cs.AIMar 20, 2026

Architecture of an AI-Based Automated Course of Action Generation System for Military Operations

Authors: Ji-il Park, Inwook Shim, Chong Hui Kim

Organizations: Ministry of National Defense, 22 Itaewon-ro, Yongsan-gu, Seoul, Republic of Korea · Department of Smart Mobility Engineering, Inha University, Incheon, Republic of Korea · Defense AI R&D Institute, Agency for Defense Development (ADD), Daejeon, Republic of Korea

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

The automation system for Course of Action (CoA) planning is an essential element in future warfare. As maneuver speeds increase, surveillance ranges extend, and weapon ranges grow, the operational area expands, making traditional manned-based CoA planning increasingly challenging. Consequently, the development of an AI-based automated CoA planning system is becoming increasingly necessary. Accordingly, several countries and defense organizations are actively developing AI-based CoA planning systems. However, due to security restrictions and limited public disclosure, the technical maturity of such systems remains difficult to assess. Furthermore, as these systems are military-related, their details are not publicly disclosed, making it difficult to accurately assess the current level of development. In response to this, this study aims to introduce relevant doctrines within the scope of publicly available information and present applicable AI technologies for each stage of the CoA planning process. Ultimately, it proposes an architecture for the development of an automated CoA planning system.

Figures & tables

Fig. 1: Overview of the planning phase in the operational execution process [ 30 ] .
Fig. 2: Intelligence Preparation of the Battlefield (IPB) Process and Major Outputs at Each Step [ 31 ] .
Fig. 3: Concept of differential implementation of echelon-specific wargaming models for unit-level course of action development.
Fig. 4: Mission Analysis via LLM-Based Operational Plan Interpretation and Multi-Modal IPB.
Fig. 5: Generation of multiple candidate courses of action using artificial intelligence.
SectionDescription
1. Situationa. Enemy Forces : Enemy disposition, location, capabilities, and activities b. Friendly Forces : Higher headquarters’ mission and intent; status of adjacent and supporting units c. Attachments & Detachments
2. MissionClear mission statement including the 5W (Who, When, Where, What, Why). Example: “The 1st Infantry Battalion seizes Objective XYZ at 0600 on 20 March 2025 in order to prevent enemy advance.”
3. Executiona. Commander’s Intent : End state, key tasks, and success criteria b. Concept of Operations : Operational approach and main phases c. Tasks to Subordinate Units d. Coordination & Control : Required coordination during the operation
4. Sustainmenta. Logistics : Supply (fuel, ammunition, rations) b. Medical Support : Medical unit deployment and evacuation plan c. Transportation : Movement methods and main routes
5. Command & Signala. Command : Command relationships and command post locations b. Signal : Frequencies, passwords, call signs
TABLE I: Example of mission analysis for illustrative purposes.
Fig. 6: AI-Based Wargaming Simulation for Evaluating Multiple Courses of Action Using Quantitative Metrics.
Detailed StepDescriptionResult (Example)
Specified taskConfirmation of the clearly assigned task issued by the higher headquartersSecure Objective Area 00
Operation purposeIdentification of the primary purpose of the operationEnsure maneuver conditions for follow-on forces
Implied taskIdentification of additional tasks determined by the commander to accomplish the specified taskSecure Route 00 to enable seizure of Objective Area 00
ConstraintIdentification of anticipated constraints during the operationRiver flowing from east to west
End-stateDescription of the desired conditions at the conclusion of the operationEnemy neutralized within the operational area
Mission statementSelection of tasks to accomplish the operational purpose–
TABLE II: Example of Mission Analysis for Course of Action (CoA) Development.
Fig. 7: Representative AI Techniques Applicable to Enemy Infiltration Analysis [ 29 ] , Force Identification, and CoA Development.
Fig. 8: Battlespace Evaluation for Defining the Area of Operations (AO) and Area of Interest (AI) [ 32 ] .
Fig. 9: Battlespace Analysis Based on Terrain Analysis [ 32 ] .
Fig. 10: Battlespace Analysis Using Terrain and Weather Information.
Fig. 11: AI-Enabled Enemy Capability Assessment in IPB Step 3 Integrating Doctrinal Patterns and Real-Time Enemy Observations.
Fig. 12: Development of Feasible Enemy CoAs and Comparative Analysis of Strengths and Weaknesses.
Fig. 13: AI-Enabled Multi-Modal IPB and Wargaming Architecture for Updating Enemy and Friendly Courses of Action.
Fig. 14: AI-Driven IPB Workflow Across Steps 1–4 from Battlespace Analysis to Enemy CoA Estimation.
Fig. 15: AI-Driven IPB-Based Decision-Making Framework for Course of Action Development and Execution.
Figure 18
Figure 19
Figure 20

Explore similar work

CardsList

  1. A Proposal for an Agentic AI Architecture to Support Multi-Domain Decision-Making in the Brazilian Armed Forces

    Sep 17, 2026Gioliano de Oliveira Braga, Sidnei Barbieri, Ágney Lopes Roth Ferraz +2Cognitive Architectures for AI AgentsAI-Assisted Decision Making

    Instituto Tecnológico de Aeronáutica (ITA), São José dos Campos/SP - Brasil

  2. Explainable Planning for Hybrid Systems

    Feb 24, 2026Mir Md Sajid SarwarExplainable Artificial Intelligence

    School of Mathematical & Computational Sciences Indian Association for the Cultivation of Science Kolkata, India

  3. Testing and Evaluation of Agentic AI Systems In Military Command and Control

    Aug 20, 2026Ulysse Richard, Heather Frase, Sarah Cao +3AI Agent EvaluationAI Assurance

    Arcadia Impact, AI Governance Taskforce · Veraitech · University of Oxford +3