Location Error Detection Using GNSS and VIO Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Augmented reality applications face challenges in accurately tracking device pose due to inaccurate GNSS measurements, especially in environments with tall buildings or other structures that reflect or block satellite signals, leading to multipath interference and degraded GNSS accuracy.
Innovation Solution
A system that compares sensor location measurements, such as GNSS, to visual inertial odometry (VIO) measurements to identify inaccuracies, and filters out inaccurate satellite signals, using a combination of sensor and VIO data to enhance localization accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS measurements are used for device localization, then absolute location can be provided, but measurement accuracy deteriorates in environments with tall buildings or structures that reflect or block satellite signals
Solution Approach 1:
The patent introduces VIO measurements as an intermediary reference system to detect and correct inaccurate GNSS measurements. The VIO system provides a complementary localization method that can identify when GNSS measurements are degraded by environmental factors like multipath interference from buildings, allowing the system to switch to or correct with VIO-based location estimates.
2Measurement precision
If VIO measurements are used for device localization, then relative location accuracy can be maintained, but absolute location capability is lost
Solution Approach 1:
The patent merges GNSS and VIO measurement systems into a hybrid localization approach. The system combines the absolute location capability of GNSS with the relative location accuracy of VIO by comparing both measurement types and using them complementarily - GNSS provides absolute positioning when available and accurate, while VIO provides reliable relative movement tracking and can correct GNSS inaccuracies.
3Reliability
If sensor location measurements are compared to VIO measurements to identify inaccuracies, then measurement reliability improves, but system complexity increases
Solution Approach 1:
The patent implements a feedback mechanism where VIO measurements are continuously compared with GNSS measurements to detect and correct inaccuracies. The system uses the discrepancy between the two measurement systems as feedback to identify when GNSS measurements are unreliable, allowing dynamic adjustment of which measurement source to trust and thereby improving overall reliability through continuous monitoring and correction.
Data Source
AI summary
A system determines an accuracy of a set containing a plurality of sensor location measurements of a client device and generating a set of sensor location measurements labeled with an associated accuracy estimate, is presented. The system receives a plurality of sensor location measurements of the client device generated by a location sensor. The system may determine the accuracy of a sensor location measurement by comparing the sensor location measurement to a reference location measurement, such as VIO location measurements computed using VIO data. The system computes a first set of location translations for the set of sensor location measurements and a second set of location translations for the set of VIO location measurements. The system may calculate a measurement difference between each corresponding pair of location translations from the first and second set, identify measurement differences that exceed a threshold, and label the corresponding sensor location measurement as inaccurate.