SLAM Map Error Recognition via Data Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional SLAM methods for mobile devices often produce erroneous maps when merging two maps, leading to incorrect pose determination and rendering navigation systems useless, as similar environmental features can be confused, causing perceptual aliasing and incorrect merges.
Innovation Solution
A method to recognize and rectify erroneous maps by comparing data sets from different acquisition periods, using a degree of matching criterion to identify contradictions and mismatches, and adjusting the SLAM graph by removing incorrect nodes and edges, allowing for early and uncertain merges with the possibility of reversing errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If maps are merged to expand coverage and improve navigation accuracy, then map completeness is improved, but map accuracy deteriorates due to perceptual aliasing and incorrect merges
Solution Approach 1:
The system continuously compares current map data with historical map data and provides feedback to detect contradictions and mismatches. When perceptual aliasing is detected, the system automatically adjusts the SLAM graph by removing incorrect nodes and edges, thereby maintaining map accuracy while enabling continuous map merging and expansion.
Solution Approach 2:
Before merging maps, the system performs preliminary comparison of environmental features and detects potential conflicts in advance. By identifying contradictions beforehand, the system can prevent incorrect merges and maintain accuracy while still achieving comprehensive coverage through controlled merging operations.
2Manufacturing precision
If SLAM graph is adjusted to correct errors, then map accuracy is improved, but processing time and computational complexity increase
Solution Approach 1:
The system segments the SLAM graph into discrete nodes and edges representing specific environmental features. This segmentation allows targeted correction of only the erroneous portions (individual nodes or edges) rather than recalculating the entire map, thereby reducing processing time while maintaining accuracy.
Solution Approach 2:
When errors are detected, the system discards the incorrect portions of the SLAM graph (erroneous nodes and edges) and recovers the correct information by comparing with historical data. This selective approach avoids reprocessing the entire graph, reducing computational overhead while ensuring accuracy.
Data Source
AI summary
A method for recognizing an erroneous map of an environment. The map being obtained by merging a first map and a second map which are based on a SLAM graph and on data sets with information about the environment. The method includes: providing an updated second map obtained by merging the first map and the second map and updated after the merge; determining whether the updated second map is erroneous, including: performing a comparison of first map data of the first map from the first acquisition period to second map data from the second acquisition period, determining a degree of matching between the second map data and the first map data, determining that the updated second map is erroneous if the degree of matching fulfills a specified criterion; and providing, if it has been determined that the updated second map is erroneous, information that the map is erroneous.