VIO Position Window Extension for GNSS Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Global Navigation Satellite Systems (GNSS) based positioning is inaccurate in urban environments due to sky obstructions, leading to positioning errors of up to 50 meters, which is detrimental for advanced vehicle automation and navigation systems.
Innovation Solution
The method involves combining Visual-Inertial Odometry (VIO) position values from previous and current time periods to ensure consistent output positions, which are then adjusted and fused with GNSS measurements for accurate position determination of mobile devices, such as vehicles, in urban canyon scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS-based positioning is used in urban environments, then positioning data can be obtained, but positioning accuracy deteriorates due to sky obstructions causing errors up to 50 meters
Solution Approach 1:
The patent combines GNSS positioning data with VIO (Visual-Inertial Odometry) data to create a fused positioning system. When GNSS accuracy degrades in urban canyons, the system integrates alternative data sources (visual odometry and inertial measurements) to maintain positioning accuracy, directly addressing the contradiction between obtaining positioning data and maintaining accuracy under sky obstruction.
Solution Approach 2:
The system dynamically adjusts the weighting and fusion parameters of different positioning sources based on environmental conditions. When sky obstruction is detected (degrading GNSS accuracy), the system changes parameters to rely more heavily on VIO data, thereby maintaining positioning accuracy despite the harmful effect of sky obstruction.
2Measurement precision
If VIO position values from multiple time periods are combined, then positioning accuracy is improved, but computational complexity increases
Solution Approach 1:
The system pre-processes and stores VIO position values from multiple time periods in an organized manner before fusion is needed. By preparing the data structure in advance and establishing predefined fusion algorithms, the system reduces the computational complexity during real-time operation while still achieving improved positioning accuracy through multi-temporal data integration.
Data Source
AI summary
Techniques provided herein are directed toward virtually extending an updated set of output positions of a mobile device determined by a VIO by combining a current set of VIO output positions with one or more previous sets of VIO output positions in such a way that ensure all outputs positions among the various combined sets of output positions are consistent. The combined sets can be used for accurate position determination of the mobile device. Moreover, the position determination further may be based on GNSS measurements.