• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.92.4-92
• /
• 2002

In this paper, as an ideal test bed for studies on multi-agent system, the multiple micro robot soccer playing system is introduced at first. The construction of such experimental system has involved lots of kinds of challenges such as sensors fusing, robot designing, vision processing, motion controlling, and especially the cooperation planning of those robots. So in this paper we want to stress emphasis on how to evolve the system automatically based on the model of behavior-based learning in multi-agent domain. At first we present such model in common sense and then apply it to the realistic experimental system . At last we will give some results showing that the proposed approach is feasi...

• 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.

• Advances in materials Research
• /
• v.6 no.3
• /
• pp.245-255
• /
• 2017

High energy ball milling is employed to produce iron matrix- multiwall carbon nanotube (MWCNT) reinforced composite. The damage caused to MWCNT due to harsh ball milling condition and its influence on interfacial bonding is studied. Different amount of MWCNT is used to find the optimal percentage of MWCNT for avoidance of the formation of chemical reaction product at the matrix - reinforcement interface. Effect of process control agent is assessed by the use of different materials for the purpose. It is observed that ethanol as a process control agent (PCA) causes degradation of MWCNT reinforcements after milling for two hours whereas solid stearic acid used as process control agent, allows satisfactory conservation of MWCNT structure. It is further noted that at a high MWCNT content (~ 2wt.%), high energy ball milling leads to reaction of iron and carbon and forms iron carbide (cementite) at the iron-MWCNT interface. At low percentage of MWCNT, dissolution of carbon in iron takes place and the amount of reinforcement in iron matrix composite becomes negligibly small. However, under the present ball milling condition (ball to metal ratio~ 6:1 and 200 rpm vial speed) iron-1wt.% MWCNT composite of good interfacial bonding can retain the tubular structure of reinforcing MWCNT.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.8
• /
• pp.758-767
• /
• 2012

In the ad-hoc wireless network environment, that the fixed sensor nodes and the sensor nodes to move are mixed, as the number of the sensor nodes with mobility are getting more, the costs to recover and maintain the whole network will increase more and more. This paper proposed the CDSR (Cost based Dynamic Source Routing) algorithm being motivated from the typical DSR algorithm, that is one of the reactive routing protocol. The cost function is defined through measuring the cost which any sensor node pays to participate in the whole network for communication. It is also showed in this paper that the proposed routing algorithm will increase the efficiency and life of whole sensor network through a series of experiments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.155-161
• /
• 2008

An automated healthcare monitoring is demand of time, lot of problems occurring just because of less monitoring of patients health condition on time. In this paper an embedded healthcare service is proposed by an iSCSI protocol on an automated multi-agent coordination by resource-constrained devices controlled system for healthcare service. The coordination between the resource constrained devices (e.g. PDA, SmartPhone, Tablet PC), and automated agents are maintained by a two-way handshaking mode iSCSI protocol. The automated health care control could be useable, and beneficial in the repetitive way. A fully centralized control is not applicable for this kind of approach.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.2
• /
• pp.120-134
• /
• 2015

Under the hypothesis that the form of road network could affect crime occurrence, this study demonstrates to prove them using Space Syntax with real crime data. We calculated integration, control, connection index by means of Space Syntax and analyzed the relationship between the three indexes and the number of crime occurrence on the each road. Next, in order to generalize the analysis results we adopted Multi-Agent Model and simulated several scenarios on the computer virtual space. The results revealed that integration index has the strongest relationship with crime occurrence both in the case of real study area and virtual space simulations. Though this study has several limitations on the extent of virtual space and realistic computer programming of agents' behavior, the results are meaningful to verify the relationship between the form of read network and crime occurrence. Moreover the simulation platform that this study developed has promising possibilities to find realistic solutions on the effective police deployment or facility layout to improve smart safe city development.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.226-234
• /
• 2022

With advances in autonomous vehicles and networked control, there is a growing interest in the consensus control of a multi-agents system to control multi-agents with distributed control beyond the control of a single agent. Since consensus control is a distributed control, it is bound to have delay in a practical system. In addition, it is often difficult to have a very accurate mathematical model for a system. Even though a reinforcement learning (RL) method was developed to deal with these issues, it often experiences slow convergence in the presence of large uncertainties. Thus, we propose a slide RL which combines the sliding mode control with RL to be robust to the uncertainties. The structure of a sliding mode control is introduced to the action in RL while an auxiliary sliding variable is included in the state information. Numerical simulation results show that the slide RL provides comparable performance to the model-based consensus control in the presence of unknown time-varying delay and disturbance while outperforming existing state-of-the-art RL-based consensus algorithms.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3277-3290
• /
• 2023

