• 제목/요약/키워드: Robot Knowledge

검색결과 256건 처리시간 0.032초

유전알고리즘을 이용한 지능형 로봇의 주행 제어 (The Navigation Control for Intelligent Robot Using Genetic Algorithms)

  • 주영훈;조상균
    • 한국지능시스템학회논문지
    • /
    • 제15권4호
    • /
    • pp.451-456
    • /
    • 2005
  • 본 논문에서는 유전 알고리즘의 한 방법인 mGA를 이용하여 지능형 로봇의 주행제어 방법을 제안한다. 지능형 로봇의 주행에 필요한 퍼지 제어기의 설계는 전문가적 지식에 많이 의존한다. 이러한 전문가의 경험에 의해 설정된 퍼지 제어기의 여러 구성 요소들의 매개 변수 값들이 최적의 값이라는 보장이 없다. 상기 문제를 해결하기 위해 본 논문에서는 퍼지 제어 기의 구성 요소인 퍼지 규칙의 수와 멤버쉽 함수의 매개 변수들을 mGA를 이용하여 동정하는 방법을 제안한다. 제안된 방법에 의해 동정된 매개 변수들의 정확성과 효율성을 평가하기 위하여 지능형 로봇의 벽면 주행에 대한 모의실험을 수행한다.

강인한 힘 추적 제어기를 적용한 콘크리트 표면 추종 로봇 시스템 (Applying the Robust Force Tracking Controller to assist the Sealing Robot System on a Concrete Surface)

  • 조철주;임계영
    • 제어로봇시스템학회논문지
    • /
    • 제22권6호
    • /
    • pp.389-396
    • /
    • 2016
  • The sealing robot must be able to calculate the slope of a contact surface for complete adherence of the sealing on different concrete shapes. After the slope is obtained, the robot will track on the surface of the concrete, but this process contains an error in the actual purpose of the force command. The reason this a phenomenon occurs, the non-linearity of the contact surface and the end-effector, is due to parasitic coupling. Errors like make it difficult to measure accurately the respective factors. Therefore, it is regarded as a disturbance that occurs when it follows the work surface it. In this paper, we selected the friction coefficient of the surface as a control factor and designed a compensator to reduce effects of disturbance. Finally, in view of the non-linearity of the end-effector of a robot to contact surfaces directly, we propose a robust force tracking controller in the finite range for managing disturbances that occur during the sealing.

Three Examples of Learning Robots

  • Mashiro, Oya;Graefe, Volker
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2001년도 ICCAS
    • /
    • pp.147.1-147
    • /
    • 2001
  • Future robots, especially service and personal robots, will need much more intelligence, robustness and user-friendliness. The ability to learn contributes to these characteristics and is, therefore, becoming more and more important. Three of the numerous varieties of learning are discussed together with results of real-world experiments with three autonomous robots: (1) the acquisition of map knowledge by a mobile robot, allowing it to navigate in a network of corridors, (2) the acquisition of motion control knowledge by a calibration-free manipulator, allowing it to gain task-related experience and improve its manipulation skills while it is working, and (3) the ability to learn how to perform service tasks ...

  • PDF

학습제어기를 이용한 직접구동형 로봇의 힘제어 (Force control of the direct-drive robot using learning controller)

  • 황용연
    • 대한기계학회논문집A
    • /
    • 제21권11호
    • /
    • pp.1819-1826
    • /
    • 1997
  • Direct-drive robots are suitable to the position and force control with high accuracy, but it is difficult to design a controller because of the system's nonlinearity and link-interactions. This paper is concerned with the study of the force control of direct-drive robots. The proposed algorithm consists of feedback controllers and a neural network. After the completion of learning, the output of feedback controller is nearly equal to zero, and the neural network controller plays an important role in the control system. Therefore, the optimum retuning of parameters of feedback controllers is unnecessary. In other words, the proposed algorithm does not require any knowledge of the controlled system in advance. The effectiveness of the proposed algorithm is demonstrated by the experiment on the force control of the parallelogram link-type direct-drive robot.

신경회로망을 이용한 직접 구동형 로봇의 위치제어에 관한 연구 (A Study on Position Control of the Direct Drive Robot Using Neural Networks)

  • 신춘식;황용연;노창주
    • Journal of Advanced Marine Engineering and Technology
    • /
    • 제21권3호
    • /
    • pp.284-292
    • /
    • 1997
  • This paper is concerned with position control of direct drive robots. The proposed algorithm consists of the feedback controller and neural networks. Mter the completion of learning, the output of the feedback controller is nearly equal to zero, and the neural networks play an important role in the control system. Therefore, the optimum retuning of control parameters is unnecessary. In other words, the proposed algorithm does not need any knowledge of the con¬trolled system in advance. The effectiveness of the proposed algorithm is demonstrated by the experiment on the position control of a parallelogram link-type direct drive robot.

