• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.6A
• /
• pp.989-997
• /
• 2001

인터넷 시장규모 확대 및 이용환경의 급속한 변화로 인하여 인터넷 이용자에 관한 통계와 인터넷 환경에 관한 통계정보 요구는 증대되고 있다. 그러나 인터넷 환경에 관한 통계 정보 중에서 국내 호스트개수, 홈페이지 개수, 국제도메인의 국내 보유 개수 산출 등은 인터넷에 연결하는 이용기관의 보안 강화의 문제점과 전문 지능형 로봇에이전트 시스템의 부재 및 국제도메인 등록기관의 통계 비공개 등으로 국내에서 주기적으로 산출하는데 문제점이 부각되고 있다. 본 논문에서는 인터넷 관련 주요 통계정보의 정확한 산출·제시로 민간의 인터넷 산업에 대한 효과적인 투자 유도를 가능케 하기 위해서 인터넷 주요 통계 산출이 가능한 로봇에이전트 설계 기법을 제안하고 구현한다. 모듈은 로봇에이전트 프로세스 모듈, 통계산출 모듈, 관리 모듈 등으로 구성되었으며, 국내의 호스트 개수, 홈페이지 개수, .com 등 국제도메인의 국내 보유 개수 등을 정기적으로 산출되기 위한 알고리즘과 그 구현결과를 제시한다.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3016-3018
• /
• 2000

생명체는 자신을 이루고 있는 단순한 구성요소들이 적은 수의 근본 규칙들에 의하여 국부적 상호작용을 함으로써 복잡한 생명 현상을 보이고있다. 이 연구에서는 생명 현상을 보이고 있는 개체가 많은 수의 단순한 구성 요소들의 집합으로 이루어져 있으며 그러한 구성 요소들이 적은 수의 근본 규칙들에 의하여 서로 국부적인 상호작용을 함으로써 복잡한 행동패턴들을 나타낸다는 가정 아래, 여러 대의 자율이동로봇 (autonomous mobile robot)들의 군지능을 나타낼 수 있는 적은 수의 근본 규칙을 찾아내고 찾아진 근본규칙들을 퍼지규칙으로 표현하는 것을 목표로 한다. 각 자율 이동로봇은 기능이 매우 제한되어 있으며. 자신만의 독특한 신호를 발생한다 이신호를 "heartbeat"이라 부르며 이를 이용하여 대략적으로 자신의 위치와 현재상태를 다른 개체에게 알리는 역할을 한다. 이 논문에서는 "heartbeat"을 이용한 로봇간의 통신과 자재반송이라는 군행동을 퍼지시스템으로 구현하고 이를 평가한다.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2930-2932
• /
• 2000

In this paper. a robust gesture recognition system is designed and implemented to explore the communication methods between human and computer. Hand gestures in the proposed approach are used to communicate with a computer for actions of a high degree of freedom. The user does not need to wear any cumbersome devices like cyber-gloves. No assumption is made on whether the user is wearing any ornaments and whether the user is using the left or right hand gestures. Image segmentation based upon the skin-color and a shape analysis based upon the invariant moments are combined. The features are extracted and used for input vectors to a radial basis function networks(RBFN). Our "Puppy" robot is employed as a testbed. Preliminary results on a set of gestures show recognition rates of about 87% on the a real-time implementation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.2
• /
• pp.209-214
• /
• 1998

In this paper, we are dealing with the problem of controlling unknown nonlinear dynamical system by using neural networks. A novel error self-recurrent(ESR) neural model is presented to perform black-box identification. Through the various outcome of the experiment, a new neural network is seen to be considerably faster than the BP algorithm and has advantages of being less affected by poor initial weights and learning rate. These characteristics make it flexible to design the controller in real-time based on neural networks model. In addition, we design an adaptive PID controller that Keyser suggested by using ESR neural networks, and present a method on the implementation of adaptive controller based on neural network for practical applications. We obtained good results in the case of robot manipulator experiment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.12
• /
• pp.993-1000
• /
• 2001

