# US 2021/0334687 A1 · Autonomous correction of course of action

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

- Number: US 2021/0334687 A1
- Document ID: US20210334687A1
- Status: Published application
- Kind: A1
- Application number: 16/856,501
- Filed: 2020-04-23
- Published: 2021-10-28
- Earliest claimed: 2020-04-23
- Assignees: Raytheon Company
- Applicants: Raytheon Company
- Inventors: Paul C. Hershey; Michael P. Sica; Danielle J. Marchione; Marilyn W. Zett
- Web page: https://patentgrep.com/patent/US20210334687A1

## CPC

- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/24323: {Tree-organised classifiers}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 7/08: using chaos models or non-linear system models
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Discussed herein are devices, systems, and methods for autonomous, dynamic course of action (COA) generation and management. A method can include issuing a communication to one or more assets indicating operations of a first COA to be performed, receiving, by an intelligence, surveillance, and reconnaissance (ISR) device, data indicating an unexpected event, not accounted for in the first COA, has occurred, in response to the data indicating the unexpected event, identifying a second COA or a portion of a second COA that satisfies a mission of the first COA and accounts for the unexpected event, and issuing a second communication to the one or more assets indicating one or more operations of the second COA to be performed.

## Claims

### Claim 1

A computer-implemented method for autonomous, dynamic course of action (COA) generation and management, the method comprising:
issuing a communication to one or more assets indicating operations of a first COA to be performed;
receiving, by an intelligence, surveillance, and reconnaissance (ISR) device, data indicating an unexpected event, not accounted for in the first COA, has occurred;
in response to the data indicating the unexpected event, identifying a second COA or a portion of a second COA that satisfies a mission of the first COA and accounts for the unexpected event; and
issuing a second communication to the one or more assets indicating one or more operations of the second COA to be performed.

### Claim 2 (depends on 1)

The method of claim 1, wherein the data indicating the unexpected event is received while the first COA is being performed, the method further comprising:
generating or receiving a first COA tree and a second COA tree, each tree including operations of assets as nodes and edges between nodes representing relationships between operations of assets.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating the first and second COA trees includes using a Markov Decision Process (MDP) for COA assessment.

### Claim 4 (depends on 2)

The method of claim 2, further comprising determining a probability of success and confidence interval for each operation of the operations and associating the probability of success with an associated branch of the COA tree.

### Claim 5 (depends on 4)

The method of claim 4, wherein determining the probability of success includes using a stochastic mathematical model of the operation.

### Claim 6 (depends on 5)

The method of claim 5, wherein determining the probability of success and confidence interval includes determining a mean and standard deviation of a statistical distribution representing the COA operations.

### Claim 7 (depends on 6)

The method of claim 6, further comprising propagating the probability of success and confidence interval across COA operations of the first and second COAs by determining mathematical combinations of respective means and standard deviations of respective branches of the first and second COA trees.

### Claim 8 (depends on 4)

The method of claim 4, further comprising:
comparing the probability of success and confidence interval of operations of the first COA to a threshold probability of success and confidence interval and altering the first COA in response to determining the probability of success and confidence interval are below the threshold probability of success and confidence interval.

### Claim 9 (depends on 1)

The method of claim 1, wherein the unexpected event includes attrition of an asset of the assets or arrival of a new adversary asset.

### Claim 10

A non-transitory machine-readable medium including instructions that, when executed by a machine, cause the machine to perform operations for autonomous, dynamic course of action (COA) generation and management, the operations comprising:
issuing a communication to one or more assets indicating operations of a first COA to be performed;
receiving, by an intelligence, surveillance, and reconnaissance (ISR) device, data indicating an unexpected event, not accounted for in the first COA, has occurred;
in response to the data indicating the unexpected event, identifying a second COA or a portion of a second COA that satisfies a mission of the first COA and accounts for the unexpected event; and
issuing a second communication to the one or more assets indicating one or more operations of the second COA to be performed.

### Claim 11 (depends on 10)

The non-transitory machine-readable medium of claim 10, wherein the data indicating the unexpected event is received while the first COA is being performed, and the operations further comprise:
generating or receiving a first COA tree and a second COA tree, each tree including operations of assets as nodes and edges between nodes representing relationships between operations of assets.

### Claim 12 (depends on 11)

The non-transitory machine-readable medium of claim 11, wherein generating the first and second COA trees includes using a Markov Decision Process (MDP) for COA assessment.

### Claim 13 (depends on 11)

The non-transitory machine-readable medium of claim 11, wherein the operations further comprise determining a probability of success and confidence interval for each operation of the operations and associating the probability of success with an associated branch of the COA tree.

### Claim 14 (depends on 13)

The non-transitory machine-readable medium of claim 13, wherein determining the probability of success includes using a stochastic mathematical model of the operation.

### Claim 15 (depends on 14)

The non-transitory machine-readable medium of claim 14, wherein determining the probability of success and confidence interval includes determining a mean and standard deviation of a statistical distribution representing the COA operations.

### Claim 16 (depends on 15)

The non-transitory machine-readable medium of claim 15, wherein the operations further comprise propagating the probability of success and confidence interval across COA operations of the first and second COAs by determining mathematical combinations of respective means and standard deviations of respective branches of the first and second COA trees.

### Claim 17

A device configured for autonomous, dynamic course of action (COA) generation and management, the device comprising:
a memory including data of a first COA tree representing operations of a first COA stored thereon;
processing circuitry coupled to the memory, the processing circuitry configured to:
issue a communication to one or more assets indicating operations of the first COA to be performed;
receiving, by an intelligence, surveillance, and reconnaissance (ISR) device, data indicating an unexpected event, not accounted for in the first COA, has occurred;
in response to the data indicating the unexpected event, identify or generating a second COA tree or a portion of a second COA tree representing operations of a second COA that satisfy a mission of the first COA and accounts for the unexpected event; and
issue a second communication to the one or more assets indicating one or more operations of the second COA to be performed.

### Claim 18 (depends on 17)

The device of claim 17, wherein the data indicating the unexpected event is received while the first COA is being performed, and the processing circuitry is further configured to generate or receive a first COA tree and a second COA tree, each tree including operations of assets as nodes and edges between nodes representing relationships between operations of assets.

### Claim 19 (depends on 18)

The device of claim 18, wherein the processing circuitry is further configured to determine a probability of success and confidence interval, using a stochastic mathematical model, for each operation of the operations and associate the probability of success with an associated branch of the COA tree.

### Claim 20 (depends on 19)

The device of claim 19, wherein determining the probability of success and confidence interval includes determining a mean and standard deviation of a statistical distribution representing the COA operations and the processing circuitry is further configured to propagate the probability of success and confidence interval across COA operations of the first and second COAs by determining mathematical combinations of respective means and standard deviations of respective branches of the first and second COA trees.
