# US 2025/0164648 A1 · Machine learning assisted satellite based positioning

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

- Number: US 2025/0164648 A1
- Document ID: US20250164648A1
- Status: Published application
- Kind: A1
- Application number: 18/661,556
- Filed: 2024-05-10
- Published: 2025-05-22
- Earliest claimed: 2018-08-09
- Assignees: Apple Inc.
- Applicants: Apple Inc.
- Inventors: Benjamin A. WERNER; Brent M. LEDVINA; Dennis P. HILGENBERG; Aarti SATHYANARAYANA
- Web page: https://patentgrep.com/patent/US20250164648A1

## CPC

- G01S 19/40: Correcting position, velocity or attitude
- G01S 19/428: {using multipath or indirect path propagation signals in position determination}
- G01S 19/07: providing data for correcting measured positioning data, e.g. DGPS [differential GPS] or ionosphere corrections
- G01S 19/393: {Trajectory determination or predictive tracking, e.g. Kalman filtering}
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A device implementing a system for estimating device location includes at least one processor configured to receive an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite, and receive a set of parameters associated with the estimated position. The processor is further configured to apply the set of parameters and the estimated position to a machine learning model, the machine learning model having been trained based at least on a position of a receiving device relative to the GNSS satellite. The processor is further configured to provide the estimated position and an output of the machine learning model to a Kalman filter, and provide an estimated device location based on an output of the Kalman filter.

## Claims

### Claim at position 1

1-12. (canceled)

### Claim 13

A device, comprising:
at least one processor; and
a memory including instructions that, when executed by the at least one processor, cause the at least one processor to:
receive an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite;
receive a set of parameters associated with the estimated position;
apply the set of parameters and the estimated position to a machine learning model;
provide an estimated device location based at least in part on the estimated position and an output of the machine learning model.

### Claim 14 (depends on 13)

The device of claim 13, the machine learning model further having been trained based on an estimated position of a receiving device provided by the positioning system, and based on a reference position of the receiving device provided by a reference positioning system.

### Claim 15 (depends on 13)

The device of claim 13, wherein the machine learning model is stored in the memory of the device.

### Claim 16 (depends on 13)

The device of claim 13, wherein the output from the machine learning model indicates an amount of uncertainty for the estimated position.

### Claim 17 (depends on 13)

The device of claim 13, wherein the output from the machine learning model indicates a revised measurement for the estimated position.

### Claim 18 (depends on 13)

The device of claim 13, wherein the output from the machine learning model indicates an order to use the estimated position in a Kalman filter, relative to other measurements used in the Kalman filter.

### Claim 19 (depends on 13)

The device of claim 13, wherein the output from the machine learning model indicates whether a Kalman filter is to disregard measurements from the GNSS satellite.

### Claim at position 9

20-22. (canceled)

### Claim 23

A computer program product comprising instructions that, when executed by one or more processors, causes the one or more processors to perform operations comprising:
receiving an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite;
receiving a set of parameters associated with the estimated position;
applying the set of parameters and the estimated position to a machine learning model; and
providing an estimated device location based at least in part on the estimated position and an output of the machine learning model.

### Claim 24 (depends on 23)

The computer program product of claim 23, the machine learning model further having been trained based on an estimated position of a receiving device provided by the positioning system, and based on a reference position of the receiving device provided by a reference positioning system.

### Claim 25 (depends on 23)

The computer program product of claim 23, wherein the machine learning model is stored in a memory of the device.

### Claim 26 (depends on 23)

The computer program product of claim 23, wherein the output from the machine learning model indicates an amount of uncertainty for the estimated position.

### Claim 27 (depends on 23)

The computer program product of claim 23, wherein the output from the machine learning model indicates a revised measurement for the estimated position.

### Claim 28 (depends on 23)

The computer program product of claim 23, wherein the output from the machine learning model indicates an order to use the estimated position in a Kalman filter, relative to other measurements used in the Kalman filter.

### Claim 29 (depends on 23)

The computer program product of claim 23, wherein the output from the machine learning model indicates whether a Kalman filter is to disregard measurements from the GNSS satellite.

### Claim 30

A method comprising:
receiving an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite;
receiving a set of parameters associated with the estimated position;
applying the set of parameters and the estimated position to a machine learning model; and
providing an estimated device location based at least in part on the estimated position and an output of the machine learning model.

### Claim 31 (depends on 30)

The method of claim 30, the machine learning model further having been trained based on an estimated position of a receiving device provided by the positioning system, and based on a reference position of the receiving device provided by a reference positioning system.

### Claim 32 (depends on 30)

The method of claim 30, wherein the machine learning model is stored in a memory of the device.

### Claim 33 (depends on 30)

The method of claim 30, wherein the output from the machine learning model indicates an amount of uncertainty for the estimated position.

### Claim 34 (depends on 30)

The method of claim 30, wherein the output from the machine learning model indicates a revised measurement for the estimated position.

### Claim 35 (depends on 30)

The method of claim 30, wherein the output from the machine learning model indicates an order to use the estimated position in a Kalman filter, relative to other measurements used in the Kalman filter.
