Vision-Aided Positioning Convergence Time Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems, particularly in 5G NR, face challenges in reducing convergence time for vision-aided positioning due to inertial measurement unit (IMU) bias calibration and feature tracking, especially during GNSS outages.
Innovation Solution
The proposed solution involves a method where a positioning device receives a list of visual features and their locations from a reference device or map, identifies these features using a camera, and estimates its position based on the identified features, thereby reducing convergence time for vision-aided positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vision-aided positioning starts with IMU bias calibration and feature tracking, then positioning accuracy is improved, but convergence time increases
Solution Approach 1:
The system performs preliminary actions by pre-identifying visual features and their locations before positioning is critically needed. The reference device or map pre-processes and provides a list of visual features with their locations, so that when positioning starts, the feature identification and tracking can begin immediately without delay, thus reducing convergence time while maintaining accuracy
Solution Approach 2:
The patent introduces an intermediary mechanism (visual features embedded in images from reference devices or maps) that bridges the gap between IMU data and final positioning. This intermediary allows the system to correct perception errors and accelerate convergence by providing pre-processed visual reference points that guide the feature tracking process
2Speed
If visual features are identified and processed in real-time, then positioning speed is improved, but measurement precision may deteriorate due to limited processing time
Solution Approach 1:
The reference device or map performs preliminary identification and cataloging of visual features in advance, creating a pre-processed list of features with known locations. This preliminary action enables real-time processing to focus only on matching and tracking these pre-identified features, thus maintaining both speed and precision
3Measurement precision
If more visual features are tracked, then positioning accuracy is improved, but device complexity increases
Solution Approach 1:
The system extracts and isolates only the critical visual features that are most useful for positioning from the complete scene. By taking out and focusing on specific pre-identified features rather than processing all visual elements, the system maintains positioning accuracy while reducing the computational complexity of feature tracking
Data Source
AI summary
Aspects presented herein may enable a UE to improve (e.g., reduce) the convergence time for vision-aided positioning by enabling the UE to use images embedded with location information. In one aspect, a UE receives, from a reference device, a server, or a map, a list of visual features and a location for each visual feature in the list of visual features. The UE identifies at least one visual feature in an area via at least one camera, where the at least one visual feature is included in the list of visual features, where the area is within a threshold distance of the UE. The UE estimates a position of the UE based on the identified at least one visual feature in the area and the location corresponding to the at least one visual feature.