• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.319-320
• /
• 2007

신경망이나 퍼지 시스템을 사용한 이족 보행 궤적 생성에 대한 연구는 있으나 로봇의 중심점이 변경되는 상황에 대한 보행 궤적 생성은 부족한 실정이다. 본 논문에서는 이족 보행 로봇의 보행에 대해 정의하고, 이를 기반으로 물체 운반시의 유전자 알고리즘을 통한 보행 궤적 생성을 제안하였다. 유전자 알고리즘은 최적화 문제에 있어서 기존의 다른 알고리즘보다 전역적이고 강인한 최적화 방법을 제시하면서도 간단한 구조로서 동작하는 장점을 가지고 있다. 따라서 본 연구에서는 기존 연구를 통해 구해진 로봇의 보행궤적을 모태로 부분 사상 교배, 순서교배, 주기교배의 교배 연산자를 순차적으로 이용하여 물체 운반시의 보행 궤적을 구하고 이를 검증하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.8
• /
• pp.685-692
• /
• 2008

In this paper, the trajectory control problem of an underwater robot is addressed. From the viewpoint of control engineering, trajectory control of the underwater robot is not an easy task due to its nonlinear dynamics, which includes various hydraulic forces such as buoyancy forces and hydrodynamic damping, the difference between the centers of buoyancy and gravity, and disturbances from a tether cable. To solve such problems, we applied Time Delay Control to the underwater robot. This control law has a very simple structure not requiring the nonlinear plant dynamics, and was proven to be highly robust against disturbances and uncertainties. We confirmed its effectiveness through experiments.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.329-330
• /
• 2007

지능형 로봇에서 환경인식과 이러한 환경에 따른 행동 결정능력은 로봇이 필수적으로 갖추어야 할 기능이다. 본 논문은 이족로봇 플랫폼에서 비전기반 환경인식과 이를 통한 안정적인 보행 제어시스템을 제안한다. 비전기반 환경인식 시스템은 움직임 모델을 이용한 로봇 자체 움직임 보정 모듈, Adaboost를 이용한 장애물 영역 추출, PCA를 이용한 장애물 특징 추출, Hierarchical SVM을 이용한 장애물 인식 모듈로 구성되어 있으며, 이러한 환경 인식 시스템으로부터 보행 제어 시스템은 상황에 맞는 안정적이 보행 궤적을 생성한다. 보행 제어 시스템은 neural network을 이용하여 보행 궤적 생성 모듈과 보행 오차를 보정하기 위한 fuzzy 제어기 모듈로 구성되어 있다. 본 시스템을 제작한 로봇에 적용한 결과 보다 안정적인 보행을 할 수 있었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.11
• /
• pp.3066-3073
• /
• 2009

Joint paths of master and branch pipes are induced mathematically for many kinds of joint patterns between both pipes in 3-axis pipe profile-cutting machines. By compensating them with a kerf width, the real cutting paths are determined, and their CL-data are generated, and the tool paths generated by CL-data are verified by a ghost function. A bevelling of welds is implemented through tilting a cutting torch in the $\beta$-axis direction for 8 sections in the chuck rotation of $\alpha$-axis. A PLC controls simultaneously position and velocity in a real time for $\alpha$, X, $\beta$-axis by loading CL-data generated. We developed the PLC-controlled 3-axis pipe profile-cutting system which can cut a master or branch pipe along the cutting path and simultaneously do a bevelling process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1759-1766
• /
• 2003

This paper proposes a neuro­fuzzy controllers for trajectory tracking control of robot manipulators. The computed torque method is an effective means for trajectory tracking control. However, the tracking performance of this method is severely affected by the uncertainties of robot manipulators. Therefore, the proposed controller is used to compensate the uncertainties of robot manipulators. In the neuro­fuzzy controllers, the number of fuzzy rules used forty­nine. The effectiveness of the proposed controllers is demonstrated by computer simulations using two­link robot manipulator, As a result, it is confirmed that the output of the proposed neuro­fuzzy controllers can efficiently decrease the uncertainties of robot manipulator.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.766-769
• /
• 2021

In order to perform tasks such as design, control, optimization, and prediction of flight vehicle trajectories based on machine learning techniques including deep learning, a certain amount of flight vehicle trajectory data is required. However, there are cases in which it is difficult to secure more than a certain amount of flight vehicle trajectory data for various reasons. In such cases, synthetic data generation could be one way to make machine learning possible. In this paper, to explore this possibility, we generated and evaluated synthetic flight vehicle trajectory data using time-series generative adversarial neural network. In addition, various ablation studies (comparative experiments) were performed to explore the possibility of using synthetic data in the aircraft trajectory prediction task. The experimental results presented in this paper are expected to be of practical help to researchers who want to conduct research on the possibility of using synthetic data in the generation of synthetic flight vehicle trajectory data and the work related to flight vehicle trajectories.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.12 s.189
• /
• pp.46-55
• /
• 2006

A robust motion controller based on self-organizing fuzzy control(SOFC) and feed-back tracking control technique is proposed for a two-wheel driven mobile robot. The feed-back control technique of the controller guarantees the robot follows a desired trajectory. The SOFC technique of the controller deals with unmodelled dynamics of the vehicle and uncertainties. The computer simulations are carried out to verify the tracking ability of the proposed controller with various driving situations. The results of the simulations reveal the effectiveness and stability of the proposed controller to compensate the unmodelled dynamics and uncertainties.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.5
• /
• pp.486-502
• /
• 1989

This paper proposes two types of the preview algorithms to predict the velocities and joint positions, and deals with a control approach using the preview algorithms for the precise trajectory control. Specifically, a predictor as the form of discrete time state equations is proposed based on the robot dynamics model linearized by the computed toque method. And another state predictor is proposed by the best line fitting in the least square sense, where present joint velocities and positions and several past positions are employed. Then computer simulations are performed for the SCARA robot with two d.o.f to show the validities of the proposed algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.693-698
• /
• 2004

In this paper, an iterative learning control method is applied to suppress a vibration of a 2-mass system which has a flexible coupling between a load and a motor. More specifically, conditions for the load speed without vibration are derived based on the steady-state condition. And the desired motor position trajectory is synthesized based on the relation between the load and motor speed. Finally, a PD-type iterative learning control law is applied for the desired motor position trajectory. Since the learning law applied for the desired trajectory guarantees the perfect tracking performance, the resulting load speed shows no vibration even when there exist model uncertainties. A modification to the learning law is also Presented to suppress undesired effects of an initial position error, The simulation results show the effectiveness of the proposed learning method.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2009.05a
• /
• pp.411-413
• /
• 2009

This paper deals with supersonic vehicle. A supersonic vehicle has very complicated and high nonlinear thrust characteristics with respect to outer and inner environment during operation. For this reason, supersonic vehicle has many maneuver constraints and allows to operate within more narrow flight envelope. In this paper, trajectory optimization of supersonic vehicle is accomplished. The trajectory optimization problem is formulated by a discrete parameter optimization problem and the operation constraints are considered during trajectory optimization. It is shown that results of trajectory optimization give senses to fuel supply and nozzle throttle area control into effectiveness. Furthermore, general operation direction and its application for supersonic vehicles are discussed.