Map Data Fusion with Delayed Coordinate Offset for Vehicle Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face low accuracy in positioning due to accumulated errors introduced by the conversion from the WGS84 to the GCJ-02 coordinate system, which cannot be sensed or eliminated, leading to increased errors in navigation and positioning data.
Innovation Solution
The method involves processing map data without offsetting in the data fusing unit, ensuring that the fused positioning data remains in the WGS84 coordinate system, and then performing offset processing only after fusion is complete to generate target positioning data in the GCJ-02 coordinate system, thereby eliminating accumulated errors and improving positioning accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If coordinate system conversion from WGS84 to GCJ-02 is performed during data fusion, then positioning data can comply with regulatory requirements, but accumulated errors are introduced that cannot be sensed or eliminated
Solution Approach 1:
The patent segments the coordinate conversion process into two distinct stages: (1) data fusion is performed in the WGS84 coordinate system without conversion, and (2) coordinate conversion to GCJ-02 is applied only in the final positioning output stage. This segmentation prevents the propagation of conversion errors through the data fusion process while still delivering compliant positioning results.
Solution Approach 2:
The patent performs data fusion in advance using the original WGS84 coordinate system before any coordinate conversion takes place. By completing the fusion operation preliminarily in the more accurate coordinate system, the system avoids introducing conversion errors into the fusion calculations, and only applies the necessary coordinate transformation at the final output stage.
2Adaptability or versatility
If coordinate system offset is applied during each positioning operation, then encrypted map data can be used, but non-linear random errors accumulate and degrade positioning accuracy
Solution Approach 1:
The patent extracts the coordinate conversion operation from the iterative positioning loop and applies it only once at the final output stage. By removing the repeated coordinate offset operations from each positioning cycle, the system eliminates the accumulation of non-linear random errors while maintaining the ability to use encrypted GCJ-02 map data for positioning.
Solution Approach 2:
Instead of converting coordinates at each positioning step (the conventional approach), the patent inverts the sequence by performing all positioning calculations in the WGS84 system and applying the coordinate transformation only at the end. This inversion of the processing sequence prevents error accumulation while achieving the same compliance goal.
Data Source
AI summary
The present application discloses a method and an apparatus for processing map data, which relate to autonomous driving technologies in the field of data processing. The specific implementation is that: a controlling unit inputs initial positioning data collected by a data collecting unit to a data fusing unit to obtain fused positioning data, where the initial positioning data and the fused positioning data are data in a first coordinate system; the controlling unit obtains target positioning data according to the fused positioning data, where the target positioning data is data in a second coordinate system, and the second coordinate system is a coordinate system obtained by offsetting the first coordinate system; and the controlling unit performs a positioning operation on the target positioning data through at least one positioning unit, to determine a position of a vehicle corresponding to an autonomous driving system.