GNSS Data Reliability Detection Using Vehicle Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
GNSS data can be unreliable due to signal obstructions or multipath errors, leading to erroneous position or speed reports that can unfairly penalize drivers and affect application performance.
Innovation Solution
Utilize non-GNSS sensors like accelerometers and gyroscopes to generate feature data, which is processed by a classifier such as a support vector machine (SVM) to identify reliable and unreliable GNSS data, filtering out unreliable data during driver assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS data is used for driver assessment, then position and speed information can be obtained, but unreliable data due to signal obstructions or multipath errors can lead to erroneous assessments
Solution Approach 1:
The patent introduces an intermediary validation system that uses non-GNSS sensors (accelerometers, gyroscopes, magnetometers) as mediators to verify GNSS data reliability. These sensors provide alternative measurement channels that help detect and filter out unreliable GNSS readings caused by signal obstructions or multipath errors, thereby protecting the driver assessment from erroneous data while maintaining the ability to use GNSS position and speed information.
2Reliability
If non-GNSS sensors are used to validate GNSS data, then reliability of driver assessment improves, but device complexity increases
Solution Approach 1:
The patent applies multi-functionality by using non-GNSS sensors (accelerometers, gyroscopes, magnetometers) that serve dual purposes: they provide orientation and motion data for driver behavior assessment while simultaneously validating GNSS position and speed measurements. This universal use of sensors reduces the need for additional dedicated validation hardware, thereby improving reliability without proportionally increasing device complexity.
Data Source
AI summary
Techniques for identifying the reliability of global navigation satellite system (GNSS) data include receiving data produced by one or more sensors during a trip within a vehicle, the data including GNSS sensor data and non-GNSS sensor data. Feature data is generated based at least in part on the GNSS sensor data and the non-GNSS sensor data. A reliability of at least a portion of the GNSS sensor data is determined by processing the feature data with a classifier.