• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1161-1162
• /
• 2023

모바일 로봇의 자율주행을 위하여 인터넷이 제약된 환경에서도 가능한 Edge computing 에서의 Object Detection 이 필수적이다. 본 논문에서는 이를 위해 Orin 보드에서 YOLOv7 과 Complex_YOLOv4 를 구현하였다. 직접 취득한 데이터를 통해 YOLOv7 을 구현한 결과 0.56 의 mAP 로 프레임당 133ms 가 소요되었다. Kitti Dataset 을 통해 Complex_YOLOv4 를 구현한 결과 0.88 의 mAP 로 프레임당 236ms 가 소요되었다. Comple_YOLOv4 가 YOLOv7 보다 더 많은 데이터를 예측하기에 시간은 더 소요되지만 높은 정확성을 가지는 것을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.11-12
• /
• 2024

건설 현장에서 자율주행 로봇의 안전한 주행을 위해 동적 장애물의 정확한 인식 및 추적이 중요하다. 본 논문에서는 실시간 3D 객체 인식 및 추적을 위한 방법을 제안한다. Complex-YOLOv4 모델을 이용한 객체 인식, SORT 알고리즘 확장을 통한 객체 추적을 구현하였다. Jetson AGX Orin 보드의 ROS2 환경에서 시스템을 구축하여, 실시간 3D 객체 인식 및 추적이 가능함을 확인하였다.

• The Journal of Korea Robotics Society
• /
• v.4 no.2
• /
• pp.155-162
• /
• 2009

A main distributing frame(MDF) is an interface unit that is used to connect office equipment cables in a telephone company to subscriber cables. Until now, there is no automated switching system for MDFs in Korea. Manual handling of an MDF has some drawbacks; It is time-consuming, very cumbersome, and expensive. It also makes maintenance hard. An automated main distributing frame system is proposed and commercialized in Japan. In that system, a robot gripper inserts connecting pins into the cross point holes of a matrix board, which reveals several disadvantages in the aspects of space, maintenance, fault tolerance, and economical efficiency. This paper describes a newly developed robotic switch board system for MDFs. In the developed system, switches are placed at the cross point of a matrix board. There is one robot in between two switch units, so one robot deals with two switch units. In the system, positioning the robot, opening and closing switches can be done by using only a pair of motors and a pair of solenoids. The newly developed system is compact in size, reduces cost, and shows high reliability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.191-196
• /
• 2006

This paper presents the moving object tracking method using vision system. In order to track object in real time, the image of moving object have to be located the origin of the image coordinate axes. Accordingly, Fuzzy Control System is investigated for tracking the moving object, which control the camera module with Pan/Tilt mechanism. Hereafter, so the this system is applied to mobile robot, we design and implement image processing board for vision system. Also fuzzy controller is implemented to the StrongArm board. Finally, the proposed fuzzy controller is useful for the real-time moving object tracking system by experiment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.197-205
• /
• 2006

This paper presents the moving object tracking method using vision system. In order to track object in real time, the image of moving object have to be located the origin of the image coordinate axes. Accordingly, Fuzzy Control System is investigated for tracking the moving object, which control the camera module with Pan/Tilt mechanism. Hereafter, so the this system is applied to mobile robot, we design and implement image processing board for vision system. Also fuzzy controller is implemented to the StrongArm board. Finally, the proposed fuzzy controller is useful for the real-time moving object tracking system by experiment.

• Journal of the Korea Convergence Society
• /
• v.9 no.9
• /
• pp.1-8
• /
• 2018

It is a key role in leading and activating coding education as a process to solve problems creatively to produce and provide the educational contents on the basis of 3D printing. In this paper, we develop a variety of fusion contents to use 3D printing and 8bit MCU base control board which provides specific functions through Arduino. The developed control program conducts various packet monitoring more than ten times per a second, supporting intrinsically full duplex. In addition, communication protocol optimized in conveying a lot of information enables to control different contents. The contents produced with the control board and 3D printing are useful as a programming education tool to train the principle and the concept of coding.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.679-686
• /
• 2022