  • PDF

유압구동 로보트의 제어를 위한 유압 실린더 모델 파라미터 추정 (Dynamic Model Parameter Estimation of Hydraulic Cylinder for Robot Manipulator Control)

  • 최명환
    • 산업기술연구
    • /
    • 제16권
    • /
    • pp.113-121
    • /
    • 1996
  • In the early developmental stages of robotics,hydraulics played an important role. As the power-to-weight ratio of electric motors increased, they eventually replaced hydraulic actuators in robot manipulators. Recently, however, task requirements have dictated that the manipulator payload capacity increase to accomodate greater payload, greater length, greater reaction forces, and hydraulic actusators are being studied as an effective form of robot actuation again. For efficient control of hydraulic actuators, the knowledge of its dynamic equation is essential. However, the dynamic equation of hydraulic actuators are nonlinear, and the dynamic coefficients are time varying. In this paper, an estimation algorithm of the dynamic coefficients of the hydraulic piston dynamics are formulated. Simulation results are presented to show the possibility of the parameter estimation.

  • PDF

DIRECT INVERSE ROBOT CALIBRATION USING CMLAN (CEREBELLAR MODEL LINEAR ASSOCIATOR NET)

  • Choi, D.Y.;Hwang, H.
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
    • /
    • pp.1173-1177
    • /
    • 1990
  • Cerebellar Model Linear Associator Net(CMLAN), a kind of neuro-net based adaptive control function generator, was applied to the problem of direct inverse calibration of three and six d.o.f. POMA 560 robot. Since CMLAN autonomously maps and generalizes a desired system function via learning on the sampled input/output pair nodes, CMLAN allows no knowledge in system modeling and other error sources. The CMLAN based direct inverse calibration avoids the complex procedure of identifying various system parameters such as geometric(kinematic) or nongeometric(dynamic) ones and generates the corresponding desired compensated joint commands directly to each joint for given target commands in the world coordinate. The generated net outputs automatically handles the effect of unknown system parameters and dynamic error sources. On-line sequential learning on the prespecified sampled nodes requires only the measurement of the corresponding tool tip locations for three d.o.f. manipulator but location and orientation for six d.o.f. manipulator. The proposed calibration procedure can be applied to any robot.

  • PDF

신경회로망을 이용한 로봇 매니퓰레이터의 힘 제어에 관한 연구 (A Study on the Force Control of a Robot Manipulator Using Neural Networks)

  • 황용연
    • Journal of Advanced Marine Engineering and Technology
    • /
    • 제21권4호
    • /
    • pp.404-413
    • /
    • 1997
  • Direct-drive robots are suitable to position and force control with high accuracy, but it is difficult to design a controller which gives satisfactory perfonnance because of the system's nonlinearity and link-interactions. This paper is concerned with the force control of direct-drive robots. The pro¬posed algorithm consists of feedback controllers and a neural network. Mter the completion of learning, the outputs of feedback controllers are nearly equal to zero, and the neural network con¬troller plays an important role in the control system. Therefore, the optimum adjustment of parameters of feedback controllers is unnecessary. In other words, the proposed algorithm does not need any knowledge of the controlled system in advance. The effectiveness of the proposed algo¬rithm is demonstrated by the experiment on the force control of a parallelogram link-type direct¬drive robot.

  • PDF

선소 정보를 이용한 로봇의 경로계획 (The Path Planning for Mobile Robot Using the Line Segment Information)

  • 김병곤;이쾌희
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
    • /
    • pp.514-516
    • /
    • 1998
  • A Mobile Robot should be able to navigate safely in the workspaces without any additional human's helps. In this paper, a method to generate the safe path to avoid the unknown obstacles using the pre-knowledge of the workspaces was proposed. For the efficiency of the algorithm, it is proposed to model the obstacles as the line segments in numerical map, which can reduce the required memory size and give the simple forms. To make the environments map, we used the Hough transform and the sonar measurements is converted to the set of line segments by Hough transform. In this algorithm, the subgoals are generated to avoid the obstacles until a mobile robot arrives the final position using the proposed environmental model.

  • PDF

불확실성을 포함한 로봇의 확장된 견실 하이브리드 제어 (An Expanded Robust Hybrid Control for Uncertain Robot Manipulators)

  • 김재홍;하인철;한명철
    • 제어로봇시스템학회논문지
    • /
    • 제7권12호
    • /
    • pp.980-984
    • /
    • 2001
  • When robot manipulatros as mathematically modeled. uncetainties may not be avoided. The uncertain factors come from imperfect knowledge of system parameters, payload change. friction, external disturbance and etc. In this work, we proposed a class of robust hybrid control of manipulatosrs. We propose a class of expanded robust hybrid control with the separated bound function and the simulation results are provided to show the effectiveness of the algorithm.

  • PDF