Automated Map Verification for High-Definition Vehicle Map Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The creation and verification of high-definition maps for autonomous vehicles is a time-consuming and costly process due to the noise in sensor-generated data, necessitating extensive manual checks for accuracy.
Innovation Solution
An automated method and system for comparing freshly generated maps with reference maps using predefined quality measures to identify deviations, allowing for initial quality assurance and reducing manual effort by focusing on specific deviation regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual checking is used to verify map accuracy, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The patent segments the map verification process into automated comparison operations that divide the map into discrete features (lane markings, road signs, intersections) and systematically compare each against reference data, enabling parallel processing and significantly improving productivity while maintaining precision
Solution Approach 2:
The patent replaces the mechanical manual checking process with an automated computer-based system that uses algorithms to compare map features against reference maps and detect deviations, eliminating human labor while maintaining or improving verification accuracy
2Productivity
If automated accuracy check is implemented, then productivity is improved, but device complexity worsens
Solution Approach 1:
The patent implements a universal automated verification system that can handle multiple types of map features (lane markings, road signs, intersections, traffic lights) and various sensor data formats through a single integrated platform, reducing overall system complexity despite the sophisticated verification tasks performed
Solution Approach 2:
The patent introduces an intermediary reference map layer that serves as a standardized comparison基准 between the generated map and ground truth data, simplifying the verification process by providing a consistent reference framework rather than requiring direct complex comparisons between multiple variable data sources
3Reliability
If comprehensive manual verification is performed, then reliability is improved, but loss of time worsens
Solution Approach 1:
The patent performs preliminary automated verification checks immediately after map generation, identifying and flagging potential errors before comprehensive manual review, which reduces the time required for full verification while maintaining high reliability by catching issues early in the process
Solution Approach 2:
The patent implements feedback mechanisms where verification results are automatically fed back into the map generation process, allowing for real-time corrections and iterative improvement of map accuracy, thereby maintaining high reliability while reducing overall verification time through continuous refinement
Data Source
AI summary
A method for creating map data for the operation of an automated and/or assisting system of a vehicle or robot. A map for a traffic route portion of a traffic route is compared with a reference map for the traffic route portion on an automated basis. The map is used exclusively for creating the map data on an automated basis when the map does not deviate from the reference map by a predefined extent with regard to at least one predefined quality measure.