• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.163-168
• /
• 2002

The voting algorithm for action selection performs self-improvement by Reinforcement learning algorithm in the dynamic environment. The proposed voting algorithm improves the navigation of the robot by adapting the eligibility of the behaviors and determining the Command Set Generator (CGS). The Navigator that using a proposed voting algorithm corresponds to the CGS for giving the weight values and taking the reward values. It is necessary to decide which Command Set control the mobile robot at given time and to select among the candidate actions. The Command Set was learnt online by means as Q-learning. Action Selector compares Q-values of Navigator with Heterogeneous behaviors. Finally, real-world experimentation was carried out. Results show the good performance for the selection on command set as well as the convergence of Q-value.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(I)
• /
• pp.244-248
• /
• 1987

The force/torque sensor for robot is developed. The compliance algorithm for peg-in-hole insertion task using the forec/troque sensor is developed. The system consists of an IBM PC, robot, force/torque sensor, strain meter, A/D board, and interface board. The IBM PC functions as a main processor and the robot controller as a slave processor. The sensor is constructed to measure $T_x$, $T_y$, $F_z$ which are necessary to precisely execute a peg-in-hole insertion task by SCARA type assembly robot. The outputs of sensor are analyzed. On the basis of the analysis, compliance algorithm for peg-in-hole insertion task is developed. Some comments concerning the development of wrist force/torque sensor and compliance algorithm are given.

• 한국지능시스템학회논문지
• /
• 제15권5호
• /
• pp.593-598
• /
• 2005

표적의 상태를 추정하기 위해 사용된 칼만 필터는 급 기동을 하거나 비선형적인 운동특성을 가지는 표적이 발생할 때, 모델은 상당한 오차를 유발하며 추적 성능은 현저히 저하될 수 있다. 이러한 문제점을 해결하기 위해서 본 논문에서는 기동하는 표적을 추정하기 위한 새로운 지능형 추정 알고리즘을 제안한다. 제안된 알고리즘은 유전 알고리즘에 기반한 퍼지 칼만 필터를 이용하여 실제 알지 못하는 표적의 가속도를 전체 프로세스 잡음으로 추정한 후, 보정된 필터의 잔여치와 변화를 이용한 퍼지 시스템으로 새로운 퍼지 이득을 추출하여 측정 예측 오차를 보정함으로써 한 개의 필터로 표적 움직임의 비선형성을 효과적으로 다룰 수 있다. 제안된 기법의 우수성을 검증하기 위해서 다중 모델 기법을 사용한 필터와 비교 모의실험을 하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 춘계학술대회 및 임시총회
• /
• pp.175-178
• /
• 2002

The proposed immune algorithm has an uncomplicated structure and memory-cell mechanism as the optimization algorithm which imitates the principle of humoral immune response, and has been used as methods to solve parameter optimization problems. Up to now, the applications of immune algorithm have been optimization problems with non-varying system parameters. Therefore, the effect of memory-cell mechanism, which is a merit of immune algorithm, is without. this paper proposes the immune algorithm using a memory-cell mechanism which can be the application of system with nonlinear varying parameters. To verified performance of the proposed immune algorithm, the speed control of nonlinear DC motor are performed. Computer simulation studies show that the proposed immune algorithm has a fast convergence speed and a good control performances under the varying system parameters.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.1977-1978
• /
• 2006

This paper discusses the method of vision based sensor fusion system for biped robot walking. Most researches on biped walking robot have mostly focused on walking algorithm itself. However, developing vision systems for biped walking robot is an important and urgent issue since biped walking robots are ultimately developed not only for researches but to be utilized in real life. In the research, systems for environment recognition and tele-operation have been developed for task assignment and execution of biped robot as well as for human robot interaction (HRI) system. For carrying out certain tasks, an object tracking system using modified optical flow algorithm and obstacle recognition system using enhanced template matching and hierarchical support vector machine algorithm by wireless vision camera are implemented with sensor fusion system using other sensors installed in a biped walking robot. Also systems for robot manipulating and communication with user have been developed for robot.

