• Journal of Electrical Engineering and Technology
• /
• v.6 no.1
• /
• pp.139-146
• /
• 2011

This paper presents a new modified Contract Net Protocol (CNP) for microgrid operation based on multiagent system. The CNP is a widely used protocol for interactions among distributed problem solving. The Contract Net Interaction Protocol of the Foundation for Intelligent Physical Agents (FIPA-CNIP) is a minor modification of the original CNP for multiagent system applications. In this paper, a modified CNP (MCNP) based on the FIPA-CNIP is proposed for more specialized interactions among agents for microgrid operation. A multiagent system is designed and constructed for microgrid operation. A microgrid operation based on the multiagent system is tested to check the functionality of the proposed MCNP.

• 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
• /
• 2007.06c
• /
• pp.309-312
• /
• 2007

최근 시뮬레이션의 분야에 인공지능의 요소가 적용된 연구가 진행되고 있다. 본 연구에서는 다양한 인공지능의 기법들 중에서 FSM을 기반으로 한 자율적 에이전트를 설계하고 이를 핑-퐁 게임에 적용시켜 실험하였다. 이러한 FSM 기반의 에이전트를 이용하게 되면 모델 설계가 용이하며, 시스템을 구성하고 있는 모든 에이전트들의 상태를 쉽게 확인 할 수 있고, 시뮬레이션 모델설계를 단순화할 수 있는 장점이 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• Journal of Power System Engineering
• /
• v.4 no.4
• /
• pp.92-98
• /
• 2000

Modern manufacturing systems should cope with the frequent changes in a product model and disturbances in manufacturing process. The control system of such systems must cover a constant adaptation and high flexibility. Holonic Flexible Manufacturing Cell(HFMC) is introduced to handle these issues more successfully. It is based on the concept of autonomous co-operating agent, called 'Holon', which is a building block of a manufacturing system for transforming, transporting, storing and/or validating information and physical objects. In this paper the basic structure of the HFMC is represented by using Unified Modeling Language and Open architecture cell controller is developed for effective integration components of a manufacturing system. Also a new control model, called MuLOM(Multi-Layered Operation Model), is suggested to represent the control behaviour for a holonic flexible manufacturing cell control system.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.4
• /
• pp.333-338
• /
• 2005

This paper presents the target object search algorithm under Dynamic Programming (DP) in the Tree-type maze. We organized an experimental environment with the concatenation of Y-shape diverged way, small mobile robot, and a target object. By the principle of optimality, the backbone of DP, an agent recognizes that a given whole problem can be solved whether the values of the best solution of certain ancillary problem can be determined according to the principle of optimality. In experiment, we used two different control algorithms: a left-handed method and DP. Finally we verified the efficiency of DP in the practical application using our real robot.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.40-42
• /
• 2003

주어진 실시간 환경의 복잡성 때문에. 항상 최적의 행동을 수행하는 완벽하게 이성적인 에이전트 (rational agent) 의 구현은 실질적으로 가능하지 않다. 이러한 실시간 문제 해결기법에서의 전통적인 접근 방식은 미리 정의된 규약에 의존한 조건-행동 추론 방식이다. 이러한 조건-행동추론 방식은 문제 영역이 다양하거나 문제의 재설계가 필요한 경우에는 아무런 해법을 갖지 못한다. 따라서 이러한 문제점을 해결하기 위해 본 논문에서는 주어진 행동들의 유틸리티를 실시간에 계산하고, 긴급한 정도를 측정하여 상황이 긴급할 경우에는 더 이상의 계산을 중단하고 즉각적인 행동을 취하며. 반면에 상황이 긴급하지 않을 경우에는 최선의 의사결정을 위하여 추가적인 정보를 고려하여 더 바람직한 행동을 결정하는 방법론을 제안한다. 제안한 방법론의 평가를 위하여 시간 제약적인 환경에서 최선의 의사결정을 수행하는 실질적이며 유연한 에이전트를 구현 하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.47-49
• /
• 2022

Robot navigation has seen a major improvement since the the rediscovery of the potential of Artificial Intelligence (AI) and the attention it has garnered in research circles. A notable achievement in the area was Deep Learning (DL) application in computer vision with outstanding daily life applications such as face-recognition, object detection, and more. However, robotics in general still depend on human inputs in certain areas such as localization, navigation, etc. In this paper, we propose a study case of robot navigation based on deep reinforcement technology. We look into the benefits of switching from traditional ROS-based navigation algorithms towards machine learning approaches and methods. We describe the state-of-the-art technology by introducing the concepts of Reinforcement Learning (RL), Deep Learning (DL) and DRL before before focusing on visual navigation based on DRL. The case study preludes further real life deployment in which mobile navigational agent learns to navigate unbeknownst areas.

• Journal of KIISE:Software and Applications
• /
• v.29 no.6
• /
• pp.377-385
• /
• 2002

An authentic simulation platform for events situated in spatio-temporal space is presented. The authenticity, i.e., logical fidelity to the reality, of this cyberspace is realized by maximizing the diversity and unpredictability of events occurring therein. The knowledge components and associated schemes required for the simulation of events situated in spatio-temporal space encompass the environmental factors, the objects, the events, and their interrelations. We deviled event activation, triggering mechanism, and cognitive function related to event to realize an authentic simulation of discretionary events. The agents in this simulation environments are autonomous in that they have their own existence and capability of event planning. We focused on identifying basic constructs relevant to authentic simulation of discretionary events whose initiation depends on human intention. Several key ideas are implemented in a typical spatio-temporal situation to demonstrate the viability of our simulation mechanism.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.15 no.1
• /
• pp.62-70
• /
• 2019

The APR1400 reactor may be operated for a long time under high temperature and pressure conditions, causing damage to the stud holes and causing stud bolts and holes to stick. The present practice is to manually remove the anti-sticking agent and foreign matter remaining in the APR1400 reactor stud hole and to visually check the surface condition of the thread to check the damage status of the threads. In the case of the APR1400 reactor stud holes, manually cleaning the threads increases the risk of radiation exposure and operator's fatigue. To avoid this, the autonomous mobile robot is used to automatically clean the reactor stud holes. The purpose of this study is to optimize the cleaning performance of the mobile robot by looking at the behavior of the surface roughness of the stud surface cleaned by the brush attached to the mobile robot due to changes in brush material, thickness of wire, and rotation speed. A microscopic approach to the surface roughness of the flank is needed to investigate the effects of the newly proposed brush of the autonomous mobile robot on the thread holes. According to this experiment, it is reasonable to use STS brush rather than Carbon one. Optimal operating conditions are derived and the safety of APR1400 reactor stud holes maintenance can be improved.