• 한국정보시스템학회지:정보시스템연구
• /
• 제21권4호
• /
• pp.185-199
• /
• 2012

The most of international shipping cargoes are transported by ship and the shipping market has been continuously increasing. However, due to the recent global recession, the volume of trade decreased accordingly, and the competition between shippers to gain a competitive advantage in the shipping market continues deepening. To do this, researches on transportation costs savings as well as ways to improve customer service are needed and recently related researches are being pursued. Car carriers which transport more than 80% of car import and export volume in the world also make a lot of effort in order to reduce transportation costs, but in contrast related researches are seldom fulfilled. In this study, we developed an agent system that supports the efficient transportation of car carriers plan so that the car carriers can increase competitiveness through reduction of the logistics costs. To make this, we researched an algorithm for maritime transportation planning, and also developed a prototype of an agent system which can collect the necessary information in real time and establish a dynamic plan.

• 한국실내디자인학회논문집
• /
• 제27권3호
• /
• pp.14-23
• /
• 2018

The spatial planning of the elderly care facility plans is analyzed using space syntax in terms of encouraging the social interaction of the residents in this study. First, through the visibility graph analysis, openness and accessibility of space is analysed. Second, the walking behavior of residents through agent analysis model is simulated. Third, the space planning methods for the elderly care facilities are proposed based on the results. The results are as follows. According to the visibility graph analysis, the main corridor has high visual openness and high accessibility. The visual openness and accessibility of the unit living room, where social interaction among residents is possible in each unit, is low. Space planning is needed to increase direct protection and observation of employees to the unit living room. The location of the nurse station that manages the entire floor needs to be located where the openness and accessibility is most high. The nursing station should have a high degree of connectivity to the entire space, so that any accidents can be managed and contact is accessible. Through the agent simulation the flow from the center to each unit space is highest in the corridor space and the inflow to the private rooms and the living room are similar. Therefore, it is necessary to plan the accessibility of the unit living room more for the natural inflow of residents.

• International Journal of Contents
• /
• 제14권3호
• /
• pp.7-16
• /
• 2018

The extent and depth of the event plan determines the scope of pedagogical experience in situations and consequently the quality of immersive learning based on our simulated world. In contrast to planning in conventional narrative-based systems mainly pursuing dramatic interests, planning in virtual world-based pedagogical systems strive to provide realistic experiences in immersed situations. Instead of story plot comprising predetermined situations, our inter-event planning method aims at simulating diverse situations that each involve multiple events coupled via their associated agents' conditions and meaningful associations between events occurring in a background world. The specific techniques to realize our planning method include, two-phase planning based on inter-event search and intra-event decomposition (down to the animated action level); autonomous and independent agents to behave proactively with their own belief and planning capability; full-blown background world to be used as the comprehensive stage for all events to occur in; coupling events via realistic association types including deontic associations as well as conventional causality; separation of agents from event roles; temporal scheduling; and parallel and concurrent event progression mechanism. Combining all these techniques, diverse exogenous events can be derived and seamlessly (i.e., semantically meaningfully) integrated with the original event to form a wide scope of situations providing chances of abundant pedagogical experiences. For effective implementation of plan execution, we devise an execution scheme based on multiple priority queues, particularly to realize concurrent progression of many simultaneous events to simulate its corresponding reality. Specific execution mechanisms include modeling an action in terms of its component motions, adjustability of priority for agent across different events, and concurrent and parallel execution method for multiple actions and its expansion for multiple events.

• 지능정보연구
• /
• 제9권3호
• /
• pp.1-21
• /
• 2003

전자상거래의 확산에 따른 환경변화 속에서 다품종소량 생산하는 주문제조업체들이 다양한 고객들의 주문에 대응하고, 동적으로 변화하는 내 외적 기업환경 속에서 경쟁력을 제고시키기 위해 본 연구에서는 멀티에이전트 기반 협상지원시스템을 개발하였다. 이 시스템은 동적으로 변하는 환경과 고객들의 주문에 대응하고, 유연한 시스템구조를 이루는데 있어 새로운 패러다임으로 부각되고 있는 에이전트 기술을 사용하였다. 또한, 에이전트간의 협업을 통해 문제를 해결할 수 있는 멀티에이전트 기술을 사용하였다 본 연구에서 제시한 멀티에이전트 기반 협상지원시스템은 주문제조업체에서 가장 중요한 거래활동인 협상의 자동화를 통해 주문에서부터 생산에 이르는 일련의 모든 거래활동을 자동화하는 것을 목적으로 한다.

• 인터넷정보학회논문지
• /
• 제5권2호
• /
• pp.97-105
• /
• 2004

에이전트가 지각이나 행위의 표상을 이해할 수 없는 이유는 의미론적 자질을 문자열로 변환하는 구문론적 표상방식에 의해서 일어난다. 자율적으로 학습하는 인지 에이전트를 구현하기위해 코헨은 에이전트가 sensor와 effector를 사용하여 주위환경과 물리적으로 직접적인 상호작용을 통하여 물리적 스키마의 의미 표상을 학습하는 의미론적 방법을 제안하였다. 본 논문에서는 부정(negation)은 그러한 물리적 스키마를 인식하게 하는 메타 스키마임을 제안한다. 최근에 Graphplan은 계획 시스템의 성능을 향상하기 위하여 inconsistency를 이용하는 제어규칙을 사용하지만, 구문론적으로 접근하여서 부정의 의미 개념을 이해하지 못하고 중복표현의 문제를 야기한다. IPP는 부정 함수인 not을 도입하여 중복문제를 해결하지만 여전히 구문론적으로 접근하며 또한 시간과 공간에서 비효율적이다. 본 논문에서는 의미론적인 접근법을 도입하여 부정을 위해서 반대 개념이라는 긍정 아톰(atom)을 사용하는 것이 지능 에이전트를 구현의 효율적 기법이라고 제안하고, 이 가설을 지지하는 실험적 결과를 제시한다.

