• Title/Summary/Keyword: Robot vision

검색결과 878건 처리시간 0.031초

Gyro/Vision Sensor Module을 이용한 주행 로봇의 미끄러짐 및 넘어짐 회피 제어 기법 (Control Method of Mobile Robots for Avoiding Slip and Turnover on Sloped Terrain Using a Gyro/Vision Sensor Module)

  • 이정희;박재병;이범희
    • 제어로봇시스템학회논문지
    • /
    • 제11권8호
    • /
    • pp.669-677
    • /
    • 2005
  • This acticle describes the control method of mobile robots for avoiding slip and turnover on sloped terrain. An inexpensive gyro/vision sensor module is suggested for obtaining the information of terrain at present and future. Using the terrain information and the robot state, the maximum limit velocity of the forward velocity of the robot is defined fur avoiding slip and turnover of the robot. Simultaneously the maximum value of the robot velocity is reflected to an operator in the form of reflective force on a forte feedback joystick. Consequently the operator can recognize the maximum velocity of the robot determined by the terrain information and the robot state. In this point of view, the inconsistency of the robot movement and the user's command caused by the limit velocity of the robot can be compensated by the reflective force. The experimenal results show the effectiveness of the suggested method.

글로벌 비젼을 이용한 자동제어 휴머노이드 축구시스템 설계 (Implementation of Active Humanoid Robot Soccer System Using Global Vision)

  • 구자일
    • 전자공학회논문지 IE
    • /
    • 제45권2호
    • /
    • pp.28-33
    • /
    • 2008
  • 본 논문에서는 휴머노이드를 이용한 로봇 축구 시스템을 새롭게 제안하며, 다수의 인간형 로봇을 제어하는 방법과 축구 경기를 하기 위한 전략 알고리즘 등에 대해 기술하였다. 로봇의 위치와 방향을 파악하기 위해서 로봇의 위쪽 어깨 부분에 각각의 로봇을 구분할 수 있는 칼라 태그를 부착하였고, 빠른 위치와 방향 인식을 위해 전용의 PC를 통해 영상인식을 수행하였다. 본 논문에서 제안한 휴머노이드 로봇 축구 시스템은 기존의 바퀴 구동형 축구 로봇을 한 단계 발전시킨 것으로, 앞으로 많은 연구를 통하여, 인간처럼 자율 이동이 가능한 로봇 축구 경기가 가능하리라 본다.

우주로봇 자율제어 테스트 베드 (Test bed for autonomous controlled space robot)

  • 최종현;백윤수;박종오
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
    • /
    • pp.1828-1831
    • /
    • 1997
  • this paper, to represent the robot motion approximately in space, delas with algorithm for position recognition of space robot, target and obstacle with vision system in 2-D. And also there are algorithms for precise distance-measuring and calibration usign laser displacement system, and for trajectory selection for optimizing moving to object, and for robot locomtion with air-thrust valve. And the software synthesizing of these algorithms hleps operator to realize the situation certainly and perform the job without any difficulty.

  • PDF

비전 센서와 초음파 센서를 이용한 이동 로봇의 자율 주행 알고리즘 (An Algorithm of Autonomous Navigation for Mobile Robot using Vision Sensor and Ultrasonic Sensor)

  • 이재광;박종훈;허욱열
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
    • /
    • pp.19-22
    • /
    • 2003
  • This paper proposes an algorithm for navigation of an autonomous mobile robot with vision sensor. For obstacle avoidance, we used a curvature trajectory method. Using this method, translational and rotational speeds are controlled independently and the mobile robot traces a smooth curvature trajectory that consists of circle trajectories to a target point. While trying to avoid obstacles, the robot fan be goal-directed using curvature trajectory.

  • PDF

사각장치에 의해 감지된 가이드 마크를 이용한 이동 로보트의 효과적인 항법 (Effective Navigation of a Mobile Robot Using Guide-Marks Sensed through Vision)

  • 조동권;권호열;서일홍
    • 대한전기학회논문지
    • /
    • 제38권12호
    • /
    • pp.963-970
    • /
    • 1989
  • The navigation problem for a mobile robot is investigated. Specifically, it is proposed that simple guide-marks be introduced and the navigation scheme be generated in conjunction with the guide-marks sensed through camera vision. For autonomous navigation, it was shown that a triple guide-mark system is more effective than a single guide-mark in estimating the position and orientation of mobile robot itself. The navigation system is tested via a mobile robot HERO-I equipped with a single camera in laboratory environment.

