SLAM Relocalization Error Reduction via Similarity-Based Object Addition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Simultaneous localization and mapping (SLAM) technologies face accuracy issues in relocalization due to multiple similar map elements, leading to errors in estimating the position/posture of moving apparatuses.
Innovation Solution
An information processing device with a detection information acquisition unit, similarity calculation unit, additional object determination unit, and notification unit is employed to identify and notify the positions of additional objects within the sensor's range, ensuring that the similarity between detection information at different positions or orientations is below a predetermined threshold, thereby reducing relocalization errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If relocalization is performed using existing map elements, then self-position/posture estimation can be recovered, but accuracy is lowered when multiple similar map elements exist
Solution Approach 1:
The system performs preliminary analysis of map elements before relocalization by calculating similarity metrics and identifying additional objects in advance. This preprocessing step prepares the system to handle multiple similar map elements by pre-computing similarity values and potential additional objects, so that when relocalization is needed, the most accurate results can be quickly determined without real-time computation delays.
Solution Approach 2:
The patent introduces an intermediary mechanism that acts as a bridge between map elements and relocalization results. This intermediary computes similarity metrics between current sensor data and stored map elements, and uses these similarity calculations to select the most appropriate map element for relocalization, thereby resolving ambiguities when multiple similar elements exist.
2Measurement precision
If additional objects are determined and added to detection range, then similarity between detection information is reduced below threshold, but system complexity increases
Solution Approach 1:
The system applies local quality by determining additional objects specifically in regions where similarity thresholds are exceeded. Rather than uniformly processing the entire detection range, the system identifies local areas with high similarity and focuses computational resources on determining additional objects in those specific regions, thereby reducing overall system complexity while maintaining precision where it matters most.
Solution Approach 2:
The patent changes parameters by dynamically adjusting similarity thresholds and using these parameter changes to control when additional objects are determined. By modifying the similarity threshold parameter based on detection conditions, the system can control the complexity of additional object determination, adding objects only when necessary to reduce similarity below the threshold.
Data Source
AI summary
An information processing device capable of reducing errors when estimating the position/posture of a moving apparatus comprises a detection information acquisition unit configured to acquire detection information detected by a sensor on a moving apparatus, a similarity calculation unit configured to calculate similarities of a plurality of pieces of detection information acquired by the detection information acquisition unit at different positions or different orientations, an additional object determination unit configured to determine positions of additional objects to be added within a detection range of the sensor when the detection information is detected, based on the similarities calculated by the similarity calculation unit, and a notification unit configured to give a notification of the positions of the additional objects determined by the additional object determination unit.