• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.7-13
• /
• 2008

This paper suggests a Path-planning algorithm for mobile agents. While there are a lot of studies on the path-planning for mobile agents, mathematical modeling of complex environment which constrained by spatio-temporally is very difficult and it is impossible to obtain the optimal solutions. In this paper, an optimal path-planning algorithm based on the graphic technique is presented. The working environment is divided into two areas, the one is free movable area and the other is not permissible area in which there exist obstacles and spatio-temporally constrained, and an optimal solution is obtained by using a new algorithm which is based on the well known ACO algorithm.

• Journal of Korea Multimedia Society
• /
• v.10 no.12
• /
• pp.1714-1725
• /
• 2007

This paper describes a top-down behavior planning framework in a simulation game from personality to real life action selection. The combined behavior creating system is formed by five levels of specification, which are personality definition, motivation extraction, emotion generation, decision making and action execution. Along with the data flowing process in our designed framework, NPC selects actions autonomously to adapt to the dynamic environment information resulting from active agents and human players. Furthermore, we illuminate applying Gaussian probabilistic distribution to realize character's behavior changeability like human performance. To elucidate the mechanism of the framework, we situated it in a restaurant simulation game.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.751-753
• /
• 2005

기존의 시맨틱 웹 서비스 에이전트는 사용자 요구에 의미적으로 부합하는 서비스를 검색하고 합성하는 플래너에 중점을 둔 반면 실행자에는 큰 비중을 두지 않았다. 그러나 기존의 다수 플래닝 알고리즘은 사용자 제약 사항의 일부만을 적용하여 불완전한 결과를 도출함에도 불구하고 플래닝을 완료하는 문제가 있다. 따라서 실행자가 단순히 플래닝된 서비스만을 실행한다면 사용자 요구를 완전히 충족시킬 수 없다. 이를 해결하기 위해 본 논문에서는 플래닝의 취약점을 보완하는 실행자를 제안하고 이를 기반으로 에이전트를 개발하였다. 본 논문에서 제안한 실행자는 서비스 실행 결과를 분석하여 사용자의 요구 사항 중 반영되지 않은 정보의 적용 또는 불필요한 정보의 제거를 위해, 플래너에게 re-planning을 요구하거나 서비스 실행 결과 자체에서 관련 정보를 추출한다. 이를 통해 사용자의 요구 사항에 대한 서비스 결과의 정확도 향상을 도모한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.5
• /
• pp.435-441
• /
• 2013

A swarm robot system consists of with multiple mobile robots, each of which is called an agent. Each agent interacts with others and cooperates for a given task and a given environment. For the swarm robotic system, the loss of the entire work capability by malfunction or damage to a single robot is relatively small and replacement and repair of the robot is less costly. So, it is suitable to perform more complex tasks. The essential component for a swarm robotic system is an inter-robot collaboration strategy for teamwork. Recently, the swarm intelligence theory is applied to robotic system domain as a new framework of collective robotic system design. In this paper, FA (Firefly Algorithm) which is based on firefly's reaction to the lights of other fireflies and their social behavior is employed to optimize the group behavior of multiple robots. The main application of the firefly algorithm is performed on path planning of swarm mobile robots and its effectiveness is verified by simulations under various conditions.

• Journal of Information Technology Services
• /
• v.17 no.3
• /
• pp.17-36
• /
• 2018

In this study, we developed a chatbot (Dialogue agent) using small Q & A data and evaluated its performance. The chatbot developed in this study was developed in the form of an FAQ chatbot that responds promptly to customer inquiries. The development of chatbot was conducted in three stages : 1. Analysis and planning, 2. Content creation, 3. API and messenger interworking. During the analysis and planning phase, we gathered and analyzed the question data of the customers and extracted the topics and details of the customers' questions. In the content creation stage, we created scenarios for each topic and sub-items, and then filled out specific answers in consultation with business owners. API and messenger interworking is KakaoTalk. The performance of the chatbot was measured by the quantitative indicators such as the accuracy that the chatbot grasped the inquiry of the customer and correctly answered, and then the questionnaire survey was conducted on the chatbot users. As a result of the survey, it was found that the chatbot not only provided useful information to the users but positively influenced the image of the pension. This study shows that it is possible to develop chatbots by using easily obtainable data and commercial API regardless of the size of business. It also implies that we have verified the validity of the development process by verifying the performance of developed chatbots as well as an explicit process of developing FAQ chatbots.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.9-19
• /
• 2014

