• 한국군사과학기술학회지
• /
• 제23권4호
• /
• pp.337-345
• /
• 2020

The Weapon-Target Assignment(WTA) problem can be formulated as an optimization problem that minimize the threat of targets. Existing methods consider the trade-off between optimality and execution time to meet the various mission objectives. We propose a multi-agent reinforcement learning algorithm for WTA based on mean field game to solve the problem in real-time with nearly optimal accuracy. Mean field game is a recent method introduced to relieve the curse of dimensionality in multi-agent learning algorithm. In addition, previous reinforcement learning models for WTA generally do not consider weapon interference, which may be critical in real world operations. Therefore, we modify the reward function to discourage the crossing of weapon trajectories. The feasibility of the proposed method was verified through simulation of a WTA problem with multiple targets in realtime and the proposed algorithm can assign the weapons to all targets without crossing trajectories of weapons.

• Asia pacific journal of information systems
• /
• 제12권2호
• /
• pp.197-216
• /
• 2002

Cooperativeness within an organization can be conceptualized as the degree of members' willingness to work with others. The simulation study investigates the relationships of cooperativeness with team performance at different levels of information redundancy by using a multi-agents model called Team-Soar. The model consists of a group of four individual Al agents situated in a network, which models a naval command and control team consisting of four members. The study used a $9{\times}3$ design in which agent cooperativeness was manipulated at nine levels by gradually replacing selfish team members with increasing numbers of neutral and cooperative members, while information redundancy was controlled at three different levels(i.e., low, medium, and high). Results of the Team-Soar simulation show that cooperation has positive impacts on team performance. Further, the results reveal that the impact of agent cooperativeness on team performance depends on the amount of information needed to be processed during the decision making process.

• 한국게임학회 논문지
• /
• 제9권5호
• /
• pp.117-125
• /
• 2009

실시간 전략 시뮬레이션 게임에서 각각의 팀은 다수의 에이전트로 구성하고 상태 팀을 이기기 위한 전략을 수행한다. 전략은 팀에 속한 에이전트들의 협력을 필요로 하며 이를 위해서는 다중 에이전트 시스템이 필요하다. 다중 에이전트 시스템의 의사 결정방법 중에서 중앙 집중적인 의사 결정 방법은 조정 에이전트를 사용해서 팀을 위한 작업을 선택한다. 비 중앙 집중적인 의사 결정 방법은 에이전트가 각각 주체가 되어서 다른 에이전트와 의사소통을 하기 때문에 비용이 많이 든다. 본 논문에서는 조정 에이전트를 사용할 때 다수의 에이전트를 그룹으로 관리하는 방법, 경매 시스템을 사용해서 에이전트에게 작업을 할당하는 방법 그리고 할당한 작업 중에서 수행에 실패한 작업은 다른 에이전트에게 다시 할당방법을 제안한다. 실험에서는 스타크래프트 게임에서 제안한 시스템을 적용할 때 공격력과 방어력이 향상되는 것을 볼 수 있었다. 제안한 방법을 사용한 에이전트의 팀 승리 비율은 8대 2로 높아졌다.

• Journal of Power Electronics
• /
• 제15권2호
• /
• pp.455-468
• /
• 2015

A microgrid (MG) with integrated renewable energy resources can benefit both utility companies and customers. As a result, they are attracting a great deal of attention. The control of a MG is very important for the stable operation of a MG. The droop-control method is popular since it avoids circulating currents among the converters without using any critical communication between them. Traditional droop control methods have the drawback of an inherent trade-off between power sharing and voltage and frequency regulation. An adaptive droop control method is proposed, which can operate in both the island mode and the grid-connected mode. It can also ensure smooth switching between these two modes. Furthermore, the voltage and frequency of a MG can be restored by using the proposed droop controller. Meanwhile, the active power can be dispatched appropriately in both operating modes based on the capacity or running cost of the Distributed Generators (DGs). The global information (such as the average voltage and output active power of the MG and so on) required by the proposed droop control method to restore the voltage and frequency deviations can be acquired distributedly based on the Multi Agent System (MAS). Simulation studies in PSCAD demonstrate the effectiveness of the proposed control method.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.249-254
• /
• 2001

Abstract In this paper, we propose a method of cooperative control based on artifical intelligent system in distributed autonomous robotic system. In general, multi-agent behavior algorithm is simple and effective for small number of robots. And multi-robot behavior control is a simple reactive navigation strategy by combining repulsion from obstacles with attraction to a goal. However when the number of robot goes on increasing, this becomes difficult to be realized because multi-robot behavior algorithm provide on multiple constraints and goals in mobile robot navigation problems. As the solution of above problem, we propose an architecture of fuzzy system for each multi-robot speed control and fuzzy-neural network for obstacle avoidance. Here, we propose an architecture of fuzzy system for each multi-robot speed control and fuzzy-neural network for their direction to avoid obstacle. Our focus is on system of cooperative autonomous robots in environment with obstacle. For simulation, we divide experiment into two method. One method is motor schema-based formation control in previous and the other method is proposed by this paper. Simulation results are given in an obstacle environment and in an dynamic environment.

