• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2003년도 춘계공동학술대회
• /
• pp.98-104
• /
• 2003

While the impact or internet on our everyday life keeps increasing, the internet users are turning toward the value added information only that suits their purpose instead of just wandering over a sea (pool) or information. Although it is easy to locate the information using various search engines. we still finds it time and cost consuming to update the existing information or to add similar Information. There are several portal sites managed by each industrial types or associations/organizations for the purpose or strengthening the competitiveness or small and medium-sized enterprises And currently, tremendous manpower and expenses are put into the selection and quality improvement or information to satisfy the needs toward the high qualify information by the specialized users in their fields collection and updating or the information is partially available manually during He period or budget allocation by the government it becomes problematic, however, to continue this service when the project expires. This report presents the system for the information collection, analysis and classification of portal sites operated for the special purposes and automatic upload to the proper sites. In addition. expression or web robots and application of robots and several information types are suggested which will eventually accomplish currency or information and automatic updates and addition or documents with the least expenses or maintenance.

• 한국인터넷방송통신학회논문지
• /
• 제13권2호
• /
• pp.165-170
• /
• 2013

본 논문은 기능 축약화 스크립트를 이용한 로봇 시뮬레이션을 제작하는 방법을 제안한다. 일반적인 로봇 시뮬레이션 저작 도구들은 이를 사용하기 위한 전문적인 개발 언어와 이와 연동되는 API등에 대한 전문적인 지식을 요구하고 있으며, 이러한 사전지식들은 로봇 시뮬레이션을 환경을 구현하는 데 매우 큰 장애 요인이 되고 있다. 이러한 문제를 해결하기 위해서 본 논문은 시뮬레이션 환경을 구성하기위해 기능 축약화 스크립트를 설계하였으며, 축약화된 스크립트는 단순화된 서비스 명령들과 최소의 옵션들로 구성된다. 실험에서는 개발된 저작 도구를 고등학교 학생과 선생님들에게 교육하였으며, 초보자들이 본 저작도구 하루의 교육과정 이수를 통해 로봇 시뮬레이션 환경을 구성하고 시뮬레이션 환경의 로봇을 제어할 수 있음을 검증하였다.

• 로봇학회논문지
• /
• 제11권4호
• /
• pp.270-276
• /
• 2016

This paper proposes a design methodology of self-reconfigurable kinematics and control engine for modular and reconfigurable robots. A modular manipulator has been proposed to meet the requirement of task adaptation in versatile needs for service and industrial robot area and the function of self-reconfiguration is required to extend the application of modular robots. Kinematic and dynamic contexts are extracted from the module and assembly information and related codes are automatically generated including controller. Thus a user can easily build and use a modular robot without professional knowledge. Simulation results are presented to verify the validity of the proposed method.

• 대한기계학회논문집A
• /
• 제31권4호
• /
• pp.517-524
• /
• 2007

This paper presents a global localization method using circular correlation of an omni-directional image. The localization of a mobile robot, especially in indoor conditions, is a key component in the development of useful service robots. Though stereo vision is widely used for localization, its performance is limited due to computational complexity and its narrow view angle. To compensate for these shortcomings, we utilize a single omni-directional camera which can capture instantaneous $360^{\circ}$ panoramic images around a robot. Nodes around a robot are extracted by the correlation coefficients of CHL (Circular Horizontal Line) between the landmark and the current captured image. After finding possible near nodes, the robot moves to the nearest node based on the correlation values and the positions of these nodes. To accelerate computation, correlation values are calculated based on Fast Fourier Transforms. Experimental results and performance in a real home environment have shown the feasibility of the method.

• 한국지능시스템학회논문지
• /
• 제18권3호
• /
• pp.329-334
• /
• 2008

바퀴구동형 메커니즘은 다양한 서비스 로봇에 유용하게 활용되고 있다. 이러한 로봇을 위하여 가장 기본적이면서 중요하게 요구되는 성능중의 하나는 경사진 도로를 어려움없이 주행할 수 있는 등반능력으로 볼 수 있다. 본 논문에서는 이러한 바퀴 구동형 로봇 메커니즘의 등반능력을 고려하고, 경사면을 원활하게 주행하기 위한 구동기의 사양을 결정하는데 유용한 필요조건을 제시하고자 한다. 결과적으로, 이러한 조건은 이동로봇 메커니즘의 설계에 유용하게 활용될 수 있을 것으로 기대한다.

