LiDAR Positioning via Global and Local Map Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional autonomous driving positioning methods using LiDAR point cloud data often result in inaccurate or failed positioning due to environmental changes, as the real-time data differs significantly from the data in the positioning map.
Innovation Solution
A method that combines LiDAR point cloud data with both global and local maps to determine global and local positioning information, using inertial measurement data for motion compensation and fusion optimization to provide a stable positioning result unaffected by environmental changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional positioning methods match real-time LiDAR point cloud data with positioning map data, then positioning can be achieved under stable conditions, but positioning accuracy deteriorates when the road environment changes
Solution Approach 1:
The patent divides the positioning system into two independent modules: global positioning (matching with positioning map) and local positioning (matching with local map). Each module operates independently to determine positioning results under different environmental conditions, preventing mutual interference and maintaining reliability when environment changes occur
Solution Approach 2:
The patent dynamically switches between global and local positioning modes based on environmental change detection. When environmental changes are detected, the system transitions from relying on global positioning to local positioning, changing the operational parameters to maintain precision under varying conditions
2Area of stationary object
If only global positioning map is used for matching, then positioning can be established over large areas, but positioning accuracy decreases when environmental changes occur
Solution Approach 1:
The patent segments the positioning map into global positioning map (for large-area coverage) and local map (for high-precision local positioning). The global map provides broad coverage while the local map ensures precision in specific areas, allowing the system to maintain both extensive coverage and high accuracy simultaneously
Solution Approach 2:
The patent adds a local positioning dimension to the traditional global positioning system. By introducing local map matching as an additional positioning layer, the system enhances precision without sacrificing global coverage capability
3Loss of time
If real-time point cloud data is matched with positioning map data, then positioning results can be obtained quickly, but positioning fails or becomes inaccurate when road environment changes
Solution Approach 1:
The patent pre-builds local maps in advance during system initialization or map construction phase. When positioning is needed, the pre-prepared local maps are immediately available for matching, eliminating the time-consuming process of real-time local map construction while ensuring reliability under environmental changes
Solution Approach 2:
The patent introduces environmental change detection as an intermediary mechanism between global and local positioning. This mediator detects environmental changes and triggers the switch to local positioning mode, ensuring reliability is maintained without significant time loss through automated condition-based switching
Data Source
AI summary
The present disclosure provides a method, an apparatus, a computer device and a computer-readable storage medium for positioning, and relates to the field of autonomous driving. The method obtains point cloud data collected by a LiDAR on a device at a current time; determines, based on the point cloud data and a global map built in a global coordinate system, global positioning information of the device in the global coordinate system at the current time; and determine, based on the point cloud data and a local map built in a local coordinate system, local positioning information of the device in the local coordinate system at the current time. A positioning result of the device at the current time is determined based on at least the global positioning information and the local positioning information. Techniques of the present disclosure can provide an effective and stable positioning service.