Volumetric Grid Localization Geometry for Pathway Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current GPS systems, even with enhanced accuracy techniques like WAAS and INS, struggle to provide high-definition mapping and navigation with sufficient positional accuracy, particularly in applications requiring precise localization of objects within a three-dimensional environment.
Innovation Solution
The method involves generating a localization geometry by processing point cloud data from distance sensors, reducing it to a predetermined volume, projecting it to a two-dimensional plane, defining a volumetric grid, determining voxel occupancy, and transforming it into a geodetic coordinate system to create an occupancy grid that represents the vicinity of a roadway.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS with enhanced accuracy techniques (WAAS, DGPS, INS) is used, then positional accuracy is improved, but it still cannot provide sufficient accuracy for high-definition mapping and navigation applications
Solution Approach 1:
The patent segments the environment into discrete volumetric units (voxels) organized in a grid structure. This segmentation transforms continuous spatial data into discrete, manageable units that can be efficiently processed and matched, enabling high-definition mapping with accuracy beyond GPS capabilities by creating a detailed occupancy grid representation of the environment
Solution Approach 2:
The patent transitions from two-dimensional map matching to three-dimensional volumetric grid matching. By adding the vertical dimension and creating volumetric voxels, the system achieves higher localization accuracy in 3D space, enabling precise positioning for applications like autonomous vehicles that require understanding of the vertical environment structure
2Measurement precision
If point cloud data is processed in full three-dimensional detail for localization, then measurement precision is improved, but computing and networking resources required increase significantly
Solution Approach 1:
The patent applies partial action by selectively processing only relevant portions of the three-dimensional space. Instead of fully processing all point cloud data, the system focuses on creating occupancy grids for specific volumetric regions of interest, reducing computational load while maintaining localization precision by processing only the necessary spatial segments
Solution Approach 2:
The patent changes the parameter representation from dense continuous point cloud coordinates to discrete volumetric grid occupancy values. This parameter transformation reduces data complexity and size, enabling efficient processing and transmission of localization data while maintaining the precision needed for high-definition mapping applications
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments include apparatus and methods for generating a localization geometry or occupancy grid for a geographic location. Point cloud that describes a vicinity of a pathway is collected by a distance sensor and describing a vicinity of the pathway. The point cloud data is reduced or filtered to a predetermined volume with respect to the roadway. The remaining point cloud data is projected onto a two-dimensional plane including at least one pixel formation. A volumetric grid is defined according to the at least one pixel formation, and a voxel occupancy for each of a voxels forming the volumetric grid is determined. The arrangement of the voxel occupancies or a sequence of data describing the voxel occupancies is a localization geometry that describes the geographic location of the pathway.