# US 2026/0098980 A1 · Method, system, and medium for processing satellite orbital information using a generative adversarial network

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

- Number: US 2026/0098980 A1
- Document ID: US20260098980A1
- Status: Published application
- Kind: A1
- Application number: 19/265,606
- Filed: 2025-07-10
- Published: 2026-04-09
- Earliest claimed: 2018-11-23
- Assignees: Slingshot Aerospace, Inc.
- Applicants: Slingshot Aerospace, Inc.
- Inventors: David Stuart Godwin, IV; Spencer Ryan Romo; Carrie Inez Hernandez; Thomas Scott Ashman; Melanie Stricklan; Luke Wendling
- Web page: https://patentgrep.com/patent/US20260098980A1

## CPC

- G01V 3/38: Processing data, e.g. for analysis, for interpretation, for correction
- G01V 3/16: specially adapted for use from aircraft (G01V3/165 - G01V3/175 take precedence)
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N 3/09: Supervised learning
- G06N 3/094: Adversarial learning
- G06N 3/096: Transfer learning
- G06N 3/098: Distributed learning, e.g. federated learning
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Method, electronic device, system, and computer-readable medium embodiments are disclosed. Some embodiments include a signal processing workflow incorporating a graphical user interface for displaying orbital information for satellites and other spacecraft. In some embodiments, a generative adversarial network (GAN) is employed for evaluating satellite orbital positions, for predicting future orbital movements, for detecting orbital maneuvers of a satellite, and for analyzing such maneuvers for potential nefarious intent.

## Claims

### Claim at position 1

1-15. (canceled)

### Claim 16

A system comprising:
one or more sensors configured to detect data comprising real orbital position observations of a satellite;
a transceiver communicatively coupled to the one or more sensors, wherein the transceiver is configured to:
(i) receive, from the one or more sensors, the data or data packets of the data from the one or more sensors, and
(ii) transmit the data or the data packets of the data for use in computing satellite orbital information from the real orbital position observations; and
a computing device communicatively coupled to the transceiver, wherein the computing device is configured to:
(i) receive, from the transceiver, the data or the data packets of the data, and
(ii) generate, using a trained machine learning (ML) model, a prediction of a future orbital track for the satellite based at least in part on analyzing the data or the data packets of the data, wherein the trained ML model is obtained based at least in part by applying a loss function to orbital position predictions corresponding to a fake orbit.

### Claim 17 (depends on 16)

The system of claim 16, wherein the computing device is further configured to use the future orbital track to determine a potential nefarious intent of the satellite.

### Claim 18 (depends on 16)

The system of claim 16, wherein the one or more sensors are mounted on one or both of an aerial vehicle or a second satellite.

### Claim 19 (depends on 18)

The system of claim 18, wherein the one or more sensors are configured to detect the data using one or more of radio detection and ranging (RADAR), light imaging detection and ranging (LIDAR), or hyperspectral sensing.

### Claim 20 (depends on 16)

The system of claim 16, wherein the transceiver comprises a radio frequency (RF) transceiver or a communication interface.

### Claim 21 (depends on 16)

The system of claim 16, wherein the one or more sensors comprise one or more of: an imaging sensor, a telecommunications sensor, or a navigational sensor.

### Claim 22 (depends on 16)

The system of claim 16, wherein the computing device is further configured to display the prediction of the future orbital track for the satellite on a graphical user interface (GUI).

### Claim 23 (depends on 22)

The system of claim 22, wherein the GUI is configured to allow a user of the GUI to receive a real-time prediction of the future orbital track.

### Claim 24 (depends on 22)

The system of claim 22, wherein the computing device is further configured to generate a desired maneuver and display the desired maneuver on the GUI.

### Claim 25 (depends on 16)

The system of claim 16, wherein the trained ML model generates the prediction of the future orbital track using backpropagating based at least in part on the orbital position predictions corresponding to the fake orbit.

### Claim 26 (depends on 16)

The system of claim 16, wherein the trained ML model comprises a neural network.

### Claim 27 (depends on 25)

The system of claim 25, wherein the trained ML model comprises one or both of a generator or a discriminator.

### Claim 28

A method comprising:
(a) detecting, via one or more sensors, data comprising real orbital position observations of a satellite;
(b) receiving, using a transceiver communicatively coupled to the one or more sensors, the data or data packets of the data;
(c) transmitting, using the transceiver, the data or the data packets of the data for use in computing, by a computing device, satellite orbital information from the real orbital position observations;
(d) receiving, from the transceiver, the data or the data packets of the data corresponding to the satellite orbital information at the computing device; and
(e) generating, using the computing device comprising a trained machine learning (ML) model, a prediction of a future orbital track for the satellite based at least in part on analyzing the data or the data packets of the data, wherein the trained ML model is obtained based at least in part by applying a loss function to orbital position predictions corresponding to a fake orbit.

### Claim 29 (depends on 28)

The method of claim 28, further comprising displaying the prediction of the future orbital track for the satellite on a graphical user interface (GUI) of the computing device.

### Claim 30 (depends on 29)

The method of claim 29, wherein displaying the prediction of the future orbital track for the satellite on a graphical user interface (GUI) of the computing device enables a user of the GUI to receive a real-time prediction of the future orbital track.

### Claim 31 (depends on 28)

The method of claim 28, further comprising using the future orbital track to determine a potential nefarious intent of the satellite.

### Claim 32 (depends on 28)

The method of claim 28, wherein the one or more sensors are mounted on one or both of an aerial vehicle or a second satellite.

### Claim 33 (depends on 28)

The method of claim 28, wherein the one or more sensors comprise one or more of: an imaging sensor, a telecommunications sensor, or a navigational sensor.

### Claim 34 (depends on 28)

The method of claim 28, wherein generating the prediction of the future orbital track further comprises backpropagating based at least in part on the orbital position predictions corresponding to the fake orbit.

### Claim 35 (depends on 28)

The method of claim 28, further comprising generating a desired maneuver based at least in part on the prediction of the future orbital track for the satellite.
