• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2011년도 제42회 하계학술대회
• /
• pp.280-281
• /
• 2011

Special Protection Scheme(SPS) that operates scenarios about faults beyond the normally protective action is wide system protection technology for the purpose of wide areas protection. Therefore, the SPS focuses on the improvement of the power supply capability by protecting the system rather than protecting the system equipments. Since the SPS requires emergency operation, the operation schedule is set up in advance by analyzing various scenarios. Since the SPS's action scheme uses generator tripping and is a classical method it is presently the most powerful one. However, as the setting of SPS is set to the most severe disturbance, the scheme tends to trip more generators than required to prevent fault propagation. It is highly likely that tripping generator units to prevent fault propagation would result in difficulty of system management and possibility of load shedding. Accordingly, it is desirable that generators are connected to the system within the range that ensures system stability and intelligent SPS is currently under development to solve the problem being stated. In this paper, as a part of developing the intelligent SPS, application of the fast-valving and braking resistor scheme to the generators is being proposed and analysed to reduce the number of tripped generators.

• 제어로봇시스템학회논문지
• /
• 제10권9호
• /
• pp.825-832
• /
• 2004

A small biped robot system is designed and implemented. The robot system consists of a mechanical robot body, a control system, a sensor system, and a user interface system. The robot has 12 dofs for two legs, 6 dofs for two arms, 2 dofs for a neck, so it has total 20 dofs to have dexterous motion capability. The implemented robot has the capability of performing intelligent actions such as playing soccer, resisting external forces, and walking on a slope terrain. In this paper, we focus on the robot's capability of playing soccer. The robot uses a color CCD camera attached on its head as a sensor for playing soccer. To make the robot play soccer with only one camera, an algorithm, which consists of searching, localization, and motion planning, is proposed and experimented. The results show that the robot can play soccer successfully in the given environments.

• 정보처리학회논문지B
• /
• 제12B권3호
• /
• pp.329-336
• /
• 2005

본 논문에서는 유전자 알고리즘을 이용하여 대전형 액션 게임의 캐릭터를 지능화 하는 방법을 제안한다. 초기에 게임 규칙을 전혀 모르는 캐릭터가 학습이 진행되면 세대를 거듭하면서 스스로 게임규칙을 학습하고 기술을 습득하며 진화할 수 있는 지능을 갖추게 된다. 제안한 캐릭터가 환경변화에 잘 적응하는지를 평가하기 위하여 게임 도중에 게임규칙을 바꾸어 규칙 변경 전후의 결과를 비교 검토하였다. 실험결과 게임규칙이 변경된 후에도 빠르게 새로운 규칙에 적응하였다. 본 논문에서 제안한 방법은 대전형 액션게임뿐만 아니라 PC게임이나 인터넷 온라인 게임 등의 캐릭터 구현에도 쉽게 적용가능한 장점이 있다.

• 정보처리학회논문지B
• /
• 제10B권7호
• /
• pp.795-802
• /
• 2003

로봇이나 가상 캐릭터와 같은 지능형 에이전트가 자율적으로 살아가기 위해서는 주어진 환경을 인식하고, 그에 맞는 최적의 행동을 선택하는 능력을 가지고 있어야 한다. 본 논문은 이러한 지능형 에이전트를 구현하기 위하여, 외부 환경에 적응하면서 최적의 행동을 배우고 선택하는 방법을 연구하였다. 본 논문에서 제안한 방식은 강화 학습을 이용한 행동기반 학습 방법과 기호 학습을 이용한 인지 학습 방법을 통합한 방식으로 다음과 같은 특징을 가진다. 첫째, 강화 학습을 이용하여 환경에 대한 적응성을 학습함으로 지능형 에이전트가 변화하는 환경에 대한 유연성을 가지도록 하였다. 둘째, 귀납적 기계학습과 연관 규칙을 이용하여 규칙을 추출하여 에이전트의 목적에 맞는 환경 요인을 학습함으로 주어진 환경에서 보다 빠르게, 확장된 환경에서 보다 효율적으로 행동을 선택을 하도록 하였다. 셋째, 본 논문은 지능형 에이전트를 구현하는데 있어서 처음부터 모든 상태를 고려하기 보다 상태 탐지기를 이용하여 새로운 상태가 입력될 때마다 상태를 확장시키는 방식을 이용하였다. 이러한 방식은 필요한 상태에 대하여서만 고려함으로 메모리를 획기적으로 축소 할 수 있으며, 새로운 상태를 동적으로 처리 할 수 있어, 환경에 대한 변화에 능동적으로 대처 할 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2568-2574
• /
• 2005

