• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.9
• /
• pp.1137-1153
• /
• 1995

It is not yet possible to solve the optimal number of neurons in hidden layer at neural networks. However, it has been proposed and proved by experiments that there is a limit in increasing the number of neuron in hidden layer, because too much incrememt will cause instability,local minima and large error. This paper proposes a module neural controller with pattern recognition ability to solve the above trade-off problems and to obtain fast learning convergence speed. The proposed neural controller is composed of several module having Multi-layer Perrceptron(MLP). Each module have the less neurons in hidden layer, because it learns only input patterns having a similar learning directions. Experiments with six joint robot manipulator have shown the effectiveness and the feasibility of the proposed the parallel module neural controller with pattern recognition perceptron.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1269-1271
• /
• 1996

This paper presents a visual servoing combined by evolutionary algorithms and neural network for a robotic manipulators to control position and orientation of the end-effector. Using the multi layer feedforward neural network that permits the connection of other layers, evolutionary programming(EP) that search the structure and weight of the neural network, and evolution strategies(ES) which training the weight of neuron, we optimized the net structure of control scheme. Using the four feature image information from CCD camera attached to end-effector of RV-M2 robot manipulator having 5 dof, we generate the control input to agree the target image, to realize the visual servoing. The validity and effectiveness of the proposed control scheme will be verified by computer simulations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1621-1623
• /
• 2013

원자력발전소를 비롯한 여러 산업플랜트들은 복잡한 파이프 시스템들이 필수적으로 필요한데, 이러한 파이프들 중 일부 파이프들은 안전성과 중요성을 고려하여 Over-haul 기간이나 가동 중에도 반드시 안전성 검사를 수행해야한다. 이 검사에는 검사자의 작업 공간 확보 어려움과 고위험 지역에 따른 작업환경으로 인하여 로봇을 이용한 검사 방안이 요구되고 있다. 본 논문에서는 파이프 등반 로봇을 개발함에 있어 영상을 이용한 파이프 자동 파지 기술과 로봇 원격제어 기술개발에 대하여 기술한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.525-528
• /
• 2021

본 논문은 산업현장이 아닌 카페등 생활현장에서의 폐기용 컵 처리를 목적으로, 사람을 대신해 지능적이고 기구학적으로 효율적인 다관절 메니퓰레이터의 설계 방법을 연구하였다. 다양한 장소에서 인간을 대신하여 임의의 위치에 있는 다양한 폐기 컵을 3D 카메라로 인식하여 알맞은 위치로 분리수거하는 6축 수직 다관절 모듈형 매니퓰레이터의 안정적인 동작을 위하여 기구부를 Yaw-Pitch-Pitch-Pitch-Yaw-Yaw의 6축 구조로 설계하고, 이를 구동하기 위한 관절 구동기의 용량을 분석하여 관절 구동기를 선정하며 전체적인 이해와 효율적인 분석을 위해 기구 전체의 외관을 3D 모델링 프로그램을 이용하여 구현하고 동작을 검증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.409-412
• /
• 2021

본 논문에서는 카페나 패스트푸드점같은 장소에서 인간을 대신하여 임의의 위치에 있는 다양한 컵을 3D 카메라로 검출하여 알맞은 위치로 분리수거하는 6축 수직 다관절 로봇 팔을 설계하였다. Yaw-Pitch-Pitch-Pitch-Yaw-Yaw 6축 구조로 설계하였으며, 이를 구동하기 위한 관절 구동기의 용량을 분석을 통해 최적화하였다. 각각 재질이 다른 컵을 그리퍼를 이용하여 잘 파지할 수 있도록 재질에 따른 파지력을 분석하였고 압력센서를 이용하여 재질이 다른 컵을 구분하여 분리수거 할 수 있도록 하였다. 실험을 통해 로봇의 성능과 개선점을 제시하였다.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.6
• /
• pp.99-108
• /
• 1998

