• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.11a
• /
• pp.157-157
• /
• 2004

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.101-114
• /
• 2018

Several different approaches and mechanisms are introduced to solve the UAV path planning problem. In this paper, we designed and implemented an agent-based simulation software using the Repast platform and Java Genetic Algorithm Package to examine an evolutionary path planning method by implementing and testing within the Repast environment. The paper demonstrates the life-cycle of an agent-based simulation software engineering project while providing a documentation strategy that allows specifying autonomous, adaptive, and interactive software entities in a Multi-Agent System. The study demonstrates how evolutionary path planning can be introduced to improve cognitive agent capabilities within an agent-based simulation environment.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.281-289
• /
• 2010

Recently the intelligent agent systems have been emerged as one of key issues for developing the defense M&S systems. However, most conventional agent architecture of M&S systems utilize the script-based models and can only deal with the individual behaviors so that they cannot suitably describe the precise tactical/strategic behavior and/or complex warfare environment. To overcome these problems, we have proposed the HEAP(Hierarchical Encapsulation and Abstraction Principle)-based hierarchical multi-agent system architecture that is able to intelligently cope with the complex missions based on the functional role of each agent on the hierarchy such as an intelligence officer, captain, commander.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.272-277
• /
• 2001

In this paper, we describe a new method for selecting information sources in a distributed environment. Recently, there has been much research on distributed information retrieval, that is information retrieval (IR) based on a multi-database model in which the existence of multiple sources is modeled explicitly. In distributed IR, a method is needed that would enable selecting appropriate sources for users\` queries. Most existing methods use statistical data such as document frequency. These methods may select inappropriate ate sources if a query contains polysemous words. In this paper, we describe an information-source selection method using two types of thesaurus. One is a thesaurus automatically constructed from documents in a source. The other is a hand-crafted general-purpose thesaurus(e.g. WordNet). Terms used in documents in a source differ from one another and the meanings of a term differ depending on th situation in which the term is used. The difference is a characteristic of the source. In our method, the meanings of a term are distinguished between by the relationship between the term and other terms, and the relationship appear in the co-occurrence-based thesaurus. In this paper, we describe an algorithm for evaluating a usefulness of a source for a query based on a thesaurus. For a practical application of our method, we have developed Papits, a multi-agent-based in formation sharing system. An experiment of selection shows that our method is effective for selecting appropriate sources.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.139-146
• /
• 2002

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.183-193
• /
• 2022

Smart cities are expected to provide residents with convenience via various agents such as CCTV, delivery robots, security robots, and unmanned shuttles. Environmental data collected by various agents can be used for various purposes, including advertising and security monitoring. This study suggests a surveillance map data framework for efficient and integrated multimodal data representation from multi-agents. The suggested surveillance map is a multilayered global information grid, which is integrated from the multimodal data of each agent. To confirm this, we collected surveillance map data for 4 months, and the behavior patterns of humans and vehicles, distribution changes of elevation, and temperature were analyzed. Moreover, we represent an anomaly detection algorithm based on a surveillance map for security service. A two-stage anomaly detection algorithm for unusual situations was developed. With this, abnormal situations such as unusual crowds and pedestrians, vehicle movement, unusual objects, and temperature change were detected. Because the surveillance map enables efficient and integrated processing of large multimodal data from a multi-agent, the suggested data framework can be used for various applications in the smart city.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.21-30
• /
• 2007

Simulation means modeling structures or behaviors of the various objects, and experimenting them on the computer system. And the major approaches are DEVS(Discrete Event Systems Specification). Petri-net or Automata and so on. But, the simulation problems are getting more complex or complicated these days, so that an intelligent agent-based is being studied. In this paper, we are describing an intelligent agent-based simulation tool, which can supports the simulation experiment more efficiently. The significances of our system can be described as follows. First, the system can provide some AI algorithms through the system libraries. Second, the system supports simple method of designing the simulation model, since it's been built under the Finite State Machine (FSM) structure. And finally, the system acts as a simulation framework by supporting user not only the simulation engine, but also user-friendly tools, such as modeler scriptor and simulator. The system mainly consists of main simulation engine, utility tools, and some other assist tools, and it is tested and showed some efficient results in the three different problems.

• Journal of Korea Multimedia Society
• /
• v.11 no.3
• /
• pp.353-363
• /
• 2008

A multi-agent system has a longer learning period and larger state-spaces than a sin91e agent system. In this paper, we suggest a new method to reduce the learning time of Nash Q-learning in a multi-agent environment. We apply Macro-actions to Nash Q-learning to improve the teaming speed. In the Nash Q-teaming scheme, when agents select actions, rewards are accumulated like Macro-actions. In the experiments, we compare Nash Q-learning using Macro-actions with general Nash Q-learning. First, we observed how many times the agents achieve their goals. The results of this experiment show that agents using Nash Q-learning and 4 Macro-actions have 9.46% better performance than Nash Q-learning using only 4 primitive actions. Second, when agents use Macro-actions, Q-values are accumulated 2.6 times more. Finally, agents using Macro-actions select less actions about 44%. As a result, agents select fewer actions and Macro-actions improve the Q-value's update. It the agents' learning speeds improve.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2780-2782
• /
• 2005

In this paper, we present a mobile robot localization solution by using a Ubiquitous Vision System (UVS). The collective information gathered by multiple cameras that are strategically placed has many advantages. For example, aggregation of information from multiple viewpoints reduces the uncertainty about the robots' positions. We construct UVS as a multi-agent system by regarding each vision sensor as one vision agent (VA). Each VA performs target segmentation by color and motion information as well as visual tracking for multiple objects. Our modified identified contractnet (ICN) protocol is used for communication between VAs to coordinate multitask. This protocol raises scalability and modularity of thesystem because of independent number of VAs and needless calibration. Furthermore, the handover between VAs by using ICN is seamless. Experimental results show the robustness of the solution with respect to a widespread area. The performance in indoor environments shows the feasibility of the proposed solution in real-time.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.4
• /
• pp.188-196
• /
• 2001

This paper presents and efficient algorithm for the loss minimization by automatic sectionalizing switch operation in distribution systems. Ant colony algorithm is multi-agent system in which the behaviour of each single agent, called artificial ant, is inspired by the behaviour of real ants. Ant colony algorithm is suitable for combinatiorial optimization problem as network reconfiguration because it use the long term memory, called pheromone, and heuristic information with the property of the problem. The proposed methodology with some adoptions have been applied to improve the computation time and convergence property. Numerical examples demonstrate the validity and effectiveness of the proposed methodology using a KEPCO's distribution system.