• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.10a
• /
• pp.108-112
• /
• 2000

Neural networks are used in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Journal of the Korean Society of Industry Convergence
• /
• v.7 no.2
• /
• pp.167-172
• /
• 2004

Neural networks are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division (Corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.10 no.6
• /
• pp.959-965
• /
• 1986

본 논문에서는 모듀울 로봇은 공장 자동화를 달성하기 위한 경제적인 방법으 로 기대되고 있다. 모듀울 로봇을 구성하는 모듀울을 개발 설계하기 위해서는 먼저 유용한 로봇을 기본 구조를 연구하여야 한다. 일반적으로 로봇의 처음 3개의 관절은 로봇 손의 위치를 결정하는 데 쓰이고 나머지 관절은 로(positional maneuverability matrix)과 방향기동행열로 구성됨음을 보이고, 가분성(separability)의 조건을 제시하 였다.또한 희전관절이나 미끄름관절로 이루어진 3자유도 로봇 팔의 3차원 공간에서 의 기본형태는 12개임을 밝히고, 3자유도 손목이 3개 방향을 완전히 조정할 수 있기 위해서는 3개의 회전관절축이 서로 직교하여야 함을 보였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.1
• /
• pp.62-68
• /
• 1996

Linear controllers, such as LQG/LTR controller, have been investigated to control flexible link manipulators. The performance and complexity of these depend largely on the linearized model upon which the controller is designed. In this study, singular perturbation model is tested in designing a LQG/LTR controller for a flexible link manipulator. The order of the resulting controller is much lower than the one based on a full model. Through numerical study, it is shown that the performance of the proposed controller reaches reasonably to the one based on the full model.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.772-775
• /
• 2002

The remote handling and maintenance devices in the nuclear hot ceil should be checked prior to the hot operation in view of reliability and operability. In this study, the digital mock-up is implemented to analyze and define the process equipment maintenance processes instead of real mock-up, which is very expensive and time consuming. To do this, the parts of equipment and maintenance devices are modeled in 3-D graphics, assembled, and kinematics is assigned. Also, the virtual workcell of the spent fuel management process is implemented in the graphical environment which is the same as the real environment. This simulator has the several functions for verification such as analyses for the manipulator's working area, the collision detection, the path planning and graphic simulation of the processes etc. This graphic simulator of the maintenance devices can be effectively used in designing of the maintenance processes for the hot cell equipment and enhance the reliability of the spent fuel management.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.580-583
• /
• 2002

This paper presents a novel pose description corresponding to the structure characteristics of parallel manipulators, which is convenient and intuitionistic to us. A class of 3-RSR parallel manipulator is considered here. Through analysis on geometry theory, we obtain a new method of the closed-form solution to the forward kinematics. The closed-form solution contains two different meanings-analytical and real-time. So we reach the goal of practical application and control. A numerical example is also presented and are verified by an inverse kinematics analysis. It shows that the method has a practical value for real-time control.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.540-543
• /
• 2002

Conventional robot manipulators actuated by motors with the speed reducer such as the harmonic drive have weakness in the load capacity, since the speed reducer does not have enough strength. To overcome this, we proposed and constructed a new type of the robot actuator which is four-bar-link mechanism driven by the ball screw. We developed a new type of a revolute-jointed robot manipulator composed of four axes. The base axis is actuated with conventional speed reducer, but the others are actuated by the proposed actuators. We analyzed the mechanism of the actuators of the robot joints, and developed the dynamics model. The dynamics are expressed in the joint coordinates, and then they are mapped into the sliding coordinates of the ball screw. The structure specifications of the manipulator shown.

• The Journal of Korea Robotics Society
• /
• v.2 no.2
• /
• pp.168-177
• /
• 2007

In a number of fields, robots are being used for two purposes: efficiency and safety. Most robots, however, have single-actuator mechanism for each joint, where the tasks are performed with high stiffness. High stiffness causes undesired problems to the environment and robots. This study proposes redundant actuator mechanism as an alternative idea to cope with these problems. In this paper, Double-Actuator Unit (DAU) is implemented at each joint for applications of multi-link manipulators. The DAU is composed of two motors: the positioning actuator and the stiffness modulator, which enables independent control of positioning and compliance. A three-link manipulator with DAUs enables adaptive control of RCC. By modulating the joint stiffness of the manipulator and controlling the position of RCC, we can significantly reduce contact force during assembly tasks and surgical procedures.

• The Journal of Korea Robotics Society
• /
• v.11 no.4
• /
• pp.235-241
• /
• 2016

Dual arm manipulators have been developed for the entertainment purpose such as humanoid type or the industrial application such as automatic assembly. Nowadays, there are some issues for applying the dual arm robot system into the various fields. Especially, robots can substitute human and perform the dangerous activity such as search and rescue in the battle field or disaster. In the paper, the dual arm manipulator which can be adapted to the rescue robot with the mobile platform was developed. The kinematic design was proposed for the rescue activity and the required specification was determined through the kinematic analysis and the dynamic analysis in the various conditions. The proposed dual arm manipulator was manufactured based on the vibration analysis result and its performance was proved by the experiment.

• Journal of the Korean Institute of Navigation
• /
• v.21 no.1
• /
• pp.109-118
• /
• 1997

In this paper, applications of multilayer neural networks to control of flexible robot beam are considered. The multilayer nerual networks can be used to approximate any continuous function to a desired degree of accuracy and the weights are updated by Gradient Method. When a flexible beam is rotated by a motor through the fixed end, transverse vibration may occur. The motor torque should be controlled insuch a way that the motor rotates by a specified angle, while simultaneously stabilizing vibration of the flexible manipulators so that is arrested as soon as possbile at the end of rotation. Accurate control of lightweight beam during the large changes in configuration common to robotic tasks requires dynamic models that describe both rigid body motions, as well as the flexural vibrations. Therefore, a linear dynamic state-space model of for a single link flexible robot beam is derived and PD controller, LQP controller, and inverse dynamical neural networks controller are composed. The effectiveness the proposed control system is confirmed by computer simulation.