Automated Vehicle Map Validation for Long-Range Route Change Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Highly automated vehicles face challenges in accurately detecting and responding to short-term route changes due to outdated digital maps and low-resolution sensors, which can compromise traffic safety, especially at high speeds.
Innovation Solution
A method that involves providing a highly accurate digital map, determining the current vehicle position, and comparing expected feature properties from the map with actual sensor data to assess the quality of sensor detections, allowing for robust detection of route changes and map validation even in long range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Length of stationary object
If sensors are used to detect features in the long range, then the detection range is improved, but the resolution and reliability of sensor data deteriorate due to low resolution and noise
Solution Approach 1:
The patent introduces digital maps as an intermediary reference system that provides expected feature properties for long-range objects. Instead of relying solely on direct sensor detection, the system uses the digital map as a mediator to supply reference data about features that are difficult to detect directly, thereby enabling reliable long-range detection without being limited by sensor resolution constraints
Solution Approach 2:
The system performs preliminary actions by pre-storing feature properties in digital maps before actual detection is needed. This allows the system to have reference information ready in advance for comparison with sensor data, enabling validation and correction of sensor detections even when the original sensor data quality is poor due to long-range detection
2Adaptability or versatility
If digital maps are used for route guidance, then navigation capability is improved, but the accuracy deteriorates when short-term route changes occur that are not reflected in the map
Solution Approach 1:
The patent implements feedback by continuously comparing sensor-detected feature properties with expected properties from digital maps. When deviations are detected (indicating short-term route changes), the system uses this feedback to identify map errors and adjust the route planning accordingly, thereby maintaining reliability despite the inherent lag in digital map updates
Solution Approach 2:
The system dynamically adjusts its operation by switching between relying on digital maps and relying on direct sensor detection based on current conditions. When the digital map is determined to be outdated or inaccurate for the current situation, the system dynamically adapts by prioritizing real-time sensor data for route determination, thus maintaining navigation reliability despite static map limitations
3Reliability
If algorithms focus on close-range position ascertainment, then detection reliability is improved, but the ability to detect distant route changes deteriorates
Solution Approach 1:
The system performs preliminary action by using digital maps to provide expected feature properties for distant features before actual detection is required. This allows the system to prepare reference data in advance for long-range objects, enabling timely detection of route changes at a distance without having to wait for close-range sensor confirmation
Solution Approach 2:
The patent uses digital maps as an intermediary to extend the effective detection range. By providing expected properties of distant features through the map, the system can detect and respond to route changes at a distance earlier than would be possible using sensor data alone, thereby reducing the time loss associated with detecting distant route changes
Data Source
AI summary
A method for operating a more highly automated vehicle (HAF), in particular a highly automated vehicle, including: S1—providing a digital map or a highly accurate digital map, in a driver-assistance-system of the HAF; S2—determining a current vehicle position and locating the vehicle position in the digital map; S3—providing at least one expected feature property of at least one feature in a surroundings of the HAF; S4—detecting at least one actual feature property of a feature in the surroundings of the HAF at least partially on the basis of the expected feature property; S5—comparing the actual feature property with the expected feature property and ascertaining at least one differential value; S6—checking the plausibility of the actual feature property at least partially on the basis of the differential value. Also described is a corresponding system and a computer program.