Traffic Sign Map Reconciliation for Real-Time Vehicle Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing approaches for fusing sensor data with map data in autonomous or semi-autonomous vehicles require high processing power and computation time, making real-time evaluation challenging, especially for reliable position determination and decision-making.
Innovation Solution
A device and method that efficiently assign sensor data with map data by focusing on traffic signs, using an iterative closest point algorithm to determine a certainty parameter for reliable assignment, allowing for extended planning horizons based on high reliability assignments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If comprehensive sensor data and map data fusion is performed for reliable position determination, then the reliability of autonomous vehicle operations is improved, but the processing power and computation time requirements increase
Solution Approach 1:
The patent extracts and focuses on specific key features (traffic signs) from the comprehensive sensor data and map data, rather than processing all available data. The evaluation unit identifies visible traffic signs from sensor data and reads known traffic signs from map data, then the assignment unit assigns visible traffic signs to known traffic signs to determine position. This selective extraction of relevant information reduces processing power requirements while maintaining reliability for autonomous vehicle operations.
2Reliability
If comprehensive sensor data and map data fusion is performed for reliable position determination, then the reliability of autonomous vehicle operations is improved, but the computation time increases
Solution Approach 1:
The patent extracts and focuses on specific key features (traffic signs) from the comprehensive sensor data and map data, rather than processing all available data. The evaluation unit identifies visible traffic signs from sensor data and reads known traffic signs from map data, then the assignment unit assigns visible traffic signs to known traffic signs to determine position. This selective extraction of relevant information reduces computation time while maintaining reliability for autonomous vehicle operations.
3Speed
If real-time evaluation of sensor data and map data is performed, then the speed of decision-making is improved, but the processing power requirement increases
Solution Approach 1:
The patent extracts and focuses on specific key features (traffic signs) from the comprehensive sensor data and map data, rather than processing all available data. The evaluation unit identifies visible traffic signs from sensor data and reads known traffic signs from map data, then the assignment unit assigns visible traffic signs to known traffic signs to determine position. This selective extraction of relevant information reduces processing power requirements while enabling real-time evaluation and decision-making for autonomous vehicle operations.
Data Source
AI summary
A device (14) for fusing sensor data with map data, includes: an input interface (24) for receiving sensor data of a surroundings sensor (18) with information regarding objects in the surroundings of a vehicle (12) and for receiving map data with information regarding the vehicle surroundings; an evaluation unit (26) for recognizing visible traffic signs (20) in the vehicle surroundings on the basis of the sensor data and for reading out known traffic signs in the vehicle surroundings from the map data; and an assignment unit (28) for assigning the visible traffic signs to the known traffic signs and for determining a certainty parameter which indicates a probability of a correct assignment.