Multi-Domain COA Planning With Machine Learning Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Multi-domain warfare and complex planning scenarios overwhelm decision-makers, leading to increased time and effort, potentially resulting in asset loss due to ineffective COA-related activities.

Innovation Solution

A machine learning-assisted system that receives situational data from multiple domains, applies user input to generate and adjust suggested courses of action (COAs) using available assets, and presents them in a graphical interface, adhering to military doctrines and incorporating real-time updates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If human operators and analysts conduct COA-related activities manually, then they can exercise judgment and control, but the time and effort required increase significantly

Engineering Contradiction:

Improvehuman judgment and controlVSAvoidtime required for COA activities

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

A machine learning model is introduced as an intermediary between situational data and COA generation. The model processes input data (situational context, objectives, constraints) and produces suggested COAs, reducing the time and effort required from human operators while maintaining strategic judgment through human-in-the-loop review and selection.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If manual COA analysis and vetting is performed, then quality control can be maintained, but the complexity and effort increase

Engineering Contradiction:

ImproveCOA quality controlVSAvoidcomplexity of planning process

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The machine learning model performs self-service by automatically generating, analyzing, and vetting COAs based on trained patterns and doctrines. It independently processes situational data, evaluates multiple options, and produces recommended courses of action, reducing the complexity burden on human operators while maintaining quality through model-based consistency and reproducibility.

Inventive Principle:

Principle #25Self-service

3Speed

If rapid COA generation is implemented, then decision-making speed improves, but the accuracy and effectiveness may decrease

Engineering Contradiction:

Improvedecision-making speedVSAvoidCOA effectiveness

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The system implements feedback mechanisms where suggested COAs are presented to human operators for review, selection, or modification. The model continuously learns from feedback and evolving situational data, refining its COA generation over time. This feedback loop ensures that rapid generation speed does not compromise effectiveness, as the model adapts to maintain accuracy through ongoing validation and learning.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12547932B2Machine learning-assisted multi-domain planning

Publication Date: 2026.02.10 RAYTHEON CO

AI summary

Techniques for machine learning-assisted multi-domain planning are disclosed, including: receiving first situational data from a first domain and second situational data from a second domain; receiving first user input indicating an objective; applying at least the first situational data, the second situational data, and the objective to a machine learning model, to obtain one or more suggested courses of action for satisfying the objective using assets selected from a plurality of assets available in the first domain and the second domain; and presenting the one or more suggested courses of action in a graphical user interface.