• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.329-342
• /
• 2001

기존의 유로도로와 유료터널의 톨게이트에서 정체로 인한 개선방안이 시급히 요구되어 진다. 이에 대해 차량속도를 향상시키며 평균차량 대기시간을 줄이는 새로운 요금정산 방법인 진자자동 요금징수 시스템에 대해 기술하였다. 유로도로를 통과시 차량당 요금정산을 위해 평균대기 시간이 길어짐으로 인해 공해, 유류 낭비 뿐만 아니라 과다한 물류비로 인해 국가적으로 손실이 엄청 크다. 이에 대해 기능이 향상되고 보안성이 뛰어난 Off-Line의 상거래 처리가 가능한, 비접촉식 IC 카드를 대상으로 게이트 리더기와 원격정보 수집장치로 구성으로 설계 및 제작을 하였다. 기존의 방식보다 차량대기속도 및 평균주행속도가 15%에서 40% 가량 개선됨을 확인할 수가 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.371-371
• /
• 2000

A strategy for the swing-up control according to states of the 2-link rotational pendulum is proposed. The proposed controller consists of two modes of control such as divergence mode and stabilization mode. When the controller is in divergence mode, control input is generated using sinusoidal and signum function to make the first and second links reach the bottom and top positions, respectively. After the controller finishes divergence mode, stabilization mode is initiated to keep the pendulum around the top position using pole-placement method. Dynamic models including actuator dynamics are obtained using coordinate changes at each control mode. Simulation results are given to show the effectiveness of the proposed method.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.9-10
• /
• 2016

본 논문에서는 의료기관에서 수진자의 검사정보를 검사기관과 1:1 계약이 아닌 다양한 검사기관으로 위탁 의뢰 할 수 있고, 검사의뢰나 검사결과 보고만을 하는 기존 검사관리 시스템과는 달리 검사결과 정보를 바탕으로 한 다양한 부가서비스를 제공할 수 있는 통합 검사관리 서비스 플랫폼을 제안한다. 본 논문에서 제안하는 서비스 플랫폼은 다양한 의료기관과 검사기관을 하나의 통합 검사관리 시스템에 연결, 병 의원 업무의 효율성 및 서비스 질 향상을 지원한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.6
• /
• pp.548-553
• /
• 2008

In this paper, we propose a new swing-up control strategy for rotary inverted pendulums with restricted rotation range. The control law is derived from a Lyapunov function. The Lyapunov function is defined as the square of the sum of the absolute value of the total mechanical energy and weighted squares of the arm's angular displacement and velocity. By adjusting the weighting parameters in the Lyapunov function, we can affect the swing-up strategy such that the restriction on rotation range can be satisfied. Finally, we verify the performance of the proposed control law through simulation and experiments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.8
• /
• pp.623-631
• /
• 2003

We have fabricated the two-dimensional inverted pendulum system and designed its controller. The two-dimensional inverted pendulum system, which is composed of X-Y table, is actuated through timing belt by each of two geared DC motors. And the control goal is that the rod is always kept to a vertical position to any distrubance and is quickly moved to the desired position. Because this system has generally nonlinear dynamic characteristics and X-axis and Y-axis move together, it is very difficult to find its exact mathematical model and to design its controller. Therefore, we have designed the PID controller with simple structure and excellent performance. Genetic algorithm(GA), which is blown as one of probabilistic searching methods, and human's heuristic control strategy are introduced to design an optimal PID controller. The usefulness of the proposed GA based PID coefficient searching technique is verified through the experiments and computer simulations.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.3
• /
• pp.157-163
• /
• 2000

In this paper, an Evolving Neural Network Controller(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algoithm(RVEGA) was presented for stabilization of an Inverter Pendulum(IP) system with nonlinearity. This proposed ENNC was described by a simple genetic chromosome. And the deletion of neuron, the determinations of input or output neuron, the deleted neuron and the activation functions types are given according to the various flag types. Therefore, the connection weights, its structure and the neuron types in the given ENNC can be optimized by the proposed evolution strategy. Through the simulations, we showed that the finally acquired optimal ENNC was successfully applied to the stabilization control of an IP system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.705-707
• /
• 2018

Rotary Inverted Pendulum 은 제어분야에서 비선형 제어 시스템을 설명하기 위해 자주 사용되어왔다. 본 논문은 강화학습 에이전트의 환경으로써 Rotary Inverted Pendulum 을 도입하였다. 이를 통해서 강화학습이 실제 세계에서의 복합적인 문제를 해결할 수 있음을 보인다. 강화학습 에이전트의 가상 환경과 실제 환경을 맵핑시키기 위해서 Ethernet 연결 위에 MQTT 프로토콜을 사용하였으며 이를 통해서 경량화된 IoT 분야에서의 강화학습의 활용도를 조명한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.493-495
• /
• 2019

제어 분야의 가장 기초적인 시스템인 Rotary Inverted Pendulum 을 제어하기 위하여, 본 논문에서는 강화학습에서 Deep Q-Network 과 함께 대표적인 알고리즘으로 알려진 Asynchronous Advantage Actor-Critic 을 활용하여 다중 디바이스 제어를 설계한다. Deep Q-Network 알고리즘을 활용한 기존 연구와 동일한 방식으로 실 세계의 물리 에이전트와 가상 환경을 맵핑시키며, 스위치를 통하여 로컬 에이전트와 글로벌 네트워크 간 통신을 구성한다. 본 논문에서는 분산 Asynchronous Advantage Actor-Critic 을 이용함으로써 실 세계의 다중 에이전트 제어를 위한 강화 학습의 활용 가능성을 조명한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.652-658
• /
• 2010

This paper presents the implementation and control of a two wheeled mobile robot(TWMR) based on a balancing mechanism. The TWMR is a mobile inverted pendulum structure that combines an inverted pendulum system and a mobile robot system with two arms instead of a rod. To improve robustness due to disturbances, the radial basis function (RBF) network is used to control an angle and a position at the same time. The reference compensation technique(RCT) is used as a neural control method. Experimental studies are conducted to demonstrate performance of neural network controllers. The robot are implemented with the remote control capability.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.527-532
• /
• 2005

In this paper, we proposed an adaptive fuzzy sliding control for unknown nonlinear systems using estimation of bounds for approximation errors. Unknown nonlinearity of a system is approximated by the fuzzy logic system with a set of IF-THEN rules whose consequence parameters are adjusted on-line according to adaptive algorithms for the purpose of controlling the output of the nonlinear system to track a desired output. Also, using assumption that the approximation errors satisfy certain bounding conditions, we proposed the estimation algorithms of approximation errors by Lyapunov synthesis methods. The overall control system guarantees that the tracking error asymptotically converges to zero and that all signals involved in controller are uniformly bounded. The good performance of the proposed adaptive fuzzy sliding mode controller is verified through computer simulations on an inverted pendulum system.