  • PDF

Development of an Embedded Vision Platform for Internet-based Robot Control

  • Kim, Tae-Hee;Jeon, Jae-Wook
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2002년도 ICCAS
    • /
    • pp.116.4-116
    • /
    • 2002
  • $\textbullet$In case of using overhead camera system, mobile robot moves under static working area. $\textbullet$Mobile robot must use onboard camera system to work under wide working area. $\textbullet$Mobile robot must have wireless LAN to remove restriction of movement. $\textbullet$Onboard camera system must have wireless LAN environment. $\textbullet$We develop embedded vision platform using onboard camera.

  • PDF

영상추적 로봇 암 시스템 (Robot manipulator Visual servoing system)

  • 정윤용;최승진;현웅근
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2007년도 제38회 하계학술대회
    • /
    • pp.1771-1772
    • /
    • 2007
  • The purpose of this project is to develop the visual servoing system with 5d.o.f robot manipulator. For this, we developed robot manipulator by using 5 serial RC motors and the visual system is also developed by using low cost USB CCD camera. RISC MPU ATMEGA128 is main controller MPU for the robot manipulator. To control the manipulator Kinematics was analyzed and GUI, API for vision system also were developed.

  • PDF

자코비안 불확실성을 포함하는 로봇 매니퓰레이터의 영상기반 강인제어 (Vision-Based Robust Control of Robot Manipulators with Jacobian Uncertainty)

  • 김진수;지민석;이강웅
    • 한국항행학회논문지
    • /
    • 제10권2호
    • /
    • pp.113-120
    • /
    • 2006
  • 본 논문에서는 로봇 매니퓰레이터가 기준 궤적을 추종할 수 있도록 영상기반 강인제어기를 제안하였다. 카메라로부터 획득된 목표물의 특징점을 원하는 특징점 좌표로 로봇이 이동할 수 있도록 기준 궤적을 생성하고, 제어 입력에 포함되는 로봇 동역학부의 파라미터 불확실성을 보상하기 위한 강인제어기를 설계하였다. 또한 자코비안에 불확실성이 존재하는 경우 이를 보상하기 위한 제어 입력을 갖는 영상기반 강인제어기를 제안하였다. 시스템의 안정도는 Lyapunov 안정도 판별법을 이용하여 검증하였다. 5-링크 2 자유도의 로봇 매니퓰레이터를 대상으로 제안된 제어기를 적용한 모의실험과 실험을 통하여 제어 성능을 입증하였다.

  • PDF

Development of an Automatic Label Attaching System Using a Robot Vision in Variable Situation

  • Lee, Young-Jung
    • 한국공작기계학회:학술대회논문집
    • /
    • 한국공작기계학회 2004년도 춘계학술대회 논문집
    • /
    • pp.225-230
    • /
    • 2004
  • A cold & hot rolling coil production line of iron nill consists of a kind of coherent automatic process, but an automatic labelling process still had technical difficulties in the automation of its process. The reason for difficulties in building an automatic process is that quantitative data for each rolled coil from every shipping is not easy to receive from the previous process. it is not possible to apply for a general and simple purpose robot that is actually worked through a taught position to the process because the size and direction of the coi1 has differed on every shipping. From these reasons. we introduce a robot vision system to accept an expected variable situation and to ensure the stability and flexibility of the process. This paper examines a study applied for similar cases and finds the position and direction of relied coil using the moment invariant algorithm proposed by Hu. In addition. the camera calibration and position error compensation algorithm is applied by the analysis of the relationship of transition in a space coordinate system. The construction of a robot vision system proposed by this paper is a more intellectual system than that of the automatic labelling system. which is already used to the Daihen steel nill of NEW JAPAN steel mill co. Ltd in Japan, and shows a better independent operation in the field of production.

  • PDF

무인로봇 정밀위치추정을 위한 전술통신 및 영상 기반의 통합항법 성능 분석 (The Performance Analysis of Integrated Navigation System Based on the Tactical Communication and VISION for the Accurate Localization of Unmanned Robot)

  • 최지훈;박용운;송재복;권인소
    • 한국군사과학기술학회지
    • /
    • 제14권2호
    • /
    • pp.271-280
    • /
    • 2011
  • This paper presents a navigation system based on the tactical communication and vision system in outdoor environments which is applied to unmanned robot for perimeter surveillance operations. GPS errors of robot are compensated by the reference station of C2(command and control) vehicle and WiBro(Wireless Broadband) is used for the communication between two systems. In the outdoor environments, GPS signals can be easily blocked due to trees and buildings. In this environments, however, vision system is very efficient because there are many features. With the feature MAP around the operation environments, the robot can estimate the position by the image matching and pose estimation. In the navigation system, thus, operation modes is switched by navigation manager according to some environment conditions. The experimental results show that the unmanned robot can estimate the position very accurately in outdoor environment.