2D Map Localization Using Ground Plane Image Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing localization techniques for autonomous and semi-autonomous machines face inaccuracies and inefficiencies due to the use of 3D map data limitations, regulatory constraints, and errors in triangulating feature poses over time, especially when only 2D map data is available.
Innovation Solution
A method for localization using 2D map data that determines predicted image locations based on ground plane projections and comparisons, eliminating the need for triangulation, thereby enhancing accuracy and reducing data requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If 3D map data is used for localization, then localization accuracy is improved, but data availability and processing feasibility deteriorate due to regulatory constraints and system limitations
Solution Approach 1:
The patent creates a 2D representation (copy) of the 3D environment by projecting ground plane locations onto a 2D map. This 2D map serves as a simplified copy that preserves essential localization information without requiring full 3D data, thereby satisfying regulatory constraints while maintaining localization capability
Solution Approach 2:
The patent extracts only the ground plane information from 3D environmental data and represents it in 2D space. By taking out only the necessary ground plane locations and projecting them onto a 2D map, the system eliminates unnecessary 3D data while preserving the essential information needed for accurate localization
2Measurement precision
If 3D map data is used for localization, then localization accuracy is improved, but processing complexity and system resource requirements increase
Solution Approach 1:
The patent extracts only ground plane information from complex 3D environmental data and represents it in simplified 2D space. This extraction reduces processing complexity by eliminating unnecessary 3D computations while maintaining localization accuracy through the preserved ground plane relationships
Solution Approach 2:
The patent transforms 3D ground plane locations into a 2D representation by projecting them onto a 2D map. This dimensional reduction simplifies processing requirements while preserving the essential spatial relationships needed for accurate localization, making the system more computationally efficient
3Ease of operation
If traditional localization techniques using multiple cameras and timestamps are used, then localization capability is achieved, but error propagation over time increases leading to inaccurate results
Solution Approach 1:
The patent performs preliminary action by pre-processing environmental data to create a 2D map with projected ground plane locations before localization occurs. This pre-computed 2D representation eliminates the need for continuous triangulation over time, preventing error propagation while maintaining localization capability
Solution Approach 2:
The patent creates a static 2D copy of the environment with ground plane projections that serves as a reference for localization. This static reference eliminates the need for dynamic triangulation over multiple timestamps, thereby preventing error accumulation and improving reliability over time
Data Source
AI summary
Embodiments of the present disclosure relate to a system and method used to localize one or more systems using 2D map data. The method may include determining an image location of a representation of a portion of an object in an image corresponding to an environment. In some embodiments, the method may additionally include determining one or more predicted image locations corresponding to the image location of the representation of the portion of the object. The method may additionally include comparing one or more ground plane locations of the portion of the object with the one or more predicted image locations, and determining a cost based at least on the comparison between the one or more ground plane locations and the one or more predicted image locations. Further, the method may include localizing a system to the 2D map data based on the determined cost.