Lane Centerline Network Generation From GPS Trajectories and Map Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining lane centerline networks in autonomous driving rely heavily on expensive equipment and complex image processing, making them costly and labor-intensive, and often fail to accurately reflect real road conditions.
Innovation Solution
A method using a vehicle's GPS and image capturing device to generate road feature information, determine section nodes, and estimate lane centerlines, which then creates a lane centerline network based on reliability and geometry, without direct image use, thus being lightweight and cost-effective.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive equipment and complex image processing are used to determine lane centerline networks, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts and utilizes readily available GPS trajectory data and basic road map information, separating the lane centerline determination task from complex image processing requirements. By taking out only the essential positioning data needed and eliminating the need for expensive imaging equipment, the solution achieves cost reduction while maintaining determination capability
Solution Approach 2:
The patent creates a virtual representation of the lane centerline network by copying and processing GPS trajectory points and road map data. Instead of using physical image capturing devices, it generates a digital model of lane centers through computational processing of position data, achieving the same functional outcome with simpler means
2Manufacturing precision
If complex image processing is used to generate road feature information, then manufacturing precision is improved, but loss of time and productivity decrease
Solution Approach 1:
The patent performs preliminary matching between GPS trajectories and road map data before generating lane centerline information. By pre-processing the trajectory data to align with known road geometries and extracting road features directly from matched positions, it eliminates the need for time-consuming image processing while maintaining accuracy
Solution Approach 2:
The patent replaces the mechanical image processing system with a computational geometry approach. Instead of capturing and analyzing visual images of roads, it uses mathematical processing of GPS coordinate data and digital road map information to determine lane centers, significantly reducing processing time while maintaining precision
3Measurement precision
If direct image-based methods are used to determine lane centerlines, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent makes the GPS positioning system perform multiple functions: it not only provides location information but also serves as the primary data source for lane centerline determination. By making the existing GPS device multi-functional, the solution eliminates the need for separate image capturing equipment while maintaining determination accuracy
Solution Approach 2:
The patent introduces road map data as an intermediary between GPS trajectories and lane centerline determination. The digital road map serves as a mediator that bridges raw position data and lane geometry information, enabling accurate lane center calculation without direct image processing
Data Source
AI summary
The disclosure relates to a method and an apparatus for determining a lane centerline network. A lane centerline network determination method according to an embodiment of the disclosure may include obtaining a driving trajectory of a vehicle by using a global positioning system (GPS) mounted on the vehicle, matching a road map with the driving trajectory, generating road feature information considering the driving trajectory based on an image captured by an image capturing device mounted on the vehicle, determining a position of a section node dividing a road on the road map into a plurality of sections based on the road feature information, determining a lane centerline placement for each section by determining a lane centerline for the traveling lane of the vehicle among a plurality of lanes included in the section based on the driving trajectory, and estimating lane centerlines for remaining lanes, determining a final longitudinal position of the section node based on reliability of the section node for each of driving trajectories through which the vehicle has passed a same road repeatedly, determining a section network connection relationship between the section, a previous section, and a next section based on the lane centerline placement for each section, determining a geometry of the lane centerline placement for each section based on reliability of a section link connecting the section nodes to each other, and generating a lane centerline network based on the section network connection relationship and a lane centerline geometry within the section.