Map Accuracy Evaluation for Autonomous Driving Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems do not adequately evaluate map accuracy, which is crucial for safe and efficient autonomous driving control, as they primarily focus on driver intervention rather than the reliability of map information.
Innovation Solution
An autonomous driving system that includes a target object position recognition unit, vehicle position recognition unit, relative-relationship-on-map acquisition unit, detected-relative-relationship acquisition unit, map accuracy evaluation unit, and autonomous driving permission unit, which assesses map accuracy by comparing relative relationships on the map with detected relationships using vehicle-mounted sensors and permits autonomous driving based on the evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous driving control uses map information without adequate accuracy evaluation, then the system can operate continuously, but the reliability of autonomous driving is compromised
Solution Approach 1:
The system performs preliminary map accuracy evaluation before permitting autonomous driving control. The map accuracy evaluation unit assesses whether map information meets required accuracy standards in advance, and only permits autonomous driving when the map is confirmed to be sufficiently accurate, preventing unreliable operation
Solution Approach 2:
The system continuously monitors map accuracy by comparing map information with actual sensor detection results. When map accuracy falls below thresholds, the system provides feedback by restricting autonomous driving permission, creating a closed-loop control mechanism that maintains reliability
2Measurement precision
If the system evaluates map accuracy using multiple target objects and their types, then the accuracy evaluation becomes more comprehensive, but the complexity of processing increases
Solution Approach 1:
The system segments the map accuracy evaluation process by target object types (e.g., intersections, curves, slopes). Different evaluation criteria and weights are applied to different object types, allowing comprehensive assessment while organizing complexity into manageable segments
Solution Approach 2:
The system applies different evaluation standards and weights to different locations and object types on the map. Critical areas like intersections receive higher evaluation weights and stricter accuracy requirements, while less critical areas use standard evaluation, optimizing both precision and processing efficiency
Data Source
AI summary
An autonomous driving system includes a target object position recognition unit configured to recognize a target object position detected by a vehicle-mounted sensor based on map information in a map database, a vehicle position recognition unit configured to recognize a vehicle position, a relative-relationship-on-map acquisition unit configured to acquire a relative-relationship-on-map between the target object and the vehicle based on the target object position and the vehicle position on the map, a detected-relative-relationship acquisition unit configured to acquire a detected-relative-relationship between the target object detected by the sensor and the vehicle based on a result of detection performed by the sensor, a map accuracy evaluation unit configured to evaluate map accuracy of the map information based on the relative-relationship-on-map and the detected-relative-relationship, and an autonomous driving permission unit configured to permit an autonomous driving control using the map information based on the result of evaluation of the map accuracy.