AI Sequence Positioning Using Earth Characteristics Without GNSS
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
GNSS signals are susceptible to jamming and spoofing, and inertial measurement units suffer from position drift over long periods, while magnetic anomaly-based navigation filters can generate erroneous geographic positions due to similar magnetic field strengths across adjacent locations.
Innovation Solution
Utilize a sequence of Earth characteristics, such as magnetic anomalies, gravity, or terrain height, measured by devices like magnetometers and altimeters, and employ an artificial intelligence (AI) to determine the vehicle's spatial position by training a generative AI model on a magnetic anomaly map, transforming data into a geospatial grid, and using a navigation filter for precise location estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single magnetic anomaly measurement is used to determine geographic location, then the navigation process is simple and fast, but the location accuracy deteriorates because magnetic field strength may be substantially the same for two or more adjacent geographic locations
Solution Approach 1:
The patent transitions from using single scalar magnetic anomaly measurements to utilizing sequences of measurements across multiple dimensions (time, space, and measurement values). By analyzing the temporal sequence of magnetic anomaly readings and comparing them against pre-recorded trajectory data, the system creates a multi-dimensional matching problem that resolves the ambiguity of single-point measurements and significantly improves location accuracy.
Solution Approach 2:
The system performs preliminary actions by pre-recording magnetic anomaly trajectories along known paths before actual navigation occurs. These pre-recorded sequences serve as reference data that can be quickly compared against real-time measurements, enabling fast and accurate location determination without requiring complex real-time calculations.
2Reliability
If inertial measurement unit is used to determine geographic position, then navigation can operate independently of GNSS signals, but the position estimate drifts over long periods of time
Solution Approach 1:
The system implements feedback by continuously comparing real-time magnetic anomaly measurements against pre-recorded reference trajectories. This comparison provides corrective information that can be used to update and correct the inertial navigation system's position estimates, preventing drift accumulation while maintaining operational independence from GNSS signals.
Solution Approach 2:
Magnetic anomaly measurements serve as an intermediary between the inertial navigation system and the Earth's reference frame. By measuring magnetic field characteristics and comparing them against known geographic locations, the system provides an external reference that corrects inertial drift without requiring direct GNSS connectivity.
3Measurement precision
If GNSS signals are used to determine geographic position, then location accuracy is high, but the system becomes vulnerable to jamming and spoofing attacks
Solution Approach 1:
The patent converts the naturally occurring magnetic field variations, which create the challenge of ambiguous single-point measurements, into a benefit through sequence analysis. By requiring matching of entire measurement sequences rather than individual points, the system creates a navigation method that is inherently resistant to spoofing while maintaining accuracy, as an attacker would need to replicate entire magnetic trajectories rather than single location signals.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Provides accurate and reliable geographic positioning even in the absence of reliable GNSS signals, mitigating errors from single magnetic measurements and drift, by leveraging AI to analyze sequential Earth characteristics for precise spatial determination.
Implementation Method 1
A magnetometer may be utilized to provide magnetic anomaly values
Implementation Method 2
An altimeter may be utilized to provide terrain height values
Data Source
AI summary
A sequence, of values of a characteristic of the Earth, is received. Each value is obtaind from a measurement, that varies with spatial position with respect to a reference. Using the sequence of values, an estimated spatial position with respect to the reference, is determined, at a time, with an artificial intelligence (AI), e.g., a generative AI (for example, an AI sequence model). The time may be a past or a current time.