• Journal of Internet of Things and Convergence
• /
• v.7 no.4
• /
• pp.29-34
• /
• 2021

In order to apply reinforcement learning to a robot in a real environment, it is necessary to use simulation in a virtual environment because numerous iterative learning is required. In addition, it is difficult to apply a learning algorithm that requires a lot of computation for a robot with low-spec. hardware. In this study, ML-Agent, a reinforcement learning frame provided by Unity, was used as a virtual simulation environment to apply reinforcement learning to the obstacle collision avoidance problem of mobile robots with low-spec hardware. A DQN supported by ML-Agent is adopted as a reinforcement learning algorithm and the results for a real robot show that the number of collisions occurred less then 2 times per minute.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.39-46
• /
• 2020

The utilization of artificial intelligence (AI) in the engagement has been a key research topic in the defense field during the last decade. To pursue this utilization, it is imperative to acquire a realistic simulation to train an AI engagement agent with a synthetic, but realistic field. This paper is a case study of training an AI agent to operate with a hardware realism in the air-warfare dog-fighting. Particularly, this paper models the pursuit of an opponent in the dog-fighting setting with a gun-only engagement. In this context, the AI agent requires to make a decision on the pursuit style and intensity. We developed a realistic hardware simulator and trained the agent with a reinforcement learning. Our training shows a success resulting in a lead pursuit with a decreased engagement time and a high reward.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2007.11a
• /
• pp.397-407
• /
• 2007

In this paper, We judge War Potential of Defense Sufficiency Task Croup Using Agent-Based Modeling and Simulation(ABMS) and indicate the Republic of Korea Navy's future. We use ABMS model, Map Aware Non-uniform Automata(MANA), to be obtained the results. To overcome future threat of Japan and China in a sea around the Korean Peninsula. War Potential of Defense Sufficiency Task Group are to be at least 4KDX-III and $20{\sim}24$KDX-II. Therefore, Republic of Korea Navy have to increase the war potential scales, $11{\sim}15$ battleship with future including build-up plan of present war Potential and Improve The battleship' performance not less than that of KDX-II.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.29-35
• /
• 2011

In this paper, an integrated simulation model for designing multi-agent system based DEMS (distributed energy management system) in stand-alone micro-grid system is proposed. In the design of the EMS(energy management system), the multi-agent based DEMS are more effective than conventional centralized EMS, but it is difficult to design the DEMS by general design tools for power system because of various states of a microgrid system during operation of stand-alone mode. Also, since performance test of the DEMS using a real system is inefficient, an integrated simulation model is required for designing an effective multi-agent system based DEMS. The proposed model consists of Matlab/SimPowerSystems based simulation model of the microgrid system and the Multi-agnet based DEMS designed by Matlab/StateFlow tool. In order to show the effect of the proposed model, the model outputs are analyzed for specified operation conditions.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.295-298
• /
• 2013

미래 전장 환경하의 복합/다종 무기체계를 대상으로 하는 군수 시뮬레이션 모델링 방법론은 기존의 에이전트 시스템에서 실시간성 및 신뢰성뿐만 아니라, 국내 군수 환경을 수용할 수 있는 모델이어야 한다. 본 논문에서는 이 같은 전장상황이라는 특수성에 맞는 다중 에이전트 기반의 모델링 방법론을 제안하다. 다중 에이전트 시스템에서 효과적으로 모델링하기 위하여 군수 시뮬레이션의 모델을 Information, Function model 로 나누고 에이전트 시스템의 중추적인 역할을 하는 Agent Management System(AMS) 을 Management model 로 구성한다. 제안하는 모델링 방법론은 다양한 도메인에서도 구성하기 적합하여 확장성과 유연성의 이점이 있으며, 각 모델이 플러그인 형식으로 구현되어 유사한 도메인에 적용할 때 재사용성이 높은 모델링 방법론을 제시한다.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1E
• /
• pp.1-8
• /
• 2009