The automotive industry has made much efforts to deliver finished vehicles to customers with speed and reliability. Decreasing the time a vehicle stays within an assembly plant from production release to shipment contributes to reduce the total order lead-time and consequently, the total transportation cost as well. Conventional shipment planning algorithms are limited in accommodating the dynamics of assembly plant operations as to finished vehicle shipment. This paper presents a market-based multi-agent shipment planning algorithm to optimize the performance of vehicle shipment process, capturing the operationally disruptive events. Experimental results using simulation show that the algorithm improves vehicle shipment performance with respect to lead time, labor efficiency, finished product quality, and transportation efficiency.

• Information Systems Review
• /
• v.10 no.1
• /
• pp.115-133
• /
• 2008

The third-party logistics industry mainly delivers goods from a place to an arrival place on behalf of the freight owner. To handle the work, they need a transportation route including transportation equipment between the starting place and the arrival place, schedule information for departure/arrival and transportation cost. Actually, automatic searching for an optimal transportation route, which considers arrival and departure points for intermodal transportation, is not a simple problem. To search efficiently transportation route, the collection of schedule information for intermodal transportation and transportation route generation have become critical and vital issues for logistics companies. Usually, they manually make a plan for a transportation route by their experience. Because of this, they are limited in their ability if there is too much cargo volume and a great many transactions. Furthermore, their dependence on the conventional way in doing business causes an inefficient selection of transporters or transportation routes. Also, it fails to provide diverse alternatives for transportation routes to the customers, and as a result, increases logistics costs. In an effort to solve these problems, this study aims to develop a route planning system based on agent, which can collect scattered schedule information on the Web. The route planning system also has an algorithm for transportation route generation in intermodal transportation.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.201-205
• /
• 1997

As manufacturing system have become complex and globalized, rapid development and production of products are essentially requisites for competitiveness. The importance of agility in manufacturing is being emphasized and a new paradigm is necessary for reduction of the time and expenses related to planning, product development and production. To meet such requirements, virtual manufacturing (VM) environment was suggested. In this paper, Multi-agent system is adopted into VM operating system. Because our system is flexible due to agent technology, agents can be added or deleted with ease. VM unit modules which were defined as DEVS models execute independent simulation of other modules in unit level and compose one VM system with other modules. They also execute simulation in system level. This research can contribute to usefulness of VM environment due to flexibility and extensibility of this system.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.1
• /
• pp.119-126
• /
• 2016

The US Army used MARK-1 composed of atropine autoinjector and 2-PAM autoinjector as a medical countermeasure against nerve agent poisoning. Recently, it has been being replaced by the ATNAA(Antidote Treatment Nerve Agent AutoInjector) for improvement the convenience in use and rapid detoxification effect. ATNAA(FDA approval, NDA 21-175, 2002. 1. 17) is a multi-chambered autoinjector that sequentially delivers atropine and 2-PAM through a single needle to allow Warfighters to survive against lethal exposure to nerve agents. In this paper, our group investigated the case of FDA approval of ATNAA in a point of the various data required by FDA guideline, thereby making it easy to meet the KFDA guideline for the approval of the prototype our group has been developed. The purpose of this study is to provide a reference for efficient research activities to minimize time and cost. Additionally, the purpose of this study is to provide a reference for the planning for the development of similar drug.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.127-129
• /
• 2007

Since the competitive market environment was introduced into the electric power industry, the structure of the industry has been changing from vertically integrated system to functionally unbundled and decentralized system composed of multiple (decision-making) market participants. So the market participants such as Gencos or LSE (load serving entity) need to forecast the market clearing price and thus build their offer or bidding strategies. Not just these market players but also a market operator is required to perform market analysis and ensure simulation capability to manage and monitor the competitive electricity market. For fulfilling the demand for market simulation, many global venders like GE, Henwood, Drayton Analytics, CRA, etc. have developed and provided electricity market simulators. Most of these simulators are based on the optimization formulation which has been used mainly for the least cost resource planning in the centralized power system planning and operation. From this standpoint, it seems somehow inevitable to face many challenges on modeling competitive market based on the method of traditional market simulators. In this paper, we propose a kind of new method, which is MAS based market simulation. The agent based model has already been introduced in EMCAS, one of commercial market simulators, but there may be various ways of modeling agent. This paper, in particular, seeks to introduce an model for MAS based market simulator.