Self-Driving Map Construction for Accurate Lane and Intersection Topology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing map construction methods for autonomous driving, indoor mapping, and topology mapping lack accuracy, particularly in complex scenarios like automated valet parking, and fail to provide essential road and lane boundary information and traffic direction guidance.
Innovation Solution
An autonomous driving map construction method that obtains road, intersection, and lane information using manual driving track data and obstacle grid maps, employing techniques such as track point buffer regions, equi-spaced point forming, and Thiessen polygons to enhance map accuracy, enabling the provision of road boundaries, lane boundaries, and traffic direction information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional obstacle grid map construction methods are used, then the map construction process is simple, but the map accuracy is low and cannot provide road boundaries, lane boundaries, or traffic direction information
Solution Approach 1:
The map construction process is segmented into multiple specialized modules: road boundary detection module, lane boundary detection module, traffic direction detection module, and intersection detection module. Each module focuses on extracting specific types of information from driving track data, enabling comprehensive and accurate map construction without requiring a single complex system.
Solution Approach 2:
The system performs preliminary processing of driving track data by generating buffer regions around track points before extracting boundary information. This preliminary action of creating buffer zones facilitates subsequent boundary detection and ensures accurate road and lane boundary extraction.
2Measurement precision
If random vehicle driving tracks are used for topology map construction, then data collection is easy, but the topology map accuracy is low and cannot meet multiple scenarios
Solution Approach 1:
The constructed autonomous driving map serves multiple functions simultaneously: it provides road boundaries for navigation, lane boundaries for path planning, traffic direction information for route selection, and intersection information for complex maneuver guidance. This multi-functional map structure enables the system to meet various driving scenarios including automated valet parking, public road navigation, and complex intersection handling.
Solution Approach 2:
The system continuously refines the autonomous driving map by incorporating new driving track data. The map construction module processes additional driving tracks and updates the map information, ensuring that the map remains accurate and up-to-date as the vehicle operates in different scenarios and conditions.
Data Source
Figure 1A
Figure 1B~1C
Figure 1D
AI summary
A map construction method and a related apparatus are provided. The method includes: obtaining, based on manual driving track data and/or an obstacle grid map, road information, intersection information, and lane information of a region through which a vehicle has traveled (101); obtaining road traffic direction information based on the manual driving track data and the road information, and obtaining lane traffic direction information based on the lane information and the road traffic direction information (102); obtaining intersection entry and exit point information based on the intersection information and the lane traffic direction information (103); and performing, based on the intersection entry and exit point information, an operation of generating a virtual topology center line to obtain an autonomous driving map of the region through which the vehicle has traveled, where the virtual topology center line is a traveling boundary line of the vehicle in an intersection region (104).