• 산업융합연구
• /
• 제15권1호
• /
• pp.43-52
• /
• 2017

Robot refers to machines that recognize the external environment and assess the given situations in order to operate autonomously by imitating the manner in which humans behave. Although Korea still lacks global competitiveness, Korea, as the $4^{th}$ ranked robot manufacturing country in the world, is currently expanding the domains of robots from application in manufacturing to application in service provision. Accordingly, this study aims to analyze the factors for the success in entry into the cooperation robot market among various robotic markets in accordance with the literary research method in consideration for the importance of robot industry that could determine the future national competitiveness. The result of the analysis of the factors for the success in entry into the cooperation robot market, shows that factors including analysis of the trends in manufacturing robot market, strategy for benchmarking of the leading cooperation robot companies, activation of small and medium enterprise-centered cooperation robotic industry, excavation of demands for cooperation robots with focus on automobile, semiconductor and IT industries, utilization of the opportunities provided by government's robotic industry policies and standardization of cooperation robot components, etc. determine whether one will succeed in the market or not. Furthermore, it is believed that fortification of competitiveness of the manufacturing sector through the powerful policy support for the robotic industry at government level and policies on cultivation of new growth engine through specialization of the robotic areas closely related to daily life must be implemented concurrently because it is forecasted that competitiveness in robotics technology will become the criterion for national competitiveness in the future.

• 로봇학회논문지
• /
• 제16권1호
• /
• pp.56-63
• /
• 2021

As the use of robots in service area increases, research has been conducted to replace human tasks in daily life with robots. Among them, this study focuses on the tidy-up task on a desk using a robot arm. The order in which tidy-up motions are carried out has a great impact on the success rate of the task. Therefore, in this study, a neural network-based method for determining the priority of the tidy-up motions from the input image is proposed. Reinforcement learning, which shows good performance in the sequential decision-making process, is used to train such a task planner. The training process is conducted in a virtual tidy-up environment that is configured the same as the actual tidy-up environment. To transfer the learning results in the virtual environment to the actual environment, the input image is preprocessed into a segmented image. In addition, the use of a neural network that excludes unnecessary tidy-up motions from the priority during the tidy-up operation increases the success rate of the task planner. Experiments were conducted in the real world to verify the proposed task planning method.

• ETRI Journal
• /
• 제44권2호
• /
• pp.183-193
• /
• 2022

Smart cities are expected to provide residents with convenience via various agents such as CCTV, delivery robots, security robots, and unmanned shuttles. Environmental data collected by various agents can be used for various purposes, including advertising and security monitoring. This study suggests a surveillance map data framework for efficient and integrated multimodal data representation from multi-agents. The suggested surveillance map is a multilayered global information grid, which is integrated from the multimodal data of each agent. To confirm this, we collected surveillance map data for 4 months, and the behavior patterns of humans and vehicles, distribution changes of elevation, and temperature were analyzed. Moreover, we represent an anomaly detection algorithm based on a surveillance map for security service. A two-stage anomaly detection algorithm for unusual situations was developed. With this, abnormal situations such as unusual crowds and pedestrians, vehicle movement, unusual objects, and temperature change were detected. Because the surveillance map enables efficient and integrated processing of large multimodal data from a multi-agent, the suggested data framework can be used for various applications in the smart city.

• 한국정보통신학회논문지
• /
• 제15권6호
• /
• pp.1245-1250
• /
• 2011

본 연구에서는 RFID(Radio Frequency Identification)와 HL7(Health Level 7) 프로토콜을 이용하여 병원을 내원한 환자의 접수를 보다 신속하고 효율적으로 처리할 수 있는 시스템을 설계하였다. 본 논문에서 설계한 시스템을 사용하면 접수뿐만 아니라 병원 내에서의 환자 정보의 활용이 가능하며 이는 병원 내에서 중복적인 서류 처리나 환자 정보를 얻기 위한 과정을 축소시킬 수 있다. 또한 HL7 프로토콜을 이용하여 병원 진료 과정을 고려한 HL7 메시지 구조를 설계하고 적용하였다. 본 논문에서는 서비스 로봇을 이용하여 환자 접수 기능을 구현하였으며, 향후과제로 진료 시에 필요한 혈압 및 체온 등 생체 데이터를 로봇을 이용하여 취득할 수 있는 기능을 추가 하는 것이다.

• 한국콘텐츠학회논문지
• /
• 제9권4호
• /
• pp.81-94
• /
• 2009

유비쿼터스 환경에서 지능형 서비스 로봇의 실시간성 기술은 QoS를 보장하기 위해서 필수 불가결한 요소이다. 본 논문에서는 지능형 서비스 로봇에 실시간성을 지원하는 실시간 프레임워크를 설계 및 구현한 내용을 기술한다. 실시간 스케줄링 서비스를 제공하는 실시간 프레임워크는 범용 운영체제를 기반으로 동작하며, 범용 운영체제에서 제공하는 스케줄러의 실시간성 미 지원 문제를 해결한다. 본 논문에서는 또한 실시간 로봇 애플리케이션에 QoS를 보장하기 위한 실시간 스케줄링 서비스를 제안한다. 제안된 실시간 프레임워크의 성능 평가를 위해 윈도우즈 운영체제 상에 구현하였다. 실험 결과를 통해 쓰레드의 응답시간 향상과 실시간 프레임워크 탑재에 따른 성능상의 오버 헤드가 $62{\mu}s$로 미미하다는 것을 알 수 있다.