Road Network Mapping with Lattice and Dipole Graph Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face challenges in generating accurate and efficient road network data for designing short-term and long-term driving plans, as existing methods are complex and difficult to maintain, especially when managing connections between roads and lanes.
Innovation Solution
A server-based system that collects and processes road network data, generates lattice road network data for short-term plans, and crossable dipole graphs for long-term plans, using sensor data and external information sources to create a road network map that facilitates autonomous vehicle navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If complex existing methods are used to generate road network data, then comprehensive road network information can be obtained, but the system becomes difficult to maintain and manage
Solution Approach 1:
The patent segments the road network data generation process into distinct modules: lattice road network data generation for short-term plans and crossable dipole graph generation for long-term plans. This modular segmentation makes the system easier to maintain while preserving comprehensive road network information coverage.
2Measurement precision
If detailed road network data is generated for both short-term and long-term plans, then navigation accuracy improves, but data processing complexity increases
Solution Approach 1:
The patent divides navigation planning into short-term and long-term components, each with specialized data structures. Lattice road network data handles short-term precise navigation while crossable dipole graphs handle long-term route planning, reducing overall processing complexity while maintaining high accuracy.
Solution Approach 2:
The patent introduces different representational dimensions for different planning horizons: lattice structures for spatial precision in short-term planning and graph-based crossable dipole representations for temporal routing in long-term planning, optimizing accuracy for each dimension.
3Reliability
If comprehensive road and lane connection information is managed, then route planning quality improves, but maintenance difficulty increases
Solution Approach 1:
The patent segments connection information management into separate lattice road network structures and crossable dipole graph structures. Each segment handles specific types of connections independently, improving route planning quality while making maintenance easier through localized updates.
Data Source
Figure 1~2
Figure 3~4
Figure 5~7
AI summary
Provided are a method, a server, and a computer program for creating a road network map to design a driving plan for an autonomous driving vehicle. A method of creating a road network map to design a driving plan for an autonomous driving vehicle is performed by a computing device and includes: generating road network data for an area; generating lattice road network data for a short-term driving plan for an autonomous driving vehicle using the generated road network data; and generating a crossable dipole graph for a long-term driving plan for the autonomous driving vehicle using the generated lattice road network data.