• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.496-499
• /
• 1999

This paper describes a medular neural network(MNN) for a vision system which tracks a given object using a sequence of images from a camera unit. The MNN is used to precisely recognize the given robot endeffector and to minize the processing time. Since the robot endeffector can be viewed in many different shapes in 3-D space, a MNN structure, which contains a set of feedforwared neural networks, co be more attractive in recognizing the given object. Each single neural network learns the endeffector with a cluster of training patterns. The training patterns for a neural network share the similar charateristics so that they can be easily trained. The trained MNN is less sensitive to noise and it shows the better performance in recognizing the endeffector. The recognition rate of MNN is enhanced by 14% over the single neural network. A vision system with the MNN can precisely recognize the endeffector and place it at the center of a display for a remote operator.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.349-351
• /
• 2007

A concept of the semi-autonomous tele-weeding-system which performs weeding tasks through co-operation of human and machine intelligence is proposed. The tele-weeding system consists of weeding robot, communication networks and operating server. The images of plants taken by the weeding robot are transferred through the communication networks to the human operator. Positions of the weeds are indicated at the operating host by the operator and transferred back to the weeding robot. Such position informations are converted to the world space and the weeding is done based on the robot intelligence. Feasibility of such concept has been tested through development of a laboratory model of the system.

• Agricultural and Biosystems Engineering
• /
• v.6 no.2
• /
• pp.54-58
• /
• 2005

In this study, tele-robotics was researched to actualize robots in agriculture. The robot system consisted of a data collecting robot, several robots that performed their own agricultural operations, a server, client computers and networks between robots and computers. In this paper, as a first step, harvesting experiments were carried out. From the results, it was observed that the tele-robotics had feasibility to propel the robotization in agriculture. The tele-robotics has advantages not only that human workers are released from the severe working environment but also that the greenhouse can be monitored and controlled anytime and anywhere.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2995-2997
• /
• 1999

Recently, real-time visual tracking control for a robot manipulator is performed by using a vision feedback sensor information. In this paper, the optical flow is computed based on the eye-in-hand robot configuration. The image jacobian is employed to calculate the rotation and translation velocity of a 3D moving object. LQG visual controller generates the real-time visual trajectory. In order to improving the visual tracking performance. VSC controller is employed to control the robot manipulator. Simulation results show a better visual tracking performance than other method.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1219-1221
• /
• 1996

In this paper, we develop a control system of an Educational Robot and implement a fuzzy algorithm for the position control. The MA2000 robot manufactured by TecQuipment Co. is the controlled system and 3 axes(waist, shoulder, elbow) of total 6 axes are controlled by the fuzzy logic-based algorithm. The control system consists of an IBM PC, an interface board capable of A/D conversion and PWM generation, and a drive board for dc motors in joints of the robot. The experiments show that the modified fuzzy algorithm yields a better performance in steady-stale than that of the conventional fuzzy algorithm.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.4
• /
• pp.415-425
• /
• 2019

This study proposes a new approach to control Moving Stuff Action Through Iterative Learning robot with dual arm for smart factory. When robot moves object with dual arm, not only position of each hand but also contact force at surface of an object should be considered. However, it is not easy to determine every parameters for planning trajectory of the an object and grasping object concerning about variety compliant environment. On the other hand, human knows how to move an object gracefully by using eyes and feel of hands which means that robot could learn position and force from human demonstration so that robot can use learned task at variety case. This paper suggest a way how to learn dynamic equation which concern about both of position and path.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.586-589
• /
• 2021

In this paper, Hyundai Motor Group's advanced cases and technologies are introduced in the mobility field through Boston Dynamics M&A, a new pivotal industrial robot technology that will lead the 21st century of Hyundai Motor Group, focusing on RT(Robot Technology) and related industries.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.111.3-111
• /
• 2002

$\textbullet$introduction $\textbullet$CO-evolution Algorithm $\textbullet$Subsumption Architecture $\textbullet$Neural Network $\textbullet$Khepera Robot

• Proceedings of the KIPE Conference
• /
• 2006.06a
• /
• pp.311-315
• /
• 2006

This paper proposes 5 phase step motor drive system has high performance dynamics with micro step control has current controller. In this paper, analog current controller has been developed to minimize system size and cost. The validity of the proposed technique is verified through experimental results of position control robot.

• Composites Research
• /
• v.28 no.3
• /
• pp.81-88
• /
• 2015

In this paper, we evaluate structural integrity of the wearable robot by using finite element analysis, which is made of CFRP(Carbon Fiber Reinforced Plastic) composite materials to be lightened. On the basis of the ASTM(American Standard Test Method), mechanical tests of the material are carried out in tensile, compressive and shear test for analytical evaluation. With the tested composite material, the main frame and two femoral frames of the robot is redesigned to satisfy the lightening design requirements. It is verified with the structural analysis that the redesigned frames are good for the part of the wearable robot.