In this paper, we proposed a multi-layer neural network for direct control method of nonlinear system. The proposed control method uses neural network as the controller to learn inverse model of plant. The neural network used consists of two parts; one part is for identification of linear part, and the other is for identification of nonlinear part of inverse system. The neural network has to be learned the liner part with RLS algorithm and the nonlinear part with error of plant. From the simulation and experiment of tracking control to use one link manipulator as plant, we proved usefulness of the proposed control method to comparing to conventional direct neural network control method. By comparing the two methods, from simulation and experiment, we were convinced that the proposed control method is more simple and accuracy than the conventional method. Moreover, number of weight and bias to be controller parameter are small, and it has smaller steady state error than conventional method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2033-2038
• /
• 2003

This paper describes an integrated navigation strategy for the autonomous service robot PSR. The PSR is under development at the KIST for service tasks in indoor public environments. The PSR is a multi-functional mobile-manipulator typed agent, which works in daily life. Major advantages of proposed navigation are as follows: 1) Structured control architecture for a systematic integration of various software modules. A Petri net based configuration design enables stable control flow of a robot. 2) A range sensor based generalized scheme of navigation. Any range sensor can be selectively applied using the proposed navigation scheme. 3) No need for modification of environments. (No use of artificial landmarks.) 4) Hybrid approaches combining reactive behavior as well as deliberative planner, and local grid maps as well as global topological maps. A presented experimental result shows that the proposed navigation scheme is useful for mobile service robot in practical applications.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.311-314
• /
• 2001

The objectives of this paper include the development of an agile prototype of SFFS, the $CAFL^{VM}$(Computer Aided fabrication of Lamination for Various Material), which is suitable for the multi-item and small-quantity production and various material fabrication. This paper includes remodeling of the layer slices for the 2D cutting, supplementing information of the layer slices and developing process conditions to fabricate products of various shape. And also includes developing control hardware as well as software by enhancing BOF of the manipulator to 3 degree for the precise 2D cutting. It will generate optimal layer trajectory considering the dynamic characteristics of the laser beam. The system can be used as a competitive agile protype system in terms of various materials, fabrication speed, and accuracy by CAD modeling precise layer slicing, material development, robot path control, and optimization of the support structure.

• The Journal of Korea Robotics Society
• /
• v.18 no.2
• /
• pp.164-171
• /
• 2023

To control the spread of COVID-19, it is important to identify the infection in its incipient stages so that the infected persons can be dealt with accordingly. The currently used face to face sampling method may increase the risk of infection for medical professionals as it exposes them to the asymptomatic yet infectious patients. This can result in further increases in the load on the medical system and workload of the medical staff. As a solution to this problem, in this paper, we present a robotic system for rapid non-face-to-face automatic nasopharyngeal swab sample collection. The system consists of a custom designed 7-DoF manipulator equipped with a specially developed safety mechanism for restricting the maximum force applied by the tip of the swab. During the swab sampling process, the force applied by the tip of the swab is continuously monitored in real-time by a 3-axis force sensor in order to detect contact with the nasopharynx. The possibility of using this system for automaticnasopharyngeal swab sample collection is proven through experimentation with a phantom model.

• Journal of the Korean Vacuum Society
• /
• v.10 no.3
• /
• pp.380-386
• /
• 2001

A nuclear microprobe system with adjustable precision object slits and a magnetic quadrupole doublet was designed by the beam optics simulation using a first order matrix formalism, and installed in a $30^{\circ}$ beam line connected with KIGAM 1.7 MV Tandem VDG Accelerator. Demagnification factors for x and y axis are calculated to be 25 and 4.9, respectively, and a minimum beam spot side is expected to be about 5 $\mu\textrm{m}$ for 3 MeV proton beams with a current of about 1 nA. A multi-purpose octagonal target chamber has been built to facilitate MeV ion-beam analytical techniques of PIXE, RBS, ERDA, and ion beam micro-machining. It contains X-ray and particle detectors, a zoom microscope, a Faraday cup, a 4-axis sample manipulator and a high vacuum pumping system. The system performance of the nuclear microprobe is now being tested, and automatic manipulator control and data acquisition system will be installed for routine applications of micro ion-beam analytical techniques.