# US 2026/0036102 A1 · Device for Autonomous Rocketry

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

- Number: US 2026/0036102 A1
- Document ID: US20260036102A1
- Status: Published application
- Kind: A1
- Application number: 18/672,666
- Filed: 2024-05-23
- Published: 2026-02-05
- Earliest claimed: 2024-05-23
- Assignees: Brian Haney
- Inventors: Brian Haney
- Web page: https://patentgrep.com/patent/US20260036102A1

## CPC

- F02K 9/805: {servo-mechanisms or control devices therefor}
- B64G 1/242: {Orbits and trajectories}
- B64G 1/244: {Spacecraft control systems}
- F02K 9/52: Injectors
- G05B 13/027: {using neural networks only}
- G05D 1/49: Control of attitude, i.e. control of roll, pitch or yaw
- G05D 1/644: Optimisation of travel parameters, e.g. of energy consumption, journey time or distance
- G05D 2101/10: using artificial intelligence [AI] techniques
- G05D 2109/28: Missiles
- G05D 2109/40: Space vehicles
- F02K: JET-PROPULSION PLANTS (features of jet-propulsion plants common to gas-turbine plants, air intakes or fuel supply control of air-breathing jet-propulsion plants F02C7/00, F02C9/00)
- B64G: COSMONAUTICS; VEHICLES OR EQUIPMENT THEREFOR
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES

## Abstract

Rocket control is a difficult and unpredictable task in environments with inclement weather. As a result, launch missions are often strictly limited based on weather conditions. The present invention provides a device for controlling a rocket to account for environmental uncertainties and maintain optimal mission performance. In embodiments, the device is a radiation hardened field programmable gate array with an embedded artificial intelligence program contained in a graphics processing unit that is used for rocket reaction control by generating thrust vector commands.

## Claims

### Claim 1

A computing device for rocket reaction control, the computing device comprising a simulation trained artificial intelligence computer program, the artificial intelligence computing program being embedded on a radiation hardened processor, the radiation hardened processor further comprising at least one graphics processing unit, the radiation hardened processor further storing an artificial intelligence computer program processing real time sensor data, the artificial intelligence computer program generalizing about the rocket's trajectory environment, the artificial intelligence computer program further comprising at least one deep learning program to optimize commands for reaction control, the commands for reaction control controlling thrust vectors for the rocket, wherein wiring connects the radiation hardened processor to the rocket's thrust vectors further comprising a fuel injector, the fuel injector injecting fuel to one or more engines according to the commands produced by the deep learning computer program, the deep learning computer program further comprising at least on neural network.

### Claim 2 (depends on 1)

The device of claim 1, wherein, a second artificial intelligence computer program optimizes metrics corresponding to distance, time, and impact, informing the command sequences for controlling the thrust vectors for the rocket, maintaining an optimal trajectory course throughout the rocket's flight, from point-to-point, wherein the first point is the launch pad, and the final point is the landing pad.

### Claim 3 (depends on 1)

The device of claim 1, wherein a second software containing a convolutional neural network integrated with a reinforcement learning program is embedded on the radiation hardened processor and optimizes control metrics corresponding to distance, time, and impact.

### Claim 4 (depends on 1)

The device of claim 1, wherein a reinforcement learning agent is embedded in software on the radiation hardened processor and controls thrust vectors to manipulate thrust control and steer the rocket's pitch, attitude, roll, and yaw.

### Claim 5 (depends on 1)

The device of claim 1, wherein the engines receiving fuel injections from the fuel injectors according to commands from thrust vectors, propel the rocket using chemical propellants, generating thrust throughout the rocket's point-to-point trajectory.

### Claim 6 (depends on 1)

The device of claim 1, wherein the engines receiving fuel injections from the fuel injectors according to commands from thrust vectors, propel the rocket using nuclear propulsion, generating thrust throughout the rocket's point-to-point trajectory.

### Claim 7 (depends on 1)

The device of claim 1, wherein the radiation hardened processor, processes data using a graphics processing unit with embedded software performing convolutional operations on real-time sensor data, the embedded software further predicting associations between thrust vector commands and flight path accuracy according to an optimal trajectory, and further signaling the thrust vector commands from launch to landing for optimal performance.

