AGV 3D Map Association Using Passage-Width Search Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for associating map elements in three-dimensional maps incur a high processing load due to the need to check associations between new and existing map elements, which is inefficient and resource-intensive.
Innovation Solution
An information processing apparatus that selectively associates new map elements with existing map elements within a predetermined distance or passage width, reducing the search range and optimizing position and orientation information using bundle adjustment processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all map elements are checked for association with new map elements, then association accuracy is improved, but processing load increases
Solution Approach 1:
The patent segments the map elements into different types (first map elements representing flat surfaces and second map elements representing other features) and processes them separately. This segmentation allows the system to apply different association strategies to different types of map elements, reducing the overall processing load while maintaining association accuracy for the most important elements.
Solution Approach 2:
The patent applies different quality standards and processing approaches to different types of map elements based on their local characteristics. First map elements (flat surfaces) are given priority in the association process with dedicated processing, while second map elements are handled differently. This local quality approach ensures that critical associations are made accurately without unnecessarily processing all elements with the same level of detail.
2Reliability
If map element association processing checks all possible associations, then completeness of association is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary classification of map elements into first map elements (flat surfaces) and second map elements before the association process. This preliminary action allows the system to prioritize and quickly associate the most important map elements (first type) while handling the remaining elements (second type) with a more efficient, reduced processing approach, thereby reducing overall processing time while maintaining essential association completeness.
Solution Approach 2:
The patent applies partial action by focusing the comprehensive association processing only on first map elements (flat surfaces), which are deemed most critical for navigation and positioning. Second map elements are processed with a more limited association approach. This partial action strategy ensures that the most important associations are made completely and accurately without spending excessive time on all possible associations.
Data Source
AI summary
An information processing apparatus includes a first selection unit configured to select at least one map element from first three-dimensional map information including map elements each including a position and orientation of an image capturing apparatus mounted on a mobile object and three-dimensional positional information in an environment about a feature point included in an image of the environment captured by the image capturing apparatus, a second selection unit configured to select a map element including a feature point with three-dimensional positional information within a predetermined distance from a position indicated by the three-dimensional positional information about a feature point included in the map element selected by the first selection unit from map elements in second three-dimensional map information preliminarily created for the environment, and an association unit configured to associate the map element selected by the first selection unit with the map element selected by the second selection unit.