environmental features at long distances, then the vehicle can react to route changes earlier, but the sensor data quality deteriorates due to low resolution and noise
Solution Approach 1:
The patent introduces digital map data as an intermediary reference to validate and supplement sensor detections. By comparing sensor-detected feature properties against stored digital map properties, the system can confirm long-distance detections that would otherwise be unreliable due to noise and low resolution. This mediator approach allows the system to trust sensor data from greater distances than would be safe without validation.
Solution Approach 2:
The system implements feedback by continuously comparing sensor measurements with digital map references and using this comparison to adjust confidence in detections. When sensor data quality is poor (at long distances), the feedback loop uses digital map consistency checks to maintain detection reliability, enabling the system to utilize long-distance sensor data safely.
2Measurement precision
If digital maps are used for vehicle localization, then positioning accuracy is improved, but the maps become outdated and fail to reflect short-term route changes
Solution Approach 1:
The system performs preliminary validation by comparing sensor detections against digital map data before fully trusting either source. This preliminary comparison action allows the system to identify when digital map data may be outdated (when sensor detections consistently differ from map expectations) and trigger appropriate responses such as alerting the driver or adjusting localization confidence.
Solution Approach 2:
The system dynamically adjusts its reliance on digital map data versus sensor data based on the degree of agreement between them. When sensor detections align with digital map features, the system trusts the high-precision map positioning. When discrepancies arise indicating short-term changes, the system dynamically shifts to rely more on real-time sensor data and reduces trust in the static digital map.
3Reliability
If sensor detection algorithms focus on close-range features, then detection reliability is improved, but the vehicle cannot detect distant route changes in time
Solution Approach 1:
The patent uses digital map data as an intermediary to enable reliable long-distance detection. By validating sensor detections against the digital map reference, the system can confidently accept feature detections at long distances that would otherwise be too noisy and unreliable. This intermediary validation mechanism extends the effective detection range without sacrificing reliability.
4Measurement precision
If more sensors are added to improve environment recording, then detection capability is improved, but system complexity and cost increase
Solution Approach 1:
The patent makes the existing sensor system multi-functional by adding software-based validation against digital map data. Rather than adding more physical sensors, the system uses the existing sensors in combination with digital map references to achieve higher effective measurement precision. This universal approach allows the same sensor hardware to provide both close-range reliable detection and extended-range detection when validated against map data.
Data Source
Figure 1
Figure 2a~3c
AI summary
The invention relates to a method for operating a more highly automated vehicle, in particular 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 highly automated vehicle; S2 determining a current vehicle position and locating the vehicle position in the digital map; S3 providing at least one desired feature property of at least one feature in an environment of the highly automated vehicle; S4 detecting at least one actual feature property of a feature in the environment of the highly automated vehicle at least partially on the basis of the desired feature property; S5 comparing the actual feature property with the desired feature property and determining at least one difference value; S6 checking the plausibility of the actual feature property at least partially on the basis of the difference value. The invention further relates to a corresponding system and to a computer program.