• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.393-397
• /
• 2001

This paper addresses an Intelligent Agent-based Open Architecture Cell Controller for Intelligent Manufacturing System(IMS). With an Intelligent Agent approach, the IMS will be a independent, autonomous, distributed system and achieve a adaptability to change of manufacturing environment. As the development methodology of Open Architecture Cell Controller, an object-oriented modeling technique is employed for building models associated with IMS operation, such as resource model, product model, and control model. Intelligent Agent-based Open Architecture Cell Controller consists of two kinds of dependant agents, that are the active agent and the coordinator agent. The Active agent is contributed to control components of IMS in real-time. The coordinator agent has great role in scheduling and planning of IMS. It communicates with other active agents to get information about status on system and generates the next optimal task through the making-decision logic and dispatch it to other active agent.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11S
• /
• pp.3410-3419
• /
• 1999

Autonomous Intrusion Analysis Agent(AIAA) is Incident Response Team staff's tool that scans, analyses, reports and alerts the traces of intrusion based on system logs and intruder's backdoors inside compromised system by IR staff after security incident is reported to the IR team. AIAA is intelligent to recognize to check out who is intruder from all the user accounts and to report the suspected candidates to the master control system in IR team. IR staff who controls AIAA with master system can pick up an intruder from the candidates reported by AIAA agent and review all related summary reports and details including source host's mane, finger information, all illegal behavior and so on. AIAA is moved to compromised system by the staff to investigate the signature of intrusion along the trace of victim hosts and it is also operated in secret mode to detect the further intrusion. AIAA is alive in all victim systems until the incident is closed and IR staff can control AIAA operation and dialogue with AIAA agent in Web interface.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.453-458
• /
• 2001

A mobile agent is an autonomous software agent capable of moving from one computer to another while performing its tasks. We view the agent as a discrete event system in the view of its computation and communication. This paper presents a methodology far modeling and simulation of such a mobile agent system as a discrete event system. The methodology is based on the Mobile Discrete Event System Specification (MDEVS) formalism and the associated simulation environment AgentSim which are previously developed by the authors. Within the methodology an atomic model represents dynamics of a mobile agent; a coupled model is modeled as mobile agent servers for representation of structural changes between atomic agents. Being based on the object-oriented environment the modeling methodology exploits inheritance of basic classes AtomicModel and CoupledModel provided by AgentSim.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.413-420
• /
• 2005

In this paper, we apply software agents, which use fuzzy logic and make autonomous decisions according to state transitions, to car driving environment. We carry out an experiment on artificial intelligent car driving in terms of real-time reactive agents. Inference techniques for constructing real-time reactive agents consider the settings with max-product inference, n-fuzzy rules, and n-associatives ($A_l,\;B_l),\;{\ldots}(A_n,\;B_n$). Then we perform defuzzification processes, extract a central value, and work out inference processes.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.760-767
• /
• 2011

The flexibility and evolvability are critical characteristics of modern manufacturing to adapt to changes from products and disturbances in the shop floor. The technologies inspired from biology and nature enable to equip the manufacturing systems with these characteristics. This paper proposes an ant colony inspired autonomous manufacturing system in which the resources on the shop floor are considered as the autonomous entities. Each entity overcomes the disturbance by itself or negotiates with the others. The swarm of cognitive agents with the ant-like pheromone based negotiation mechanism is proposed for controlling the shop floor. The functionality of the developed system is proven on the test bed.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1998.10a
• /
• pp.124-127
• /
• 1998

One of the eventual goals of VR research is to provide valuable experiences to the participants. In this work, we view that the content of experience is composed of a sequence of events, and develop algorithms authoring those events. Event authoring can be realized by controlling agents in VE in two different modes: (1) the autonomous mode, in which the agent exhibit autonomous behaviors based on the current world status and its own personality, and (2) the event mode, in which the behaviors generated form the autonomous mode is further controlled to meet the needs of the experiment. We define the event authoring language, so that the authors can design experiments by writing event-programs. Then the architecture of event execution manager is described, which is the heart of event-program execution. prove the effectiveness of our approach by showing results of several experiments.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.5 no.4
• /
• pp.243-248
• /
• 2005

The UAV (Unmanned Aerial Vehicle) systems like unmanned autonomous helicopters are used in various missions of flight navigation and used to collect the environmental information of the surroundings. To realize the full functionalities of the UAV, the software part becomes a challenging problem. In this paper embedded real-time software architecture for unmanned autonomous helicopter is proposed that guarantee real-time performance of hard-real time tasks and re-configurability of soft-real time and non-real time tasks. The proposed software architecture has four layers: hardware, execution, service agent and remote user interface layer according to the reactiveness level for external events. In addition, the layered separation of concurrent tasks makes different kinds of mission reconfiguration possible in the system. An Unmanned autonomous helicopter system was implemented (Kyosho RC Helicopter) in our lab to test and evaluate the performance of the proposed system.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.572-575
• /
• 2004

Since the 1990s, the advancement of semiconductor technology has resulted in the development of microprocessor technology, auxiliary computer technology, and application technology such as intelligent algorithms (neural network, fuzzy, etc.). These based the development of intelligent machines. An agent is autonomous software that recognizes environment, exchanges knowledge with other agents and makes decisions. We designed agent-based sensor structure. For the purpose, first, it modeled the function of an intelligent machine. Second, it designed sensory function on the agent level.

• Korean journal of aerospace and environmental medicine
• /
• v.31 no.2
• /
• pp.33-37
• /
• 2021

In the era of the 4th industrial revolution, the aviation industry is also growing remarkably with the development of artificial intelligence and networks, so it is necessary to study a new concept of crew resource management (CRM), which is required in the process of operating state-of-the-art equipment. The automation system, which has been treated only as a tool, is changing its role as a decision-making agent with the development of artificial intelligence, and it is necessary to set clear standards for the role and responsibility in the safety-critical field. We present a new perspective on the automation system in the CRM program through the understanding of the autonomous system. In the future, autonomous system will develop as an agent for human pilots to cooperate, and accordingly, changes in role division and reorganization of regulations are required.