• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.6
• /
• pp.584-590
• /
• 2000

Urban traffic situations are extremely complex and highly interactive. The multi-agent systems approach can provide a new desirable solution. Currently, a traffic simulator is needed to understand and explore the difficulties in an agent-oriented traffic control. This paper presents an agent-oriented fuzzy logic controller for multiple crossroads simulation. A fuzzy logic control simulation with variables of arrival, queue, and traffic volume could alleviate traffic congestion. We developed an agent-oriented simulator suitable for traffic junctions with η$\times$η intersections in Visual C++. The proposed method adaptively controls the cycle of traffic signals even though the traffic volume varies. The effectiveness of this method was shown through simulation of multiple intersections.

• Advances in robotics research
• /
• v.2 no.3
• /
• pp.247-257
• /
• 2018

Various studies have been performed to coordinate robots in transporting objects and different artificial intelligence algorithms have been considered in this field. In this paper, we investigate and solve Multi-Robot Transportation problem by using a combined auction algorithm. In this algorithm each robot, as an agent, can perform the auction and allocate tasks. This agent tries to clear the auction by studying different states to increase payoff function. The algorithm presented in this paper has been applied to a multi-robot system where robots are responsible for transporting objects. Using this algorithm, robots are able to improve their actions and decisions. To show the excellence of the proposed algorithm, its performance is compared with three heuristic algorithms by statistical simulation approach.

• 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 Safety Management & Science
• /
• v.14 no.3
• /
• pp.159-166
• /
• 2012

A*algorithm is highly useful to search the shortest route to the destination in the evacuation simulation. For this reason, A*algorithm is used to evaluate the evacuation experiment by the computer simulation. However there are some problems to analyze the outcome in relation to the reality. Because all the people in the building are not well-informed of the shortest route to the exit. And they will not move to the disaster spot though it is shortest route to the exit. Therefore, evacuation simulation program based on A*algorithm raise a problem of bottleneck phenomenon and dangerous result by damage surrounding the disaster spot. The purpose of this research is to prove the necessity for dispersion evacuation simulation by Multi agent system to solve the problems of the existing evacuation simulation program based on A*algorithm.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.75-83
• /
• 2014

Most warship combat systems inquire human operator to control several sensor and another equipments as well as decision-modeling. For this reason, many researches with multi-agent based M&S (Modeling and Simulation) have been increasingly conducted. However there cannot find any researches of M&S based analysis for anti-submarine warfare that requires a high level of mission complexity between multiple platforms. In this research, we have been developed various combat platform models such as warship, submarine and helicopter, etc. In order to apply the multi-agent-based M&S technology to the anti-submarine warfare i.e. a HVU (High Value Unit) escort mission scenario. Then we have successfully analyzed the measures of effectiveness according to the different tactics and different situations. In future, the defence engineer maybe employ our methodology and tools to analyze actual tactical problem by simply inserting actual data into our agent model.

• Korean Management Science Review
• /
• v.32 no.2
• /
• pp.111-124
• /
• 2015

In the management literature, it has been widely accepted among both researchers and practitioners that the level of team creativity is significantly related to the organizational performance. Besides, researchers posited with confidence that team diversity and task difficulty would affect team creativity through team members' activities of exploration and exploitation. However, empirical approaches to proving this belief suffered from lack of real data and proper methods as well. To tackle the research void like this, we propose a multi-agent simulation (MAS) mechanism. By adopting a set of parameters which validity were proven in the related literature, we conducted a series of experiments in the environment of the MAS platform named NetLogo. There sults suggest that managers can differentiate team diversity strategies according to task difficulty. In the case of a difficult task, managers need to increase team diversity so that their teams can maximize team creativity through rigorous exploration and exploitation. It is desirable to maintain an average level of team diversity when performing an easy task.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.149.5-149
• /
• 2001

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 ...

• 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.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.4
• /
• pp.107-114
• /
• 2017

In general, credibility for some analysis results is very important to most decision makers. Especially, it is even more critical for military commander to choose the best course of action by using the simulation results when he want to decide to allocate his available weapon system assets. Therefore, improving the credibility of simulation output is one of the key issues in military research fields. In this paper, we proposed a new simulation framework to improve the credibility of weapon's effectiveness analysis results. Multi-agent based simulation tool is applied and compare current process to the proposed framework. We also showed an example case when a communication repeaters are installed to expand the commanding area scope. The example clearly tells why this new simulation framework is more efficient and improve the credibility of simulation results.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.2
• /
• pp.194-205
• /
• 2006

The purpose of this study is to develop a pedestrian multi-agent model and simulation system using multi-agent theory, which may be utilized as a planning support system for building a comfort and safe environment of pedestrian street. Differing from existing pedestrian models, however, every single pedestrian was regarded as an individual agent in the model. Multiple agents like multiple pedestrians in the street then maintain their own characteristics and respond to surrounding environment. In addition their moving behavior are made by their own decision rules that they have or had acquired through the interactive communications or learning between agents like real world. After verifying the model validation, as the $R^2$ between the predicted value and observed value was up to 0.781, the developed model was applied to Gazwa district within Gyeongsang university village. The simulation system was developed by Flash MX action scripts and the physical environment of the streets was configured with the digital map and ArcGis within computer virtual space. The attribute data of buildings such as type and size of commercial business were collected through the field survey and combined with physical features. Then the effect of the variation of building attractiveness and the occurrence of street events to pedestrian environment were simulated. Through the experiments this study could make suggestions to improve pedestrian environment.