Nuclear power plant (NPP) operations with multiple objectives and devices are still performed manually by operators despite the potential for human error. These operations could be automated to reduce the burden on operators; however, classical approaches may not be suitable for these multi-objective tasks. An alternative approach is deep reinforcement learning (DRL), which has been successful in automating various complex tasks and has been applied in automation of certain operations in NPPs. But despite the recent progress, previous studies using DRL for NPP operations have limitations to handle complex multi-objective operations with multiple devices efficiently. This study proposes a novel DRL-based approach that addresses these limitations by employing a continuous action space and straightforward binary rewards supported by the adoption of a soft actor-critic and hindsight experience replay. The feasibility of the proposed approach was evaluated for controlling the pressure and volume of the reactor coolant while heating the coolant during NPP startup. The results show that the proposed approach can train the agent with a proper strategy for effectively achieving multiple objectives through the control of multiple devices. Moreover, hands-on testing results demonstrate that the trained agent is capable of handling untrained objectives, such as cooldown, with substantial success.

• Journal of the Korean Society of Safety
• /
• v.18 no.3
• /
• pp.94-100
• /
• 2003

Gel-like compounds containing flammable solvents were prepared to use fur cleaning agents in field of innovative industries and general purposes. And experiments were conducted to improve the defects of liquified flammable solvents from the view point of safety and health hazards. Flammable solvents used in this study were several single component flammable solvents(turpentine oil, N-methyl-2-pyrrolidone(NMP), d-limonene) and multi component flammable solvent(gasoline and ethanol). For gelation of flammable solvents, commercially Known as Aerosil(equation omitted) 200 fumed silica and triethanolamine(TEA) were used as gelation agent dispersant. The analyses on properties of gel-like compounds was studied by gelation and viscosity test pH test, volatility test and differential scanning calorimetry(DSC) measurement. The experimental results indicate that gel-like compounds containing flammable solvents have pH stability, high viscosity, volatile organic compounds(VOC) control by the decrease of volatility and odor component generation, fluidity control etc. From the experimental values, it can be predicted that the safety in the working place is improved by manufacturing flammable solvents into gel-like compounds.

• Restorative Dentistry and Endodontics
• /
• v.24 no.1
• /
• pp.55-66
• /
• 1999

The purpose of this study was to evaluate the microleakage of 5 current dentin bonding systems which are composed of 2 multi-bottle systems(Scotchbond Multi-Purpose, All Bond2) and 3 one-bottle systems(Single bond, One-Step, Prime & Bond). In this in vitro study, class V cavities were prepared on buccal and lingual surfaces of sixty extracted human premolars and molars on cementum margin. The experimental teeth were randomly divided into six groups of 10 samples (20 surfaces) each, Group 1 : Scotchbond Multi-Purpose ; Group 2 : All Bond 2 ; Group 3 : Single Bond ; Group 4 : One-Step ; Group 5 : Prime & Bond ; Group 6 : no bonding agent(control). The bonding agent and composite resin were applied for each group following the manufacturer's instructions. After 500 thermocycling between $5^{\circ}C$ and $55^{\circ}C$, the 60 teeth were placed in 2% Methylene blue dye for 24 hours, then rinsed with tab water. The specimen were embedded in clear resin, then sectioned buccolingually through the center of restoration with a low speed diamond saw. The dye penetration on each of the specimen were then observed with a stereomicroscope at ${\times}20$. The results of study were statistically analyzed using the Student-Newmann-Keul's Methods and the Mann-Whitney Rank Sum Test. The resin/dentin interfaces were examined under Scanning Electron Microscopy. The results of this study were as follows. 1. None of the dentin bonding systems used in this study showed significant difference in leakage values at both the enamel and the dentin margins (P>0.05). 2. In all groups except the control, leakage value seen at the enamel margin was significantly lower than that seen at the dentin margin (P<0.05). 3. Compared to the control group, all the groups treated with dentin bonding systems showed significantly lower leakage value at both enamel and dentin margins (P<0.05). 4. In the SEM view, gaps were observed in the composite resin / dentin interface in group 6 where no dentin bonding agent was used, and in all the other groups (group 1, 2, 3, 4, 5) composite resin, hybrid layer, and dentin were seen to be closely adhering to each other where there were no leakages. Well-developed resin tags 3~100${\mu}m$ in length infiltrated dentinal tubules past the hybrid layer and a hybrid layer 1~5${\mu}m$ thick had developed between the dentinal surface and the composite resin surface.