• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.11-19
• /
• 2024

Multi-agent systems can be utilized in various real-world cooperative environments such as battlefield engagements and unmanned transport vehicles. In the context of battlefield engagements, where dense reward design faces challenges due to limited domain knowledge, it is crucial to consider situations that are learned through explicit sparse rewards. This paper explores the collaborative potential among allied agents in a battlefield scenario. Utilizing the Multi-Robot Warehouse Environment(RWARE) as a sparse reward environment, we define analogous problems and establish evaluation criteria. Constructing a learning environment with the QMIX algorithm from the reinforcement learning library Ray RLlib, we enhance the Agent Network of QMIX and integrate Random Network Distillation(RND). This enables the extraction of patterns and temporal features from partial observations of agents, confirming the potential for improving the acquisition of sparse reward experiences through intrinsic rewards.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.2
• /
• pp.177-186
• /
• 2022

A network QoS model for the joint integrated C4I structure was proposed for the integration of network infrastructure and network operations(NetOps) for NCOE. Detailed QoS requirements process of the joint integrated C4I systems are needs in the Multi-Domain Operation Environment(MDOE). A process is proposed for identifying QoS requirements and establishing in the MDOE using JMT(Joint Mission Thread) reference architecture and solution architecture. Mission analysis identify JCOAs(Joint Critical Operational Activities) and related activities based on JMT & System architecture's OVs, and Information analysis identify QoS attributes using System architecture's SVs. Identifying QoS attributes will be registered at PPS Registry by pre-regulated process, and will be set-up by NetOps. MDOE QoS requirement Process will support efficiently MUM-T and smart defense platform users under the future uncertain battlefield circumstances.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.115-120
• /
• 2022

The Rsussian Armed Forces(RAF) invaded Ukraine on Feburary 24. However, the Armed Forces of Ukraine(AFU) unexpectedly blocked the Russian wave attack made the war between Ukraine and Russia lengthened. Major think-tanks and military experts in the world assessed that the AFU overwhelmed the RAF at the initial stage of the war because of decentralized combats based on mission command. Especially, the decentralized small units of the AFU damaged the RAF and slowed down its Iniative. The 4^th industrial revolution makes the Korean Peninsula the multi-domain battlefield in the future; accordingly, the Decentralized combat won't be a choice, but a necessity in the future. Therefore, the AFU's offensive decentralized combats in this war Suggests many things to the Republic of Korea Army.

• Journal of Internet Computing and Services
• /
• v.16 no.6
• /
• pp.69-78
• /
• 2015

Recently, research on the multi-agent system is developed actively in the various fields, especially on the control of complex system and optimization. In this study, we develop a multi-agent system for NPC simulation in game environment. The purpose of the development is to support quick and precise decision by inferencing the situation of the dynamic discrete domain, and to support an optimization process of the agent system. Our approach employed Petri-net as a basic agent model to simplify structure of the system, and used fuzzy inference engine to support decision making in various situation. Our experimentation describes situation of the virtual battlefield between the NPCs, which are divided two groups, such as fuzzy rule based agent and automata based agent. We calculate the percentage of winning and survival rate from the several simulations, and the result describes that the fuzzy rule based agent showed better performance than the automata based agent.

• Convergence Security Journal
• /
• v.19 no.4
• /
• pp.87-96
• /
• 2019

Recently, with the rapid development of video equipment and technology, tremendous video information is produced and utilized in military domain to acquire battlefield information or for effective command control. Note that the video playback devices currently used in the military domain ranges from low-performance tactical multi-functional terminals (TMFT) to high-performance video servers and the networks where the video information is transmitted also range from the low speed tactical information and communication network (TICN) to ultra-high speed defense broadband converged networks such as M-BcN. Therefore, there is a need for an efficient streaming technique that can efficiently transmit defense video information in heterogeneous communication equipment and network environments. To solve the problem, this paper proposes a Scalable Video Coding (SVC) and balanced selection algorithm based Peer-to-Peer (P2P) streaming technique and the feasibility of the proposed technique is verified by simulations. The simulation results based on our BitTorrent simulator show that the proposed balanced selection scheme outperforms the sequential or rarest selection algorithm.

• Journal of KIISE:Software and Applications
• /
• v.35 no.3
• /
• pp.189-196
• /
• 2008

To build autonomous agents who can make a decision on behalf of humans in time-critical complex environments, the formulation of operational knowledge base could be essential. This paper proposes the methodology of how to formulate the knowledge base and evaluates it in a practical application domain. We analyze threat data received from the multiple sensors of Aircraft Survivability Equipment(ASE) for Korean helicopters, and integrate the threat data into the inductive model through compilation technique which extracts features of the threat data and relations among them. The compiled protocols of state-action rules can be implemented as the brain of the ASE. They can reduce the amounts of reasoning, and endow the autonomous agents with reactivity and flexibility. We report experimental results that demonstrate the distinctive and predictive patterns of threats in simulated battlefield settings, and show the potential of compilation methods for the successful detection of threat systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.291-298
• /
• 2021

In this study, the future of countermobility capability is presented by analyzing the status of the countermobility obstacles focusing on the history of landmines and munitions. The conventional landmine was forbidden globally by the CCW and Ottawa Treaty because it caused civilian damage after the war. Because the inhumanity of those mines had been acknowledged, shatterable mines with a self-destruct (SD) function and M93 "HORNET" anti-tank munition with enhanced sensors have been fielded. In 2016, the Obama administration announced a policy that banned all antipersonnel landmines, leaving a considerable gap in the countermobility capability. To deal with these problems, the developments of "SAVO" and the SLEP program of Volcano mines were conducted. In the sense of a long-term approach, the countermobility obstacles, including mines, were chosen as fundamental forces for Multi-Domain Operations and were improved to Terrain Shaping Obstacles (TSO). TSO has improved sensors and mobility kill capabilities and features an enhanced remote control over each munition on the battlefield through a network established with satellite communication. The combined arms countermobility might be fully capable until 2050 if the TSO program can be completed successfully.