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.181-188
• /
• 2022

An intelligent distributed multi-agent system (IDMS) using reinforcement learning (RL) is a challenging and intricate problem in which single or multiple agent(s) aim to achieve their specific goals (sub-goal and final goal), where they move their states in a complex and cluttered environment. The environment provided by the IDMS provides a cumulative optimal reward for each action based on the policy of the learning process. Most actions involve interacting with a given IDMS environment; therefore, it can provide the following elements: a starting agent state, multiple obstacles, agent goals, and a cluttered index. The reward in the environment is also reflected by RL-based agents, in which agents can move randomly or intelligently to reach their respective goals, to improve the agent learning performance. We extend different cases of intelligent multi-agent systems from our previous works: (a) a proposed environment-clutter-based-index for agent sub-goal selection and analysis of its effect, and (b) a newly proposed RL reward scheme based on the environmental clutter-index to identify and analyze the prerequisites and conditions for improving the overall system.

• 대한기계학회논문집A
• /
• 제29권11호
• /
• pp.1463-1471
• /
• 2005

This paper proposes an agent-based scheduling method fur semiconductor wafer fabrication facilities with hard inter-operation temporal constraints. The scheduling problem is to find the feasible schedules that guarantee both logical and temporal correctness. A proposed multi-agent based architecture is composed of scheduling agents, workcell agents, and machine agents. A scheduling agent computes optimal schedules through bidding mechanisms with a subset or entire set of the workcell agents. A dynamic planning-based approach is adopted for the scheduling mechanism so that the dynamic behaviors such as aperiodic job arrivals and reconfiguration can be taken into consideration.

• 로봇학회논문지
• /
• 제3권1호
• /
• pp.23-32
• /
• 2008

This paper presents a task planning system for a steward robot, which has been developed as an interactive intermediate agent between an end-user and a complex smart home environment called the ISH (Intelligent Sweet Home) at KAIST (Korea Advanced Institute of Science and Technology). The ISH is a large-scale robotic environment with various assistive robots and home appliances for independent living of the elderly and the people with disabilities. In particular, as an approach for achieving human-friendly human-robot interaction, we aim at 'simplification of task commands' by the user. In this sense, a task planning system has been proposed to generate a sequence of actions effectively for coordinating subtasks of the target subsystems from the given high-level task command. Basically, the task planning is performed under the framework of STRIPS (Stanford Research Institute Problem Solver) representation and the split planning method. In addition, we applied a state-partitioning technique to the backward split planning method to reduce computational time. By analyzing the obtained graph, the planning system decomposes an original planning problem into several independent sub-problems, and then, the planning system generates a proper sequence of actions. To show the effectiveness of the proposed system, we deal with a scenario of a planning problem in the ISH.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2003년도 추계학술대회 및 정기총회
• /
• pp.338-341
• /
• 2003

CPFR (Collaborative Planning, Forecasting and Replenishment)은 기존의 공급망 개선에 관한 어플리케이션이 갖는 문제점인 정보의 부정확성, 시스템의 단절, 관련 기업 간 협력의 부족 등과 같은 여러 장해요소들을 극복하기 위한 목적으로 설계된 최신 비즈니스 모델로서, 이는 공급망의 총재고를 최소화하기 위해서 공급망의 모든 구성원들이 최종소비자의 실제 수요정보에 근거하여 계획(Planning), 예측(Forecasting), 그리고 보충(Replenishment)을 시스템 상에서 협력적으로 결정하는 것이다. 본 연구에서는 구성원들 간에 발생할 수 있는 예외적인 사항들을 CPFR시스템의 예측단계에서 판별하고, 그러한 예외 사항들을 역동적으로 다루기 위한 지식기반 협업 에이전트 시스템(Knowledge-Based Collaboration Agent System)을 제시한다. 또한 지능적 추론(Reasoning)과 학습(Learning)을 통해 구성원들에게 예외 사항에 대한 최적의 해결안을 제시함으로써 협업 시스템의 자동화를 구현한다.

• 전자공학회논문지CI
• /
• 제48권5호
• /
• pp.42-48
• /
• 2011

에이전트는 특정 목적을 위해 행동을 하는데 이것은 자율지능형 가상군(Computer Generated Forces, CGF)의 공통된 요소이다. 목적을 달성하기 위해 지정된 스크립트를 따라 행위를 하거나 업무 수행의 계획을 세우는 것을 기본적인 에이전트의 지능이라 볼 수 있는데 이보다 더 발전된 지능 에이전트는 계획을 세우는 것뿐만 아니라 계획했던 수행이 어려울 때 계획을 다시 수정하거나 새로운 계획을 적응적으로 만들어내는 것이다. 계획을 수행 할 때 에이전트가 목적을 위한 적응적 행동을 하려면 목표를 달성할 가능성이 적어질 때 스스로 계획을 수정하고 이러한 방식으로 수정되는 방법을 계속적으로 학습하여 차후 같은 경우에는 학습이 반영된 더 좋은 계획 및 전술을 반영하도록 해야 한다. 즉, 목표와 현재의 상태를 실시간으로 분석하고 측정하여 목표 달성도를 정량적으로 계산하고 측정값이 임계값보다 적으면 수정된 계획을 선택하도록 하는 것이다. 본 논문에서는 위와 같이 에이전트가 목표 달성 가능성이 적어질 때 적응적으로 계획을 새롭게 수정하여 적용하는 방법을 연구한 목적 지향적 행위계획 방법을 제안한다.