• 제목/요약/키워드: robot detection

검색결과 584건 처리시간 0.025초

편로드 유압실린더 내부 누유 검출을 위한 T—S 퍼지 모델 기반 샘플치 관측기 설계: LMI 접근법 (T—S Fuzzy Model-based Sampled-data Observer Design for Detecting Internal Oil Leakage in Single-rod Hydraulic Cylinder: LMI Approach)

  • 지성철;김효곤;박정우;이문직;강형주;이계홍
    • 한국해양공학회지
    • /
    • 제30권5호
    • /
    • pp.405-414
    • /
    • 2016
  • This paper presents an internal oil leakage detection problem for a hydraulic single-rod cylinder. We derive the dynamics of the hydraulic cylinder as a state space model, and then design a T—S fuzzy model-based fault detection observer. We adopt an H observer design scheme so that the observer is robust against disturbance and relatively sensitive to the leakage fault. Sufficient design conditions are derived in the form of linear matrix inequalities. A numerical example is provided to verify the proposed techniques.

딥러닝과 확률모델을 이용한 실시간 토마토 개체 추적 알고리즘 (Real-Time Tomato Instance Tracking Algorithm by using Deep Learning and Probability Model)

  • 고광은;박현지;장인훈
    • 로봇학회논문지
    • /
    • 제16권1호
    • /
    • pp.49-55
    • /
    • 2021
  • Recently, a smart farm technology is drawing attention as an alternative to the decline of farm labor population problems due to the aging society. Especially, there is an increasing demand for automatic harvesting system that can be commercialized in the market. Pre-harvest crop detection is the most important issue for the harvesting robot system in a real-world environment. In this paper, we proposed a real-time tomato instance tracking algorithm by using deep learning and probability models. In general, It is hard to keep track of the same tomato instance between successive frames, because the tomato growing environment is disturbed by the change of lighting condition and a background clutter without a stochastic approach. Therefore, this work suggests that individual tomato object detection for each frame is conducted by YOLOv3 model, and the continuous instance tracking between frames is performed by Kalman filter and probability model. We have verified the performance of the proposed method, an experiment was shown a good result in real-world test data.

증분형 엔코더를 이용한 로봇 관절의 절대위치 검출 (Detection of Absolute Position of Robot Joint Using Incremental Encoders)

  • 임재식;이영진
    • 제어로봇시스템학회논문지
    • /
    • 제21권6호
    • /
    • pp.577-582
    • /
    • 2015
  • This paper proposes an efficient detection of absolute position of a robot joint using two incremental encoders. We considers a robot joint comprising a motor, a reducer, two encoders, and a motor drive. An incremental(first) encoder provides motor's rotor position or input position of reducer while another incremental(second) encoder does output position of the reducer. A table is made where the relationship between the first and the second encoder counts is recorded. The key point is placed where the table is constructed: when a pulse occurs in the second encoder, there exists a corresponding unique count value of the first encoder. The absolute position is detected using the table by searching the second encoder position corresponding to the first encoder count value when a pulse occurs in the second encoder. The proposed method needs a small rotation, as just one second encoder's pulse angle, for the initial absolute position detection.

유압실린더 내부 누유 검출을 위한 H 관측기 설계 (H Observer Design for Detecting Internal Oil Leakage in a Hydraulic Cylinder)

  • 지성철;강형주;이문직;이계홍
    • 제어로봇시스템학회논문지
    • /
    • 제22권2호
    • /
    • pp.117-125
    • /
    • 2016
  • This paper presents the internal oil leakage detection problem for a hydraulic double-rod cylinder. We represent the dynamics of the hydraulic cylinder as a convex combination of linear equations. To detect oil leakage, we propose a model-based fault detection observer design scheme. The observer is designed to be robust against disturbance. Sufficient design conditions are derived in the form of linear matrix inequalities. A numerical example is provided to verify the proposed techniques.

Study on the Effective Solution of Obstacle Avoidance Strategy for a Mobile Robot in the Guideline Navigation

  • Wang, Jiwu;Sugisaka, Masanori
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2005년도 ICCAS
    • /
    • pp.2015-2018
    • /
    • 2005
  • Obstacle avoidance is a basic skill to make a mobile robot move effectively and safely even in any arbitrarily given environment. Because of the difficulty of self-location caused by unavoidable slip and drift errors of sensors and effective detection of any encountered obstacle, only finite and simple obstacle avoidance strategies can be carried out. In this paper we mainly explored how to make a robot perform effectively obstacle detection and avoidance in the guideline navigation with one CCD video camera and some supersonic sensors. Making use of the specially designed guideline, the detection and calculation of the geometric dimensions of the encountered obstacle became simpler. And possible avoidance strategies appropriate to our navigation were studied and the simulations results were given.

