• 한국산업융합학회 논문집
• /
• 제24권6_1호
• /
• pp.645-658
• /
• 2021

In this paper, we propose a new approach to intelligent control based on fuzzy logic for work efficiency improvement of smart factory by the applicaion of ariticulated robot. The intelligent control that is applied to the working process by the joint of robotic manipulator is the main focus to improve a work efficiency for implimentation of smart factory in general manufacturing process. In this study, we propose a new method of a fuzzy model and then develop a nonlinear relationship between interaction forces and manipulator position using a fuzzy model. The reliability of the proposed control method is illustrated by simulation and experiments.

• 대한임베디드공학회논문지
• /
• 제14권4호
• /
• pp.187-195
• /
• 2019

In the fourth industrial revolution era, various commercial smart platforms for smart system implementation are being developed and serviced. However, since most of the smart platforms have been developed for general purposes, they are difficult to apply / utilize because they cannot satisfy the requirements of real-time data management, data visualization and data storage of smart factory system. In this paper, we implemented an open source based smart manufacturing big data platform that can manage highly efficient / reliable data integration for the diagnosis diagnostic system of manufacturing robots.

• 한국정보기술학회 영문논문지
• /
• 제8권2호
• /
• pp.129-137
• /
• 2018

Smart machines are one of the topics of our society recently. A smart machine should have a wiser or smarter function than the past. In the modern society, the environment of each family is being improved toward the direction of smart home. In this environment, smart speakers are now increasingly serving as interfaces for controlling various devices in the home, from devices that listen to conventional music. In this paper, we review the technology development trends of domestic and foreign smart speaker market, and describe the core technologies required. In Korea, while SKT and KT are dominant in the speaker market, major IT companies such as Amazon, Google and Apple are focusing on launching related products and technology development.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2009년도 춘계학술대회 논문집
• /
• pp.567-568
• /
• 2009

• 한국산업융합학회 논문집
• /
• 제19권2호
• /
• pp.69-74
• /
• 2016

This study proposes a new approach to design of the robust control application of a mobile manipulator with dual-arm. The mobil manipulator robot system consists of 12 DOF manipulators and a mobile robot. Kinematics of the robotics has been analyzed and simulated to verify reliability. A position-based torque control technique is applied to the robot by adding an outer loop to interact with the environment. Experimental studies of torque control applications of robot arm and interaction with a user operator are conducted. Experimental results has been proved that the robot arm performed regulated to follow the desired reference.

• 한국산업융합학회 논문집
• /
• 제24권3호
• /
• pp.351-361
• /
• 2021

This study proposes an intelligent control of manufacturing robot with dual arm based on neural network for smart factory implementation. In the control method of robot system, the perspectron structure of single layer based on neural network is useful for simple computation. However, the limitations of computation are emerging in areas that require complex computations. To overcome limitation of complex parameters computation a new intelligent control technology is proposed in this study. The performance is illustrated by simulation and experiments for manufacturing robot dual arm robot with eight axes.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.477-480
• /
• 2012

본 연구에서는 스마트폰을 활용한 프로그래밍 학습용 로봇시스템을 설계하고 개발하였다. 본 연구에서 제작된 시스템은 스마트폰을 이용하여 로봇에 직접 프로그램을 작성하도록 설계되어 있고 스마트폰으로 작성된 프로그램을 블루투스 모듈을 통하여 로봇제어회로에 전송하여 동작을 시킬 수 있도록 되어있다. 이는 로봇 교육에 있어서 장소의 제약을 받지 않고 교육이 가능함을 의미하며 학생들의 프로그래밍 결과가 스마트폰을 통하여 로봇의 움직임으로 나타나므로 기존 교육의 한계를 뛰어 넘는 프로그래밍 교육이 가능하다.

• ETRI Journal
• /
• 제43권2호
• /
• pp.221-231
• /
• 2021

To resolve energy depletion issues in massive Internet of Things sensor networks, we developed a set of distributed energy beamforming methods with one-bit feedback and clustering for multi-node wireless energy transfer, where multiple singleantenna distributed energy transmitters (Txs) transfer their energy to multiple nodes wirelessly. Unlike previous works focusing on distributed information beamforming using a single energy receiver (Rx) node, we developed a distributed energy beamforming method for multiple Rx nodes. Additionally, we propose two clustering methods in which each Tx node chooses a suitable Rx node. Furthermore, we propose a fast distributed beamforming method based on Tx sub-clustering. Through computer simulations, we demonstrate that the proposed distributed beamforming method makes it possible to transfer wireless energy to massive numbers of sensors effectively and rapidly with small implementation complexity. We also analyze the energy harvesting outage probability of the proposed beamforming method, which provides insights into the design of wireless energy transfer networks with distributed beamforming.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1236-1242
• /
• 2019

최근 로봇 기술의 발전에 따라 모바일 로봇에 대한 연구가 주목을 받고 있다. 현재 모바일 로봇의 대부분은 2륜 및 4륜 기반으로 개발되어 직선 주행에는 강하지만 방향전환 및 제자리 회전에 제한이 있으며, 이러한 문제점을 극복하고자 구 형태의 바퀴를 사용하는 볼 로봇에 대한 연구가 진행되고 있다. 볼 로봇은 협소한 공간에서 큰 제약 없이 이동이 가능하다는 장점을 가지고 있지만, 구조적으로 불안정하여 안정적인 자세 및 주행 제어가 요구된다. 본 연구에서는 무선통신으로 자세 및 주행 제어가 가능한 스마트폰 어플리케이션을 제안하고, 이를 적용하여 제작된 볼 로봇을 이용하여 자세 및 주행 제어 실험을 수행하였다. 실험을 통해 Roll 각도 오차 ±0.8도, Pitch 각도 오차 ±0.7도 이내에서 제어됨을 확인하였으며, 1m 주행제어에 대해 x축 방향 위치오차 ±0.1m, y축 방향 위치오차 ±0.08m 이내에서 제어됨을 확인하였다.

• 센서학회지
• /
• 제33권1호
• /
• pp.18-23
• /
• 2024

Humanoid robots, designed to interact in human environments, require stable mobility to ensure safety. When a humanoid robot falls, it causes damage, breakdown, and potential harm to the robot. Therefore, fall detection is critical to preventing the robot from falling. Prevention of falling of a humanoid robot requires an operator controlling a crane. For efficient and safe walking control experiments, a system that can replace a crane operator is needed. To replace such a crane operator, it is essential to detect the falling conditions of humanoid robots. In this study, we propose falling detection methods using Convolution Neural Network (CNN) model. The image data of a humanoid robot are collected from various angles and environments. A large amount of data is collected by dividing video data into frames per second, and data augmentation techniques are used. The effectiveness of the proposed CNN model is verified by the experiments with the humanoid robot MAX-E1.