Control architecture of the action based robot engineering can be divided into two types of deliberate type - and reactive type- controller. Typical deliberate type, slow in reaction speed, is well suited for the realization of the higher intelligence with its capability to forecast on the basis of environmental model according to time flow, while reactive type is suitable for the lower intelligence as it fits to the realization of speedy reactive action by inputting the sensor without a complete environmental model. Looking at the environments in the application areas in which robots are actually used, we can see that they have been mostly covered by the uncertain and unknown dynamic changes depending on time and place, the previously known knowledge being existed though. It may cause, therefore, any deterioration of the robot performance as well as further happen such cases as the robots can not carry out their desired performances, when any one of these two types is solely engaged. Accordingly this paper aims at suggesting Goal-oriented Geometric Model(GGM) Based Intelligent System Architecture which leads the actions of the robots to perform their jobs under variously changing environment and applying the suggested system structure to the navigation issues of the robots. When the robots do perform navigation in human life changing in a various manner with time, they can appropriately respond to the changing environment by doing the action with the recognition of the state. Extending this concept to cover the highest hierarchy without sticking only to the actions of the robots can lead us to apply to the algorithm to perform various small jobs required for the carrying-out of a large main job.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.496-498
• /
• 2004

An action-selection-mechanism is proposed to deal with sequential behaviors, where associations between some of stimulus and behaviors will be learned by a shortest-path-finding-based reinforcement team ins technique. To be specific, we define behavioral motivation as a primitive node for action selection, and then sequentially construct a network with behavioral motivations. The vertical path of the network represents a behavioral sequence. Here, such a tree fur our proposed ASM can be newly generated and/or updated. whenever a new sequential behaviors is learned. To show the validity of our proposed ASM, some experimental results on a "pushing-box-into-a-goal task" of a mobile robot will be illustrated.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1049-1058
• /
• 2022

HAR(Human Action Recognition) such as anomaly and object detection has become a trend in research field(s) that focus on utilizing Artificial Intelligence (AI) methods to analyze patterns of human action in crime-ridden area(s), media services, and industrial facilities. Especially, in real-time system(s) using video streaming data, HAR has become a more important AI-based research field in application development and many different research fields using HAR have currently been developed and improved. In this paper, we propose and analyze a deep-learning-based HAR that provides more efficient scheme(s) using an intelligent AI models, such system can be applied to media services using RGB video streaming data usage without feature extraction pre-processing. For the method, we adopt Slowfast based on the Deep Neural Network(DNN) model under an open dataset(HMDB-51 or UCF101) for improvement in prediction accuracy.

• 한국발생생물학회:학술대회논문집
• /
• 한국발생생물학회 2005년도 제20차 학술대회 논문집
• /
• pp.35-35
• /
• 2005

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.217-220
• /
• 2004

Controller that is designed in this paper is form that apply PID controller about Fuzzy algorithm. Fuzzy Controller that using this paper is can speak that compensation style fuzzy controller as form to solidify action of PID controller for plant. This is not form that autotuning the each PID coefficient. We Apply and examined the response character to AGC(Automatic Generation Control) system using designed controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.1091-1096
• /
• 1989

All mechanical systems have saturation nonlinearity in actuators or in final control elements. When controllers have integral action, reset windup can cause instability as well as make the system performance unsatisfactory. In this study, an intelligent limiter which needs no tuning of parameters is tested with the PDF controller used for control of a second order plant. This paper presents analysis of the stability of the system using the describing function method and the Nyquist stability theorem. The improvement of the system performance by the limiter is illustrated by computer simulations.