  • PDF

의료서비스로봇을 위한 얼굴추출 방법 (Face Detection for Medical Service Robot)

  • 박세현;류정탁
    • 한국산업정보학회논문지
    • /
    • 제16권3호
    • /
    • pp.1-10
    • /
    • 2011
  • 본 논문에서는 의료 서비스로봇을 위한 얼굴추출 방법을 제안한다. 제안된 방법은 기존의 얼굴 추출방법의 단점을 보완하여 배경과 조명에 강건한 방법이다. 본 방법은 먼저 평균 이동 알고리즘을 이용하여 배경을 제거하고, 컬러 공간에서 얼굴을 추출한 후 외형 기반의 Haar-like feature 방식으로 최종 얼굴을 검출하게 된다. 제안된 시스템의 효율을 위해 실험을 하였고, 실험결과가 제안된 방법이 의료서비스 로봇에 적용 가능함을 보였다.

감광성 CNT 페이스트를 이용한 IED 폭발물 제거로봇 탐지전극 형성에 관한 연구 (A Study on the Formation of Detection Electrode for the IED Removal Robot by Using A Photosensitive CNT Paste)

  • 권혜진
    • 한국전기전자재료학회논문지
    • /
    • 제31권4호
    • /
    • pp.231-237
    • /
    • 2018
  • In this study, two important requirements for the home production of a robot to detect and remove improvised explosive devices (IEDs) are presented in terms of the total cost for robot system development and the performance improvement of the mine detection technology. Firstly, cost analyses were performed in order to provide a reasonable solution following an engineering estimate method. As a result, the total cost for a mass production system without the mine detection system was estimated to be approximately 396 million won. For the case including the mine detection system, the total cost was estimated to be approximately 411 million won, in which labor costs and overhead charges were slightly increased and the material costs for the mine detection system were negligible. Secondly, a method for fabricating the carbon nanotube (CNT) based gas detection sensor was studied. The detection electrodes were formed by a photolithography process using a photosensitive CNT paste. As a result, this method was shown to be a scalable and expandable technology for producing excellent mine detection sensors. In particular, it was found that surface treatments by using adhesive taping or ion beam bombardment methods are effective for exposing the CNTs to the ambient air environment. Fowler-Nordheim (F-N) plots were obtained from the electron-emission characteristics of the surface treated CNT paste. The F-N plot suggests that sufficient electrons are available for transport between CNT surfaces and chemical molecules, which will make an effective chemiresistive sensor for the advanced IED detection system.

야외 순찰로봇을 위한 단일 레이저거리센서 기반 충돌 회피 주행 제어기법 개발 (Motion Control of an Outdoor Patrol Robot using a Single Laser Range Finder)

  • 홍승범;신유진;정우진
    • 제어로봇시스템학회논문지
    • /
    • 제16권4호
    • /
    • pp.361-367
    • /
    • 2010
  • This paper reports the development of a mobile robot for patrol using a single laser range finder. A Laser range finder is useful for outdoor environment regardless of illumination change or various weather conditions. In this paper we combined the motion control of the mobile robot and the algorithm for detecting the outdoor environment. For obstacle avoidance, we adopted the Vector Field Histogram algorithm. A laser range finder is mounted on the mobile robot and looking down the road with a small tilt angle. We propose an algorithm for detecting the surface of the road. The outdoor patrol robot platform is equipped with a DGPS system, a gyro-compass sensor, and a laser range finder. The proposed obstacle avoidance and road detection algorithms were experimentally tested in success.

FPGA-based ARX-Laguerre PIO fault diagnosis in robot manipulator

  • Piltan, Farzin;Kim, Jong-Myon
    • Advances in robotics research
    • /
    • 제2권1호
    • /
    • pp.99-112
    • /
    • 2018
  • The main contribution of this work is the design of a field programmable gate array (FPGA) based ARX-Laguerre proportional-integral observation (PIO) system for fault detection and identification (FDI) in a multi-input, multi-output (MIMO) nonlinear uncertain dynamical robot manipulators. An ARX-Laguerre method was used in this study to dynamic modeling the robot manipulator in the presence of uncertainty and disturbance. To address the challenges of robustness, fault detection, isolation, and estimation the proposed FPGA-based PI observer was applied to the ARX-Laguerre robot model. The effectiveness and accuracy of FPGA based ARX-Laguerre PIO was tested by first three degrees of the freedom PUMA robot manipulator, yielding 6.3%, 10.73%, and 4.23%, average performance improvement for three types of faults (e.g., actuator fault, sensor faults, and composite fault), respectively.

정적 Passive RFID 태그를 이용한 지능적인 로봇위치추정기법 (An Intelligent Estimation Method of Robot-location based on Passive RFID Tags in Static Position)

  • 문승욱;지용관;박장현
    • 제어로봇시스템학회논문지
    • /
    • 제12궈1호
    • /
    • pp.9-14
    • /
    • 2006
  • This paper presents methods of robot localization using recent radio frequency identification technology. If the absolute position and orientation of a tag are given in an indoor environment where RFID tags are installed, a robot can estimate its location using the relationship of the identified tag and the robot in a relative coordinate. To derive this relationship, we propose three estimation techniques using a model of a RFID reader, the direction of identification and the detection range. In this algorithm, a suitable estimation method is selected out of the three proposed techniques depending on the situations and trajectory of robot in the detection range. Simulation and experimental results show that the proposed methods can provide good performance for localization.