• 제어로봇시스템학회논문지
• /
• 제19권10호
• /
• pp.936-940
• /
• 2013

As the ageing population grows around the world, the demand for electric wheelchairs, an important mobility assistance device for the disabled and elderly, is gradually increasing. Therefore, a number of studies related to intelligent wheelchairs are actively underway to improve safety and comfort for wheelchair users. However, previous collision avoidance studies for intelligent wheelchairs have concentrated on collision avoidance methods with the shortest distance and by only changing either velocity or heading angle, rather than considering the forces exerted on the user. If a collision avoidance algorithm that does not consider these forces is applied to an intelligent wheelchair, there is a possibility of an accident due to falling as wheelchair users are generally disabled and elderly people. In this paper, we propose a collision avoidance algorithm which minimizes the forces exerted on a wheelchair user by minimizing the variation of the wheelchair's velocity and heading angle when the sizes, positions, velocities, and heading angles of a wheelchair and a moving obstacle are known.

• 전기학회논문지
• /
• 제66권12호
• /
• pp.1782-1791
• /
• 2017

In this paper, an optimal design of hybrid magnetic levitation(Maglev) system using intelligent optimization algorithms is proposed. The proposed maglev system adopts hybrid suspension system with permanent-magnet(PM) and electro magnet(EM) to reduce the suspension power loss and the teaching-learning based optimization(TLBO) that can overcome the drawbacks of conventional intelligent optimization algorithm is used. To obtain the mathematical model of hybrid suspension system, the magnetic equivalent circuit including leakage fluxes are used. Also, design restrictions such as cross section areas of PM and EM, the maximum length of PM, magnetic force are considered to choose the optimal parameters by intelligent optimization algorithm. To meet desired suspension power and lower power loss, the multi object function is proposed. To verify the proposed object function and intelligent optimization algorithms, we analyze the performance using the mean value and standard error of 10 simulation results. The simulation results show that the proposed method is more effective than conventional optimization methods.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.563-566
• /
• 2004

An intelligent Kalman filter (IKF) is proposed for tracking an incoming anti-ship missile. In the proposed IKF, the unknown target acceleration is regarded as an additive process noise. When the target maneuver is occurred, the residual of the Kalman filter increases in proportion to its magnitude. From this fact, the overall process noise variance can be approximated from the filter residual and its variation at every sampling time. A fuzzy system is utilized to approximate this valiance, and the genetic algorithm (GA) is applied to optimize the fuzzy system. In computer simulations, the tracking performance of the proposed IKF is compared with those of conventional maneuvering target tracking methods.

• 한국자동차공학회논문집
• /
• 제5권2호
• /
• pp.205-212
• /
• 1997

In this study, active vibration control for a flexible cantilever beam was performed by using the intelligent control technique. The intelligent control method which integrating the back propagation algorithm and the fuzzy inference technique was proposed and its performance was examined. The proposed control algorithm for the flexible cantilever beam was verified via computer simulation of active vibration control. Furthermore, the control system and its efficiency were investigated via experiments on active vibration control by the intelligent control technique without a digital signal processing device.

• Journal of Platform Technology
• /
• 제11권1호
• /
• pp.38-51
• /
• 2023

인공지능에 기반한 손 제스처 인식 정보를 활용한 지능형 인터페이스 알고리즘을 제안한다. 이 방법은 기능적으로 사용자 손 제스처의 추적 및 인식을 미디어파이프와 KNN, LSTM, CNN의 인공지능 기법을 사용해 다양한 동작을 빠르고 지능적으로 인식되는 인터페이스이다. 제안한 알고리즘 성능 평가를 위해 자체 제작한 2D 탑뷰 레이싱 게임과 로봇제어에 적용한다. 알고리즘 적용 결과 게임의 가상 객체의 다양한 움직임을 세밀하고 강건하게 제어할 수 있었으며, 실세계의 로봇 제어에 적용한 결과 이동과 정지, 좌회전, 우회전 등의 제어가 가능하였다. 또한 게임의 메인 캐릭터와 실세계 로봇을 동시에 제어하여 가상과 현실의 공존공간 상황 제어를 위한 지능형 인터페이스로 최적화된 동작도 구현하였다. 제안한 알고리즘은 신체를 활용한 자연스럽고 직관적 특성과 손가락의 미세한 움직임 인식에 따른 정교한 제어가 가능하며, 빠른 기간 내에 숙련되는 장점이 있어 지능형 사용자 인터페이스 개발을 위한 기본자료로 활용될 수 있다.