### Claim 8

A computing device for rocket reaction control, the computing device comprising a simulation trained artificial intelligence computer program, the artificial intelligence computing program being embedded on a radiation hardened processor, the radiation hardened processor further comprising one graphic processing unit, the radiation hardened processor further storing the artificial intelligence computer program processing real time sensor data, the artificial intelligence computer program generalizing about the rocket's trajectory environment, the artificial intelligence computer program further comprising one reinforcement learning program to optimize commands for reaction control, the commands for reaction control controlling thrust vectors for the rocket, wherein wiring connects the radiation hardened processor to the rocket's thrust vectors further comprising a fuel injector, the fuel injector injecting fuel to one or more engines according to the commands produced by the reinforcement learning computer program.

### Claim 9 (depends on 8)

The device of claim 8, wherein a second artificial intelligence computer program optimizes metrics corresponding to distance, time, and impact, informing the command sequences for controlling the thrust vectors for the rocket, maintaining an optimal trajectory course throughout the rocket's flight, from point-to-point, wherein the first point is the launch pad, and the final point is the landing pad.

### Claim 10 (depends on 8)

The device of claim 8, wherein a second software containing a convolutional neural network integrated with the reinforcement learning program is embedded on the radiation hardened processor and optimizes control metrics corresponding to distance, time, and impact.

### Claim 11 (depends on 8)

The device of claim 8, wherein a second reinforcement learning agent is embedded in software on the radiation hardened processor and controls thrust vectors to manipulate thrust control and steer the rocket's pitch, attitude, roll, and yaw.

### Claim 12 (depends on 8)

The device of claim 8, wherein the engines receiving fuel injections from the fuel injectors according to commands from thrust vectors, propel the rocket using chemical propellants, generating thrust throughout the rocket's point-to-point trajectory.

### Claim 13 (depends on 8)

The device of claim 8, wherein the engines receiving fuel injections from the fuel injectors according to commands from thrust vectors, propel the rocket using nuclear propulsion, generating thrust throughout the rocket's point-to-point trajectory.

### Claim 14 (depends on 8)

The device of claim 8, wherein the engines receiving fuel injections from the fuel injectors according to commands from thrust vectors, propel the rocket using nuclear propulsion, generating thrust throughout the rocket's extraterrestrial trajectory.

### Claim 15 (depends on 8)

The device of claim 8 wherein, the radiation hardened processor, processes data using a graphics processing unit with embedded software performing convolutional operations on real-time sensor data, the embedded software further predicting associations between thrust vector commands and flight path accuracy according to an optimal trajectory, and further signaling the thrust vector commands from launch to landing for optimal performance.

### Claim 16

A computing device for rocket reaction control, the computing device comprising a simulation trained artificial intelligence computer program, the artificial intelligence computing program being embedded on a radiation hardened processor, the radiation hardened processor further storing the artificial intelligence computer program processing real time sensor data, the artificial intelligence computer program generalizing about the rocket's trajectory environment, the artificial intelligence computer program optimizing commands for reaction control, the commands for reaction control controlling thrust vectors for the rocket to minimize error in reaction control.

### Claim 17 (depends on 16)

The device of claim 16, wherein a second artificial intelligence computer program optimizes metrics corresponding to distance, time, and impact, informing the command sequences for controlling the thrust vectors for the rocket, maintaining an optimal trajectory course throughout the rocket's flight, from point-to-point, wherein the first point is the launch pad, and the final point is the landing pad.

### Claim 18 (depends on 16)

The device of claim 16, wherein a second software containing a convolutional neural network integrated with a reinforcement learning program is embedded on the radiation hardened processor and optimizes control metrics corresponding to distance, time, and impact.

### Claim 19 (depends on 16)

The device of claim 16, wherein a reinforcement learning agent is embedded in software on the radiation hardened processor and controls thrust vectors to manipulate thrust control and steer the rocket's pitch, attitude, roll, and yaw.

### Claim 20 (depends on 16)

The device of claim 16, wherein the engines receiving fuel injections from the fuel injectors according to commands from thrust vectors, propel the rocket using chemical propellants, generating thrust throughout the rocket's point-to-point trajectory.
