GPS Error Correction via 3D HD-Map Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
GPS errors in autonomous driving systems can be fatal due to obstacles or weak GPS signals, especially when high-precision data is required, and existing methods rely on expensive equipment like high-precision GPS receivers and stereo cameras.
Innovation Solution
A method for calculating GPS error correction values by comparing three-dimensional HD-maps in duplicate areas using LiDAR and IMU data, without requiring expensive equipment, by confirming duplicate paths, generating three-dimensional HD-maps, and calculating correction values through matrix transformations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive equipment such as high-precision GPS receivers and stereo cameras are used to correct GPS errors, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual three-dimensional map copy of the environment using LiDAR point cloud data. This digital replica serves as a reference to compare against GPS-reported positions, enabling error detection and correction without requiring expensive hardware. The virtual map acts as a substitute for complex correction equipment.
Solution Approach 2:
The patent replaces mechanical/optical correction systems (such as stereo cameras and high-precision GPS receivers) with an information-processing approach using LiDAR data and algorithmic comparison. Instead of using additional sensors to physically measure position more accurately, the system uses computational methods to infer correct positions from environmental features.
2Measurement precision
If multiple high-precision sensors are deployed to achieve accurate positioning, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent makes the LiDAR system multi-functional by using it not only for creating three-dimensional maps but also for GPS error correction. The same LiDAR point cloud data serves dual purposes: environmental representation and positioning verification, eliminating the need for separate correction sensors.
Solution Approach 2:
The system uses its own LiDAR-generated three-dimensional map to correct its GPS errors, making the system self-correcting without external assistance. The vehicle's navigation system validates and corrects its own position data by comparing GPS coordinates against the pre-built virtual map of the environment.
3Measurement precision
If GPS signal strength is increased to improve positioning accuracy, then measurement precision is improved, but reliability deteriorates in areas with obstacles or weak signals
Solution Approach 1:
The patent introduces the three-dimensional virtual map as an intermediary between the GPS receiver and the final position determination. When GPS signals are weak or obstructed, the system uses the virtual map as a reference framework to infer the vehicle's position, effectively mediating the positioning process and reducing direct dependence on GPS signal strength.
Solution Approach 2:
The system prepares a detailed three-dimensional virtual map in advance before GPS errors occur. This pre-built environmental model serves as a cushion or backup that protects against GPS failures in obstructed areas. When GPS signals become unreliable, the pre-prepared virtual map is already available to provide position correction without requiring additional real-time measurements.
Data Source
AI summary
Proposed is a GPS error correction method performed through comparison of three-dimensional HD-maps in a duplicate area, and more particularly, a method that can calculate a correction value for a GPS error by comparing three-dimensional HD-maps of a corresponding duplicate area when the duplicate area is generated on a GPS route in the process of acquiring raw data to be used in a HD-map for autonomous driving. Particularly, in the method, an accurate correction value for the GPS error can be calculated by comparing three-dimensional point cloud data acquired by utilizing basically installed LiDAR, an Inertial Measurement Unit (IMU) and the like, without using expensive equipment such as a plurality of high-precision GPS receivers, stereo cameras or the like.