Map Feature Association for Accurate Vehicle-Based Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing map update systems face inaccuracies due to erroneous recognition or recording of similar features, leading to improper association and increased data redundancy.
Innovation Solution
A map update device that utilizes feature group information to associate collected data with registered features of the same type or similar types, updating positions and types based on multiple data points, and incorporates confidence scores for precise mapping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If feature data is associated only with features of the same type among recorded features, then the association process is simple, but similar features of different types cannot be properly associated leading to inaccurate map updating
Solution Approach 1:
The patent merges the association criteria by combining both exact type matching and group-based similarity matching. The server associates feature data with registered features not only when types exactly match but also when types belong to the same group indicating similarity, thereby resolving the contradiction between simple association processes and accurate map updating.
2Reliability
If the system collects data from multiple vehicles for map updating, then the map accuracy can be improved, but the amount of data to be processed increases significantly
Solution Approach 1:
The patent extracts and utilizes the group information from registered features to organize and categorize features by similarity. By pre-grouping features into categories based on their characteristics, the system can efficiently process and associate data from multiple vehicles without handling each individual feature separately, thereby reducing the computational burden while maintaining map accuracy.
3Reliability
If the system processes all collected feature data for every map update, then comprehensive updating is achieved, but processing time and computational resources increase
Solution Approach 1:
The patent segments the feature data processing by dividing features into different groups based on their types and similarities. This segmentation allows the server to process each group independently and efficiently, applying appropriate association rules for each category, thereby reducing overall processing time while maintaining comprehensive updating of the map.
Data Source
AI summary
A map update device includes a processor configured to identify one or more registered features within a predetermined distance of the position of a feature indicated by feature data received from a vehicle among individual registered features represented in map information, associate the feature indicated by the feature data with a registered feature of the same type as the feature indicated by the feature data or of a type belonging to the same group as the type of the feature among the one or more identified registered features, by referring to feature group information indicating two or more similar types among a plurality of types of the features as the same group, and update at least the position or type of a registered feature, based on the positions or types of the features indicated by the feature data associated with the registered feature.