Graph Estimation for Road Lane Geometry Generation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing digital maps face challenges in accurately generating and updating road and lane geometry due to missing or erroneous data, which can impact route guidance and vehicle autonomy.

Innovation Solution

The method involves receiving a rasterized image representing map geometry, identifying node pixels, determining the presence and location of next nodes based on pixel properties, and generating map elements through graph estimation to update a map database.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual verification and correction of map geometry is performed, then map accuracy is improved, but labor cost and time consumption increase

Engineering Contradiction:

Improvemap geometry accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-verification and self-correction of map geometry by automatically detecting inconsistencies in lane connectivity and topology, and correcting them without human intervention. The algorithm independently identifies errors such as disconnected lanes or incorrect intersections and repairs the map data autonomously

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical verification processes are replaced with automated computational algorithms that analyze map geometry data, detect topological inconsistencies, and perform corrections. The system uses computer-based image processing and graph theory algorithms to substitute human operators in the map verification workflow

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If comprehensive map geometry data is collected, then map completeness is improved, but data errors and inconsistencies increase

Engineering Contradiction:

Improvemap completenessVSAvoiddata accuracy

Core Design Contradiction:

Loss of informationVSReliability

Solution Approach 1:

The system implements feedback mechanisms where detected map geometry errors are fed back into the processing pipeline for correction. The error detection results trigger automated correction processes that adjust the map data, and the corrected data is then re-verified to ensure consistency and accuracy

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system converts data errors and inconsistencies into beneficial information by using detected anomalies as indicators for targeted verification and correction. Errors in comprehensive data sets serve as useful signals that guide the automated system to focus on problematic areas, ultimately improving overall data quality

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

3Productivity

If automated map generation is implemented, then productivity is improved, but manufacturing precision decreases

Engineering Contradiction:

Improvemap generation speedVSAvoidlane geometry accuracy

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The system performs preliminary error detection and correction operations during the automated map generation process itself, rather than requiring separate verification stages. Topological consistency checks and geometry validation are embedded into the generation workflow, allowing errors to be prevented or corrected before final output

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces intermediate processing steps including error detection algorithms and correction mechanisms that act as mediators between automated map generation and final output. These intermediary processes analyze generated geometry data, identify inconsistencies, and perform corrections to bridge the gap between speed and accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12287225B2Method, apparatus, and computer program product for lane geometry generation based on graph estimation

Publication Date: 2025.04.29 HERE GLOBAL BV

AI summary

A method is provided for automatically creating road and lane geometry from images representing probe data within a geographical area using graph estimation. Methods may include: receiving a rasterized image representative of map geometry within a geographic area, where each pixel of the rasterized image includes a property representing at least one feature of the map geometry; identifying pixels within the rasterized image corresponding to nodes of one or more map elements as node pixels; determining, for a respective node pixel, presence of a next node based on the at least one property of the respective node pixel; determining for the respective node pixel, a location corresponding to the next node based on the at least one property of the respective node pixel; generating, from a sequence of node pixels, at least one map element; and updating a map in a map database with the at least one map element.