Primary radiation force on ultrasound contrast agents (UCA) in a propagating and standing acoustic field was explored. A specific ultrasound contrast agent $Albunex^{(R)}$ and $Optison^{(R)}$ were chosen for simulation. The model was developed based on a shelled bubble model proposed by Church. The numerical simulation suggests that bubble translational motion is more significant in therapeutic ultrasound due to higher intensity and long pulse duration. Even a single cycle of a propagating wave of 4 MPa at 1 MHz can cause a bubble translational motion of greater than $1{\mu}m$ which is approximately one tenth of capillary. Hence, UCA characteristics can be significantly changed in therapeutic ultrasound without rapid bubble collapses.

• Journal of Construction Engineering and Project Management
• /
• v.5 no.4
• /
• pp.12-15
• /
• 2015

Size of building has a direct relationship with building cost, energy use and space maintenance cost. Therefore, minimizing building size during a project development is of paramount importance against such wastes. However, incautious reduction of building size may result in crowded space, and therefore harms the functionality despite the fact that building is supposed to satisfactorily support users' activity. A well-balanced design solution is, therefore, needed at an optimum level that minimizes building size in tandem with providing sufficient space to maintain functionality. For such design, architects and engineers need to be informed accurate and reliable space-use information. We present in this paper a conceptual framework of an agent-based space-use prediction simulation system that provides individual level space-use information over time in a building in consideration of project specific user information and activity schedules, space preference, ad beavioural rules. The information will accordingly assist architects and engineers to optimize space of the building as appropriate.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.393-400
• /
• 2022

Agent-based modeling (ABM), as a relatively new simulation technique, has recently gained in popularity in the civil engineering domain due to its uniquely advantageous features. Among many civil engineering applications, ABM has been applied to facility operation and management, such as energy consumption management, as well as the enhancement of maintenance and repair processes. The former studies used ABM to manage energy consumption through simulating human energy-related behaviors and their interactions with facilities, as well as electrical, heating, and cooling systems and appliances, while the latter used ABM to enhance maintenance process through facilitating coordination, negotiation, and decision making between facility managers, service providers, and repair workers. The present study aims to provide a short qualitative review on the most recent applications of ABM in the above-mentioned areas. Based on the review and follow-up analysis, the study identifies the advantages, disadvantages, and limitations of ABM applications to facility operation and management, and offers several potential future research topics in the hope of filling the existing literature gaps.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.349-352
• /
• 2015

Size of building has a direct relationship with building cost, energy use and space maintenance cost. Therefore, minimizing building size during a project development is of paramount importance against such wastes. However, incautious reduction of building size may result in crowded space, and therefore harms the functionality despite the fact that building is supposed to satisfactorily support users' activity. A well-balanced design solution is, therefore, needed at an optimum level that minimizes building size in tandem with providing sufficient space to maintain functionality. For such design, architects and engineers need to be informed accurate and reliable space-use information. We present in this paper a conceptual framework of an agent-based space-use prediction simulation system that provides individual level space-use information over time in a building in consideration of project specific user information and activity schedules, space preference, ad beavioural rules. The information will accordingly assist architects and engineers to optimize space of the building as appropriate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.6A
• /
• pp.832-844
• /
• 1999

In this paper, we analyzed mobile-IP protocol of IETF, and propose new method to improve performance in handover environments. In proposed method, cache agent manages mobility binding information for mobile host. Thus, effective support of mobility is possible. Also, when handover occurs, mobile host recognizes change of foreign agent, and transmits registration message to new foreign agent. However, during registration time, data packet loss is occurs in old foreign agent. Thus, we prevent data loss by using data packet buffering and forwarding in old foreign agent.According to simulation results for data packet transmission performance in the case of handover occurring, proposed method has better performance than previous method in the view of transmission delay and throughput. Especially, if handover occurs very often, data buffering and forwarding method in foreign agent could guarantee better performance.