• 인터넷정보학회논문지
• /
• 제10권1호
• /
• pp.101-110
• /
• 2009

효율적인 자원공유 및 동적인 시스템구성을 위한 지능형 분산 접근방식에서 주로 멀티에이전트 시스템을 사용한다. 또한 객체중복은 고장허용시스템을 구축하여 시스템에 예기치 않은 결함의 문제를 해결하기 위해 흔히 사용된다. 본 논문은 동적인 객체그룹관리에 기반한 지능형 멀티에이전트 분산플랫폼을 제시하고, 제안한 filtered k-means (Fk-means)를 기반으로 하여 객체검색기법을 제시한다. 객체 결함의 경우에, 대체 객체를 검색하여 클라이언트에게 적절한 객체를 투명하게 재 연결 시켜주기 위해 Fk-means를 사용한다. 검색방법을 효율적으로 수행하고, 그룹 내의 적절한 객체를 포함시키기 위해 Fk-means의 여과 범위를 설정한다. 시뮬레이션 결과 제안한 기법이 분산객체그룹에 대해 빠르고 정확한 검색을 나타내었다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.145-150
• /
• 2001

A Controlled Ecological Life Support System(CELSS) is essential for man to live a long time in a closed space such as a lunar base or a mars base. Such a system may be an extremely complex system that has a lot of facilities and circulates multiple substances,. Therefore, it is very difficult task to control the whole CELSS. Thus by regarding facilities constituting the CELSS as agents and regarding the status and action as information, the whole CELSS can be treated as multi-agent system(MAS). If a CELSS can be regarded as MAS the CELSS can have three advantages with the MAS. First the MAS need not have a central computer. Second the expendability of the CELSS increases. Third, its fault tolerance rises. However it is difficult to describe the cooperation protocol among agents for MAS. Therefore in this study we propose to apply reinforcement learning (RL), because RL enables and agent to acquire a control rule automatically. To prove that MAS and RL are effective methods. we have created the system in Java, which easily gives a distributed environment that is the characteristics feature of an agent. In this paper, we report the simulation results for material circulation control of the CELSS by the MAS and RL.

• 지능정보연구
• /
• 제11권3호
• /
• pp.1-23
• /
• 2005

개인화된 상기 시스템은 사용자의 현재 상황 정보를 토대로 현재 욕구를 동적이며 선응적으로 파악하여야 한다. 하지만 기존의 욕구 인식 방법론 및 상기시스템 아키텍처들은 이러한 요구 사항을 잘 반영하지 못해왔다. 따라서 본 논문은 에이전트, 시맨틱 웹, 그리고 RFID기반의 상황인지를 활용한 선응적인 욕구 인지 메커니즘을 유력한 유비쿼터스 서비스 지원환경의 하나인 개인화된 상기 시스템에 적용하는 것을 목적으로 한다. 이를 위하여 주된 욕구 인지 이론으로 Rescorla-Wagner 모형을 채택하였다. 또한 본 논문에서 제안하는 방법론의 실현 가능성을 보이기 위해 NAMA (Need Aware Multi-Agent)-RFID라고 하는 프로토타입 시스템을 개발하였다. NAMA는 사용자의 욕구를 인지하기 위해 상황 정보 및 사용자 프로파일과 선호도, 가용 서비스 관련 정보 등을 고려할 수 있으며, 웹 서비스의 형태로 구현된 서비스 집합들을 사용자에게 연결시켜준다. 더욱이 범위성 측면에서의 시스템 성능을 보이기 위해 시뮬레이션을 수행하였으며, 그 결과를 보였다.

• 한국자동차공학회논문집
• /
• 제15권1호
• /
• pp.8-15
• /
• 2007

Freeway corridors consist of urban freeways and parallel arterials that drivers can use alternatively. Ramp metering in freeways and signal control in arterials are contemporary traffic control methods that have been developed and applied in order to improve traffic conditions of freeway corridors. However, most of the existing studies have focused on either optimal ramp metering in freeways, or progression signal strategies between arterial intersections. There have been no traffic control systems in Korea that integrates the freeway ramp metering and arterial signal control. The effective control strategies for freeway operations may cause negative effects on arterial traffic. On the other hand, traffic congestion and bottleneck phenomenon of arterials due to the increasing peak-hour travel demand and ineffective signal operation may generate an accessibility problem to freeway ramps. Thus, the main function of the freeway which is the through-traffic process has not been successful. The purpose of this study is to develop an integrated control model that connects freeway ramp metering systems and signal control systems in arterial intersections. And Optimization of integrated control model which consists of ramp metering and signal control is another purpose. The design of experiment, neural network, and simulated annealing are used for optimization.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권9호
• /
• pp.4379-4397
• /
• 2017

Three different improvements of the Velocity-based model were proposed in a minimal velocity-based pedestrian model. The improvements of the models are based on the different agent forms. The different representations of the agent lead to different results, in this paper, we simulated the pedestrian movements in some typical scenes by using different agent forms, and the agent forms included the circles with different radiuses, the ellipse and the multi-circle stand for one pedestrian. We have proposed a novel model of pedestrian dynamics to optimize the simulation. Our model specifies the pedestrian behavior using a dynamic ellipse, which is parameterized by their velocity and can improve the simulaton accuracy. We found a representation of the pedestrian much closer to the reality. The phenomena of the self-organization can be observable in the improved models.