• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.329-333
• /
• 2003

최근 전문가의 지식과 경험정보가 데이터베이스로 구축된 전문가 시스템의 지식 정보를 이용하여 안전하고 효율적인 선박운항이 가능한 지능형 선박 시스템에 관한 연구가 활발하게 진행되고 있다. 인공지능기법을 이용하여 보다 인간 친화적인 시스템을 구현하고, 음성인식기술을 이용하여 원격으로 선박 조타기를 제어하여 조업자의 부담경감 및 인원절감의 효과를 가져올 수 있는 선박 조종시스템의 개발이 절실하다. 따라서, 본 논문에서는 PC를 기반으로 하여 일격으로 모형 선박의 조타기를 제어하는 시스템을 구축한다. 구체적인 연구방법으로는, 음성인식기술과 지능형 학습 기법을 바탕으로 음성지시기반학습 시스템을 구축하고, 퍼지 조타수 조작모델을 구현하여 PC 기반 원격 제어시스템을 구축한다. 또한, 구축된 원격 조타제어시스템을 축소된 선박모형(Miniature Ship) 시스템에 적용하여 그 효용성을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.14-15
• /
• 2021

물리 시뮬레이션 기반의 캐릭터 동작 제어 문제를 강화학습을 이용하여 해결해 나가는 연구들이 계속해서 진행되고 있다. 이에 따라 이 문제를 강화학습을 이용하여 풀 때, 영향을 미치는 요소에 대한 연구도 계속해서 진행되고 있다. 우리는 지금까지 이뤄지지 않았던 상태 표현 방식에 따른 강화학습에 미치는 영향을 분석하였다. 첫째로, root attached frame, root aligned frame, projected aligned frame 3 가지 좌표계를 정의하였고, 이에 대해 표현된 상태를 이용하여 강화학습에 미치는 영향을 분석하였다. 둘째로, 동역학적 상태를 나타내는 캐릭터 관절의 위치, 각도에 따라 학습에 어떠한 영향을 미치는지 분석하였다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.3
• /
• pp.27-38
• /
• 2000

This paper proposes how the recurrent neural network controller for a Khepera mobile robot with an obstacle avoiding ability can be determined by co-adaptation of the evolution and learning, The proposed co-adaptation scheme consists of two folds： a population of NN controllers are evolved by the genetic algorithm so that the degree of obstacle avoidance might be reduced through the global searching and each NN controller is trained by CRBP learning so that the running behavior is adapted to its outer environment through the local searching. Experimental results shows that the NN controller coadapted by evolution and learning outperforms its non-learning equivalent evolved by only genetic algorithm in both the ability of obstacle avoidance and the convergence speed reaching to the required running behavior.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.503-509
• /
• 2014

In this paper, a PID controller with adaptive neural network compensator is proposed to control the formations of mobile robot. The control system is composed of a kinematic controller based on the leader-following robot and dynamic controller for considering the dynamics of the mobile robot. The dynamic controller is constituted by a PID controller and the adaptive neural network compensator for improving the performance and compensating the change in dynamic characteristics. Simulation results show the performance of the PID controller and the neural network compensator for the circular trajectory and linear trajectory. And it is verified that by improving the performance of a PID controller via the adaptive neural network compensator, the following robot's tracking performance is improved.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.3
• /
• pp.173-183
• /
• 1998

In this paper, an auto-tuning method for fuzzy controller's membership functions based on the neural network is presented. The neural network emulator offers the path which reforms the fuzzy controller's membership functions and fuzzy rule, and the reformed fuzzy controller uses for speed control of induction motor. Thus, in the case of motor parameter variation, the proposed method is superior to a conventional method in the respect of operation time and system performance. 32bit micro-processor DSP(TMS320C31) is used to achieve the high speed calculation of the space voltage vector PWM and to build the self-learning fuzzy control algorithm. Through computer simulation and experimental results, it is confirmed that the proposed method can provide more improved control performance than that PI controller and conventional fuzzy controller.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1679-1687
• /
• 2016

Mobile robots are effectively used in industrial fields that require flexible manufacturing systems. Mobile robots have to move with mechanical loads such as product parts along the specified paths, and are usually equipped with kinematic controllers. When the loads and nonlinear frictions are too high, satisfactory control performances can not be expected with the kinematic controllers, so some dynamic controllers have been developed. Conventional dynamic controllers require the exact weights and locations of the loads; however, the loads are frequently changed and unknown so that the control performances of the conventional controllers are limited. This paper proposes an adaptive PD control method using gradient descent learning to have sufficient dynamic control performance for unknown loads. Simulation studies have been conducted for various load conditions to verify that the adaptive PD control method have much broader convergence region than the convention method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.4
• /
• pp.49-60
• /
• 1996

The objective of this paper is to develop an adaptive learning method for fuzzy hypercubes using a neural network. An intelligent control system is proposed by exploiting only the merits of a fuzzy logic controller and a neural network, assuming that we can modify in real time the consequential parts of the rulebase with adaptive learning, and that initial fuzzy control rules are established in a temporarily stable region. We choose the structure of fuzzy hypercubes for the fuzzy controller, and utilize the Perceptron learning rule in order to upda1.e the fuzzy control ru1c:s on-line with the output errors. As a result, the effectiveness and the robustness of this intelligent controller are shown with application of the proposed adaptive fuzzy-neuro controller to control of the cart-pole system.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.11
• /
• pp.1423-1428
• /
• 2011

This paper proposes a learning input shaper with nonlinear actuator dynamics to reduce the residual vibration of flexible systems. The controller is composed of an estimator of the time constant of the nonlinear actuator dynamics, a recursive least squares method, and an iterative updating algorithm. The updating mechanism is modified by introducing a vibration measurement function to cope with the dynamics of nonlinear actuators. The controller is numerically evaluated with respect to parameter convergence and control performance by using a benchmark pendulum system. The feasibility and applicability of the controller are demonstrated by comparing its control performance to that of an existing controller algorithm.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.6 no.3
• /
• pp.273-281
• /
• 2001

In this paper, we propose a CMAC(Cerebellar Model Articulation Controller) neural network for controlling a non-linear system. CMAC is a neural network that models the human cerebellum. CMAC uses a table look-up method to resolve the complex non-linear system instead of numerical calculation method. It is very fast learn compared with other neural networks. It does not need a calculation time to generate control signals. The simulation results show that the proposed CMAC controllers for a simple non-linear function and a DC Motor speed control reduce tracking errors and improve the stability of its learning controllers. The validity of the proposed CMAC controller is also proved by the real-time tension control.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.257-260
• /
• 2001

일반적으로 기계학습은 교사신호의 유무에 따라 교사학습과 비교사학습, 그리고 간접교사에 의한 강화학습으로 분류할 수 있다. 강화학습이란 용어는 원래 실험 심리학에서 동물의 학습방법 연구에서 비롯되었으나, 최근에는 공학 특히 인공생명분야에서 뉴럴 네트워크의 학습 알고리즘으로 많은 관심을 끌고 있다. 강화학습은 제어기 또는 에이전트의 행동에 대한 보상을 최대화하는 상태-행동 규칙이나 행동발생 전략을 찾아내는 것이다. 본 논문에서는 최근 많이 연구되고 있는 강화학습의 방법과 연구동향을 소개하고, 특히 인공생명 연구에 있어서 강하학습의 중요성을 역설한다.