# US 2026/0085935 A1 · Apparatus and method for estimating azimuth

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0085935 A1
- Document ID: US20260085935A1
- Status: Published application
- Kind: A1
- Application number: 19/209,709
- Filed: 2025-05-15
- Published: 2026-03-26
- Earliest claimed: 2024-05-15
- Assignees: Hansung University Industry-University Cooperation Foundation
- Applicants: Hansung University Industry-University Cooperation Foundation
- Inventors: Jongtaek Oh
- Web page: https://patentgrep.com/patent/US20260085935A1

## CPC

- G01C 21/1654: {with electromagnetic compass}
- G01C 21/08: involving use of the magnetic field of the earth
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/08: Learning methods
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Provided are an azimuth estimation apparatus and an azimuth estimation method. The azimuth estimation apparatus includes a processor performing a plurality of operations including: acquiring acceleration values, angular velocity values, and geomagnetic values in different directions while the azimuth estimation apparatus rotates at a first location; acquiring a rotation angle value of the azimuth estimation apparatus based on the acceleration values and angular velocity values; acquiring sampled geomagnetic values by sampling the geomagnetic values based on the rotation angle value; estimating an azimuth at the first location based on the sampled geomagnetic values; training a neural network-based azimuth estimation model based on the sampled geomagnetic values and the estimated azimuth; and estimating an azimuth at a second location using the trained azimuth estimation model.

## Claims

### Claim 1

An azimuth estimation apparatus comprising:
a memory storing instructions; and
a processor operably coupled to the memory and configured to execute the instructions,
wherein, when the instructions are executed by the processor, the processor is configured to perform a plurality of operations, the plurality of operations comprising:
acquiring an acceleration value, an angular velocity value, and geomagnetic values in different directions of the azimuth estimation apparatus while the azimuth estimation apparatus rotates at a first location;
obtaining a rotation angle value of the azimuth estimation apparatus based on the acceleration value and the angular velocity value;
acquiring sampled geomagnetic values by sampling the geomagnetic values based on the rotation angle value;
estimating an azimuth at the first location based on the sampled geomagnetic values;
calculating a true azimuth by adding the rotation angle to an initial azimuth of the azimuth estimation apparatus at the first location;
training a neural network-based azimuth estimation model based on the sampled geomagnetic values and the estimated azimuth; and
estimating an azimuth at a second location using the trained azimuth estimation model.

### Claim 2 (depends on 1)

The azimuth estimation apparatus of claim 1, wherein the plurality of operations further comprises obtaining corrected geomagnetic values by correcting the geomagnetic values,
wherein the acquiring sampled geomagnetic values comprises sampling the corrected geomagnetic values at predetermined angle intervals during rotation of the azimuth estimation apparatus based on the rotation angle value to obtain the sampled geomagnetic values.

### Claim 3 (depends on 1)

The azimuth estimation apparatus of claim 1, wherein the plurality of operations further comprises obtaining a data set including geomagnetic values and azimuth values that are shifted by a predetermined angle based on the sampled geomagnetic values, and
wherein the training a neural network-based azimuth estimation model comprises training the neural network-based azimuth estimation model based on the sampled geomagnetic values, the data set, and the azimuth values.

### Claim 4 (depends on 1)

The azimuth estimation apparatus of claim 1, wherein the plurality of operations further comprises measuring an accuracy of the azimuth at the second location based on the trained neural network-based azimuth estimation model.

### Claim 5 (depends on 1)

The azimuth estimation apparatus of claim 1, wherein the different directions include a first direction, a second direction, and a third direction that are perpendicular to each other.

### Claim 6 (depends on 1)

The azimuth estimation apparatus of claim 1, wherein the neural network-based azimuth estimation model is based on at least one of a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, or a long short-term memory (LSTM) model.

### Claim 7 (depends on 1)

The azimuth estimation apparatus of claim 1, wherein the acquiring an acceleration value, an angular velocity value, and geomagnetic values comprises acquiring the acceleration value, angular velocity value, and geomagnetic value of the azimuth estimation apparatus while the azimuth estimation apparatus rotates during movement.

### Claim 8 (depends on 1)

The azimuth estimation apparatus of claim 1, wherein the training a neural network-based azimuth estimation model comprises training the neural network-based azimuth estimation model based on an initialized rotation angle of the azimuth estimation apparatus.

### Claim 9

A method for estimating an azimuth, performed by an azimuth estimation apparatus, comprising:
acquiring an acceleration value, an angular velocity value, and a geomagnetic value for different directions of the azimuth estimation apparatus while the azimuth estimation apparatus rotates at a first location;
acquiring a rotation angle value of the azimuth estimation apparatus based on the acceleration value and the angular velocity value;
acquiring sampled geomagnetic values by sampling the geomagnetic value based on the rotation angle value;
estimating an azimuth at the first location based on the sampled geomagnetic values;
training a neural network-based azimuth estimation model based on the sampled geomagnetic values and the azimuth; and
estimating an azimuth at a second location using the trained neural network-based azimuth estimation model.

### Claim 10 (depends on 9)

The method of claim 9, further comprising acquiring corrected geomagnetic values by correcting the geomagnetic values,
wherein the acquiring sampled geomagnetic values comprises sampling the corrected geomagnetic values at predetermined rotation angle intervals while the azimuth estimation apparatus rotates, based on the rotation angle value.

### Claim 11 (depends on 9)

The method of claim 9, further comprising acquiring a dataset including geomagnetic values and azimuth values that are shifted by a predetermined angle based on the sampled geomagnetic values,
wherein the training a neural network-based azimuth estimation model comprises training the neural network-based azimuth estimation model based on the sampled geomagnetic values, the dataset, and the azimuth.

### Claim 12 (depends on 9)

The method of claim 9, further comprising measuring an accuracy of the azimuth at the second location based on the trained azimuth estimation model

### Claim 13 (depends on 9)

The method of claim 9, wherein the different directions comprise a first direction, a second direction, and a third direction that are orthogonal to each other.

### Claim 14 (depends on 9)

The method of claim 9, wherein the neural network-based azimuth estimation model is based on at least one of a convolutional neural network model, a recurrent neural network model, or an LSTM (long short-term memory) model.

### Claim 15 (depends on 9)

The method of claim 9, wherein the acquiring an acceleration value, angular velocity value, and geomagnetic value comprises acquiring the acceleration value, angular velocity value, and geomagnetic value of the azimuth estimation apparatus while the azimuth estimation apparatus rotates during movement.

### Claim 16 (depends on 9)

The method of claim 9, wherein the training a neural network-based azimuth estimation model comprises training the neural network-based azimuth estimation model based on an initialized rotation angle of the azimuth estimation apparatus.