In this paper, we implemented an algae removal device that recognizes and removes algae existing in water using Raspberry Pi camera and DO (Dissolved Oxygen) sensor. The Raspberry Pi board recognizes the color of green algae by converting the RGB values obtained from the camera into HSV. Through this, the location of the algae is identified and when the amount of dissolved oxygen's decrease at the location is more than the reference value using the DO sensor, the algae removal device is driven to spray the algae removal solution. Raspberry Pi's camera uses OpenCV, and the motor movement is controlled according to the output value of the DO sensor and the result of the camera's green algae recognition. Algae recognition and spraying of algae removal solution were implemented through Arduino and Raspberry Pi, and the feasibility of the proposed portable algae removal device was verified through experiments.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.227-229
• /
• 2012

한국해양연구원에서 개발하고 있는 해저보행로봇 CR200은 6개의 다리를 이용하여 해저면에서 보행으로 이동하며 정밀 해저탐사 및 작업을 수행할 수 있는 로봇이다. 운용자는 선상제어실에서 유선으로 연결된 CR200을 원격으로 모니터링하거나 제어한다. 특히 안정적인 보행을 위해서는 100Hz의 주기로 CR200의 상태 정보가 선상제어실로 전송되고, 선상제어실에서는 전송된 정보를 기반으로 제어 명령을 산출하여 CR200으로 전송해야 한다. 이러한 주기적인 실시간 제어를 위해서는 일반적으로 실시간 운영체제를 사용하지만, 본 논문에서는 실시간 운영체제를 사용하지 않고 시스템 시간 기반의 백그라운드 프로세스로 동작하는 소프트웨어 타이머를 사용하여 실시간 제어를 하는 방법을 제안하고, 성능 평가 결과를 제시한다. 제안한 방법의 실시간 속성을 검증하기 위하여, 현재 설계에서 운영체제로 고려하고 있는 우분투 10.04와 윈도우즈 7을 CR200에 탑재되는 Advantech 사의 PCM-3362 보드에 설치하여 소프트웨어 타이머의 성능을 10ms부터 100ms까지 각각 실험하였다. 실험결과에 따르면, 두 운영체제에서 모두 누락이 없이 타이머 동작이 수행되었으며, 10ms 간격으로 타이머를 동작하였을 때에 우분투에서는 평균 오차가 $41{\mu}s$이었고 윈도우즈 7에서는 7.7ms였다. 윈도우즈 7에서의 오차는 100Hz 제어 주기에 사용하기에 적합하지 않지만, 우분투에서의 오차는 제어 주기 간격의 0.41%에 불과하기 때문에 해저보행로봇의 실시간 제어에 영향을 주지 않는 오차이다. 따라서 CR200의 임베디드 컴퓨터와 선상제어실의 원격제어 컴퓨터는 우분투 운영체제 상에서 소프트웨어 타이머를 이용하여 상호 연동되도록 구현할 예정이다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.8
• /
• pp.1374-1380
• /
• 2002

Recently, the use of Robot increase little by little for the purpose of developing a welding quality and productivity in the welding part. It is more important to contact the seam for arc welding before moving a welding robot. There are two types of method to contact the seam namely contact and non-contact type largely. In this paper, image processing sensor(a kind of non-contact sensor) is concerned to track the seam by using laser diode and CCD camera. A structured laser diode's light illuminated on the weld groove and the reflected shape is introduced by CCD camera. The image board captures this image and software analyzes this image. The robot is moved and welded exactly as acquired image X-Y data is changed with robot's X-Y value. Also, most of seam tracking are considered by changing the program simply in case of the different weld groove of plane surface.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.05a
• /
• pp.460-464
• /
• 2001

Recently, the use of Robot increase little by little for the purpose of developing a welding quality and productivity in the arc welding part. It is more important to contact the seam for arc welding before moving a welding robot. There are two types of method to contact the seam namely contact and noncontact type largely In this paper, image processing sensor(a kind of non-contact sensor) is concerned to track the seam by using laser diode and CCD camera. A structured laser diode's light illuminated on the weld groove and the reflected shape is introduced by CCD camera. The image board captures this image and software analyzes this image. The robot is moved and welded exactly as acquired image X-Y data is changed with robot's X-Y value. Also, most of seam tracking are considered by changing the program simply in case of the different weld prove of plane surface.