Autonomous Vehicle Road Map Generation Using Polygonal Hub Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Generating high definition vector maps for autonomous driving is challenging due to the complexity of linking navigation information and traffic control indications with reference paths, requiring significant effort and labor.
Innovation Solution
A method for generating high definition maps involves obtaining an original road map, generating reference paths through crossroad junctions, creating a polygonal hub to encompass the junction, and automatically linking navigation information and traffic control indications based on geometrical relationships between binders, allowing for efficient and accurate navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used to link navigation information and traffic control indications with reference paths, then accuracy can be maintained, but the process requires tremendous effort and time
Solution Approach 1:
The system performs automatic self-linking of navigation information and traffic control indications to reference paths using geometric algorithms. The computer automatically identifies relationships between map elements and generates linkages without human intervention, allowing the system to serve itself in the map generation process
Solution Approach 2:
The patent replaces manual mechanical linking processes with automated computer-based algorithms. The system uses geometric calculations and spatial relationship analysis to automatically establish connections between navigation elements and reference paths, substituting human manual operations with computational processes
2Reliability
If detailed navigation information is included in HD vector maps, then autonomous driving decision-making capability is improved, but the complexity of processing and linking this information increases
Solution Approach 1:
The patent segments the complex task of map generation into distinct automated steps: generating reference paths, identifying geometric relationships, linking navigation information, and associating traffic control indications. This segmentation allows the system to handle detailed information through systematic automated processing rather than overwhelming manual analysis
3Productivity
If automated methods are used to generate HD vector maps, then productivity is improved, but precision in linking navigation information may deteriorate
Solution Approach 1:
The patent replaces manual linking operations with automated geometric algorithms that calculate spatial relationships between map elements. The computer uses mathematical models to determine precise connections between reference paths, navigation information, and traffic control indications, ensuring accuracy through computational precision rather than human judgment
Solution Approach 2:
The system introduces geometric relationship analysis as an intermediary process between automated map generation and final linking accuracy. By using geometric calculations as a mediator, the system ensures that automated linking maintains precision through objective mathematical criteria rather than direct automated assignment
Data Source
AI summary
A method for generating a road map for vehicle navigation comprises: receiving an original road map having a crossroad junction, an inward lane entering the crossroad junction, and an outward lane leaving the crossroad junction; generating a reference path capable of guiding a vehicle driving from the inward lane to the outward lane through the crossroad junction; generating a polygonal hub that encompasses the crossroad junction, wherein the reference path enters and leaves the hub by crossing a first binder and a second binder, respectively; and generating automatically a type of the reference path based on the geometrical relationship between the first binder and the second binder.