Map Geometry Generation via Data Aggregation and Conflation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital maps, especially high-definition maps, face challenges in accurately generating and maintaining map geometry, particularly lane geometry, due to issues like missing or erroneous data, which can impact route guidance and vehicle autonomy.
Innovation Solution
The method involves aggregating and conflating data from various sources using statistical analysis and Bayesian inference to automatically generate and update map geometry, including road and lane geometries, by rasterizing objects and extracting analytic geometries from raster images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data from multiple sources is aggregated and conflated using statistical analysis, then map geometry accuracy is improved, but processing complexity and computational requirements increase
Solution Approach 1:
The patent segments the map generation process into distinct modules: data collection from multiple sources, data aggregation, statistical conflation analysis, and map geometry generation. Each module processes specific tasks independently, reducing overall complexity while maintaining accuracy through coordinated operation of specialized processing units.
Solution Approach 2:
The patent introduces statistical analysis as an intermediary layer between raw multi-source data and final map geometry. This intermediary processing layer consolidates and reconciles data from diverse sources through probabilistic models, transforming complex multi-source data into unified accurate geometry without requiring direct complex processing of all source data simultaneously.
2Measurement precision
If manual verification of map geometry is performed, then accuracy can be ensured, but time consumption and labor requirements increase
Solution Approach 1:
The patent implements self-service verification through automated statistical conflation analysis that continuously validates map geometry against aggregated data from multiple sources. The system automatically detects and corrects geometric inaccuracies by comparing generated geometry with observed data patterns, eliminating the need for manual verification while maintaining high accuracy standards.
Solution Approach 2:
The patent establishes feedback loops where map geometry generation results are continuously fed back into the statistical conflation analysis. This feedback mechanism allows the system to automatically adjust and refine geometry based on observed data patterns, ensuring accuracy without requiring manual verification time.
3Quantity of substance
If high-definition maps with rich content are created, then information completeness is improved, but data corruption from missing or erroneous information increases
Solution Approach 1:
The patent applies local quality analysis by evaluating the reliability and completeness of different map elements independently through statistical conflation. Each geographic feature and data element is assessed individually against observed data patterns, allowing the system to maintain high information completeness while identifying and excluding corrupted or erroneous data locally without affecting the entire map dataset.
Data Source
AI summary
A method is provided automatically creating map geometry from data from various sources gathered within a geographical area using data aggregation and conflation with statistical analysis. Methods may include: receiving observation data associated with a geographic area; rasterizing objects within the observation data onto corresponding channels in a raster image corresponding to the geographic area having a given resolution; determining a distribution of locations of the objects parameterized by values in different channels in the raster image from the observation data; extracting analytic geometries from the raster image; generating map geometry based on the extracted analytic geometries; and updating a map database with the generated map geometry.