Robot Relocation Using Weighted Boundary Complexity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot relocation methods, which rely on template matching or gradient matching, suffer from high false alarm rates due to the similarity of boundary information in 2D grid maps, particularly in long corridor areas or junctions with multiple walls, leading to inaccurate robot positioning and poor user experience.
Innovation Solution
A relocation method that sets matching weights for black boundaries based on their length and curve complexity, enhancing the impact of small objects and thin areas during relocation, thereby reducing false alarms and improving robustness without increasing hardware costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If template matching or gradient matching is used for robot relocation, then the relocation process can be completed, but the false alarm rate increases due to high similarity of boundary information in 2D grid maps
Solution Approach 1:
The patent applies local quality by differentiating the treatment of different boundary elements in the 2D grid map. Instead of treating all boundaries uniformly, the system identifies and emphasizes small boundaries and thin areas that provide unique localization cues, while reducing the weight of large boundaries that cause false alarms. This selective emphasis on specific local features resolves the contradiction by maintaining relocation capability while reducing false alarm rate.
Solution Approach 2:
The patent changes the parameter of boundary weight assignment in the matching process. By introducing a weight mechanism that adjusts the importance of different boundary elements based on their characteristics (size, shape, complexity), the system transforms the matching process to be less sensitive to similar boundary information. This parameter change enables the system to maintain relocation functionality while significantly reducing false alarm rate.
2Ease of manufacture
If 2D grid maps are used to describe boundary information, then the map construction is simple, but the distinction between large areas and long borders becomes unclear leading to high false alarm rate
Solution Approach 1:
The patent applies local quality by differentiating the treatment of different boundary elements in the 2D grid map. Instead of treating all boundaries uniformly, the system identifies and emphasizes small boundaries and thin areas that provide unique localization cues, while reducing the weight of large boundaries that cause false alarms. This selective emphasis on specific local features resolves the contradiction by maintaining relocation capability while reducing false alarm rate.
Solution Approach 2:
The patent segments the boundary information into different categories based on their characteristics (small boundaries, thin areas, long borders, large areas). By dividing the boundary information into distinct segments and applying different weighting strategies to each segment, the system improves the ability to distinguish between different boundary types while maintaining the simplicity of 2D grid map construction.
3Device complexity
If matching weight is uniformly applied to all boundaries, then the computation is simple, but small objects and thin areas have insufficient impact on relocation accuracy
Solution Approach 1:
The patent changes the parameter of boundary weight assignment in the matching process. By introducing a weight mechanism that adjusts the importance of different boundary elements based on their characteristics (size, shape, complexity), the system transforms the matching process to be less sensitive to similar boundary information. This parameter change enables the system to maintain relocation functionality while significantly reducing false alarm rate.
Solution Approach 2:
The patent applies local quality by differentiating the treatment of different boundary elements in the 2D grid map. Instead of treating all boundaries uniformly, the system identifies and emphasizes small boundaries and thin areas that provide unique localization cues, while reducing the weight of large boundaries that cause false alarms. This selective emphasis on specific local features resolves the contradiction by maintaining relocation capability while reducing false alarm rate.
Data Source
AI summary
A relocation method and a mobile machine using the same are provided. The method includes: obtaining a global map and a current scan map of a target scene where a mobile machine is located, and generating a local sub-map based on the global map; obtaining a black boundary in the local sub-map, determining a length and a curve complexity of the black boundary, and determining a weight of the black boundary based on the length and the curve complexity of the black boundary; determining an estimated pose and a target black boundary based on the local sub-map and the current scan image, and obtaining a matching value between the current scan image and the local sub-map based on a weight of the target black boundary; and determining the estimated pose as a relocated pose of the mobile machine in response to the matching value being larger than a preset threshold.