HAV Digital Map Verification Using Sensor-Feature Comparison
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for short-term changes such as construction sites or accidents, which can lead to safety issues due to incomplete or outdated map data.
Innovation Solution
A method involving a digital map verification process that compares setpoint feature properties stored in the map with actual feature properties detected by sensors, determining a difference value to assess the map's update status and requesting updates from a central server when deviations exceed a threshold, using feature, sensor, and environment models to optimize detection and classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If digital maps are updated frequently to reflect short-term changes, then the map accuracy and up-to-date status improve, but the complexity of maintaining and updating the digital map increases
Solution Approach 1:
The system performs self-verification by automatically comparing sensor-detected feature properties with stored setpoint feature properties from the digital map. The vehicle's own sensors and processing systems serve the function of verifying map accuracy without requiring external intervention, thereby improving reliability while avoiding the complexity of external verification infrastructure.
Solution Approach 2:
The system establishes a feedback loop where verification results (difference values) are continuously monitored and compared against threshold values. When deviations exceed thresholds, the system automatically requests map updates from central servers, creating a closed-loop system that maintains map accuracy through automated feedback-driven updates rather than manual intervention.
2Reliability
If the vehicle hand over control to the driver due to outdated map data, then traffic safety is maintained, but the productivity and automation level of the vehicle decrease
Solution Approach 1:
The system performs preliminary verification of digital map accuracy by comparing setpoint feature properties with actual sensor detections before automated driving operations proceed. This advance verification ensures that map data is current and accurate, allowing the vehicle to maintain automated control without safety compromises. The verification happens proactively rather than reactively, preventing safety issues before they arise.
Solution Approach 2:
The continuous feedback mechanism monitors map accuracy in real-time, comparing detected features with digital map data. When the map is verified as up-to-date (difference values below thresholds), the system maintains automated driving capability. This feedback-driven approach ensures productivity is maximized whenever safety conditions are met, eliminating unnecessary handovers to manual control.
3Measurement precision
If the search area of the vehicle sensor system is restricted using feature properties, then the detection robustness improves, but the measurement coverage is reduced
Solution Approach 1:
The system applies local quality by using setpoint feature properties (such as expected locations, types, and characteristics of features like traffic lights, signs, and road markings) to guide sensor attention to specific local areas of interest. Rather than uniformly scanning the entire environment, the sensor system focuses computational and sensing resources on verifying specific features predicted to be present based on the digital map, thereby improving detection accuracy without proportionally increasing overall sensor coverage requirements.
Data Source
AI summary
A method and corresponding system and computer program for a highly-automated-vehicle (HAV), the method including: providing a digital-map; determining a present vehicle-position relative to the digital-map; providing at least one setpoint property of at least one feature in an HAV-environment; using at least one sensor to detect at least one actual property of a feature in the HAV-environment based at least in part on the setpoint property; comparing the actual property to the setpoint property and determining at least one difference-value based on the comparison; and verifying the digital-map, the digital-map being classified as not up-to-date if the difference-value reaches/exceeds a specified-threshold-value of a deviation, and being classified as up-to-date if the difference-value remains below the specified-threshold-value of the deviation.