Configuration-dependent nonlinear coefficient matrices in the dynamic equation of robot manipulator impose computa- tional burden in real-time implementation of tracking control based on the inverse dynamics controller. However, parallel manipulators such as Stewart platform have relatively small workspace compared to serial manipulators. Based on the characteristics of small motion range. nonlinear coefficient matrices can be approxiamted to constant ones. The modeling errors caused by such approximation are compensated for by H-infinity controller that treats the modeling errors disturbance. The proposed inverse dynamics controller with approximate dynamics combined with H-infinity control shows good tracking performance even for fast tracking control in which computation of full inverse dynamics is not easy to implement.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2362-2364
• /
• 2003

In this paper, behaviors performing controls of a mobile robots are designed based on the concept of closed-loop controls. A control architecture, in which the behaviors coordinate concurrently with one others to achieve a task is also proposed. In the control architecture, task manager allocates valid resources and configures the weight of the behavior outputs to achieve the task. For practical implementation, a rate modulation strategy based on RMS(Rate Modulation Strategy) is proposed for efficient resource allocations. The rate modulation strategy is performed with considering control stability. The efficiency of the proposed rate modulation strategy is validated through simulation tests.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.369-372
• /
• 1993

In this thesis, we consider an iterative learning controller to control the continuous trajectory of 2 links direct drive robot manipulator and process computer simulation and real-time experiment. To improve control performance, we adapt an iterative learning control algorithm, drive a sufficient condition for convergence from which is drived extended conventional control algorithm and get better performance by extended learning control algorithm than that by conventional algorithm from simulation results. Also, experimental results show that better performance is taken by extended learning algorithm.

• The Journal of Korea Robotics Society
• /
• v.10 no.2
• /
• pp.90-95
• /
• 2015

The main goal of e-learning systems is just-in-time knowledge acquisition. Rule-based e-learning systems, however, suffer from the mesa effect and the cold start problem, which both result in low user acceptance. E-learning systems suffer a further drawback in rendering the implementation of a natural interface in humanoids difficult. To address these concerns, even exceptional questions of the learner must be answerable. This paper aims to propose a method that can understand the learner's verbal cues and then intelligently explore additional domains of knowledge based on crowd data sources such as Wikipedia and social media, ultimately allowing for better answers in real-time. A prototype system was implemented using the NAO platform.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.3
• /
• pp.43-49
• /
• 2013

Recently harmonics flowing into power system is increasing as the usage of semiconductor equipments and switching mode power equipments are increasing. Harmonics cause problems such as heat increasing and reduction in capacity of transformers, especially the harmonics flowing into a distribution transformer can lead to the lifetime reduction of transformer. In this paper, we are about to develop a device that can monitor harmonics in real-time as it is affixed to a distribution transformer. Unlike the existing expensive harmonic analysis device, a new harmonic analysis algorithm is proposed in order to implement low-cost equipment. The real-time harmonic analysis algorithm proposed in this paper allows implementation on low performance microcontrollers, thus it can monitor the harmonic in real-time as it is individually affixed to the transformer. Therefore, it would improve the reliability of the transformer and stable power system operation would be possible as it can prevent the transformer accidents in advance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.319-323
• /
• 2007

현재 일반적으로 사용되고 있는 저가형 청소 로봇은 환경 지도를 사용하지 않기 때문에 주행시 문제가 발생하고 이런 이유로 청소 효율이 좋지 않다. 본 논문에서는 환경 지도를 사용하는 고가의 청소 로봇처럼 동작하는 저가의 청소 로봇을 하드웨어 부분과 알고리즘 부분으로 나누어 제안한다. 제안하는 청소 로봇은 확장된 그리드 기반의 지도를 사용하여 청소를 수행한다. 본 논문에서 제안하는 로봇을 제작하여 실험한 결과는 기존의 저가형 청소 로봇에 비해 제안한 청소 로봇이 효율적임을 보여주고 있다.