• Journal of Korean Institute of Industrial Engineers
• /
• v.18 no.2
• /
• pp.83-97
• /
• 1992

A new approach, to seam tracking for robotic are welding is proposed. In this approach, the weld model is a snapshot image and the acquired image is analyzed and compared to the welding database which contains CAD data, weld positions, weld parameters, etc. This paper presents a fast and robust algorithm for the Hough Transform. This modified Hough Transform(MHT) algorithm uses the least-squares regression analysis method in order to approximate the edge lines more precisely, and leads to a significant reduction in both computation and storage. In comparison with the conventional seam tracking methods, this new approach has the advantages of low cost, continuous welding, and various type welding.

• Journal of Korean Institute of Industrial Engineers
• /
• v.18 no.2
• /
• pp.131-140
• /
• 1992

The purpose of this study is to improve the performance of robot by providing visual function with robot and developing high-functioned controller and control program. The developed high-functioned controller and software have the better accuracy and flexibility in the movement of robot by complementing the existing robot controller and software problems. To provide visual function to robot, camera calibration, thresholding and contouring tools are also developed and applied in this study. These tools help robot recognize the central points and orientations of objects on work-bench.

• Proceedings of the KIEE Conference
• /
• 1994.11a
• /
• pp.299-301
• /
• 1994

Visual feedback has traditionally been used in robot manipulator control to a limited extent. However in varying environment, visual data is needed to control the manipulator to complete the desired task. In this paper we present a method of manipulator control scheme called image-based visual servo. In this scheme we use image data as feedback to control robot manipulator. And we also show the experimental results with an industrial robot manipulator.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.353-356
• /
• 2003

본 논문은 이동로봇의 다양한 작업들 중에 선행하는 물체를 안정하게 추종하는 동작중 예기치 못한 움직이는 장애물의 효과적인 회피 방법을 고려한다. 센서 기반의 이동로보트에서는 이동물체 추종과 충돌회피를 센서정보에 의존해서 해결해야 하는데 동일한 센서 정보로 추종물체와 충돌물체를 구분하는 것이 쉽지 않은 문제이다. 또한 명확히 규정되지 않은 환경에서 적용하기 어렵다. 따라서 본 논문에서는 이와 같이 명확히 규정되지 않은 환경에서 선행물체의 안정한 추종과 추종 중에 마주치는 이동 장애물에 대한 충돌회피를 위하여 이동로봇의 상태 판단에 따라 구분된 행동 선택 모드를 제안하고 실험적으로 확인한다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.11 no.1
• /
• pp.21-32
• /
• 1985

Presented in this paper is a procedure of developing graphical simulation software for planning robot welding processes. Welding is by far the highest application area for industrial robots, and it has been in great need of such a simulator in designing robot work cells, in justifying the economics of robot welding and in planning robotized welding operations. The model of a robot welding cell consists of four components: They are an welding structure which is a collection of plates to be welded, a positioner to hold the welding structure, a robot with a weld torch, and a set of welding lines (in case of arc welding). Welding structure is modeled by using the reference plane concept and is represented as boundary file which is widely used in solid modeling. Robot itself is modeled as a kinematic linkage system. Also included in the model are such technical constraints as weaving patterns and inclination allowances for each weld joint type. An interactive means is provided to input the welding structure and welding lines on a graphics terminal. Upon completion of input, the program displays the welding structure and welding lines and calculates the center of mass which is used in determining positioner configurations. For a given positioner and robot configuration, the welding line segments that can be covered by the robot are identified, enabling to calculate the robot weld ratio and cycle time. The program is written in FORTRAN for a VAX computer with a Tektronix 4114 graphic terminal.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.10a
• /
• pp.550-555
• /
• 1993

The aim of this paper is to present the development of visual seam tracking system equipped with visual range finder. The visual range finder, which consists of a CCD camera and a diode laser system with line generating optics, developed to recognize the types of weld joints and detect the location of weld joints. In practical applications, however, images of the weld joints are often degraded due to spatters, are flares, surface specularity, and welding smoke. To overcome the problem, this paper proposes a syntactic approach which is a class of artificial intelligence techniques. In the approach, the type of weld joint is inferred based upon the production rules which are linguiques grammars consisting of a set of line and junction primitives of laser strip image projected on weld joint. The production rules eliminate several noisy primitives to create new primitives through the merging process of primitives. After the recognition of weld joint, arc welding is started and the location of weld joints is repeatedly detected using a spring model-based template matching in which the template model is a by-product of the recognition process of weld joint. To show the effectiveness of the proposed approach a series of experiments-identification and robotic tracking-are conducted for four different types of weld joints.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.9
• /
• pp.104-114
• /
• 1995

Mathematical models of industrial robots or manipulators are composed of highly nonlinear equations with nonlinear couplings between the variables of motions. These nonlin- earities were not considered important in the first stage that the working speed of the manipulator was not so fast, but the effect of nonlinear forces has become serious, as the working speed has been increased. So more improvement of performance cannot be expected by the control of manipulator using approximate linearization. As an approach for solving these problems, there is a method that eliminates nonlinear theory, which makes possible cecoupling of coupling terms and arbitrary arranging of poles is briefly introduced in this study. When the theory is applied to design the control law, its feasibility is examined whether the reasonable control results are obtained by simulating position, velocity, torque and tracing trajectory. The relations between the coefficients of the linearized differential equations and the maximum error and torque for the prescribed trajectory are also examined. Finally, the method for selecting the values for getting the most rapid and precise response within maximum torque of each drive is suggested in the choice of coefficients of characteristic equations which are obtained as a result of the control.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.1 no.2
• /
• pp.49-55
• /
• 2000

In this paper, we show that our previously proposed second-order iterative learning control method with feedback is more effective and has better convergence performance than the second-order iterative learning control method without feedback, particularly in the case of the existence of initial condition errors. Also the convergence proof of the proposed method is given. And through the simulation result of applying the proposed method to the linear time-varying system, we show that our proposed method has enhanced robustness and stability in case of the existence of initial condition errors.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.940-943
• /
• 1996

In teleoperating, as seeing the monitor screen obtained from a camera instituted in the working environment, human operator generally controls the slave arm. Because we can see only 2-D image in a monitor, human operator does not know the depth information and can not work with high accuracy. In this paper, we proposed a traded control method using an visual sensor for the purpose of solving this problem. We can control a teleoperation system with precision when we use the proposed algorithm. Not only a human operator command but also an autonomous visual sensor feedback command is given to a slave arm for the purpose of coincidence current image features and target image features. When the slave arm place in a distant place from the target position, human operator can know very well the difference between the desired image features and the current image features, but calculated visual sensor command have big errors. And when the slave arm is near the target position, the state of affairs is changed conversely. With this visual sensor feedback, human does not need coincide the detail difference between the desired image features and the current image features and proposed method can work with higher accuracy than other method without, sensor feedback. The effectiveness of the proposed control method is verified through series of experiments.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.679-684
• /
• 1989

In this paper, we describe the PTP notion of robot manipulators by neural networks. The PTP motion requires the inverse kinematic redline and the joint trajectory generation algorithm. We use the multi-layered Perceptron neural networks and the Error Back Propagation(EBP) learning rule for inverse kinematic problems. Varying the number of hidden layers and the neurons of each hidden layer, we investigate the performance of the neural networks. Increasing the number of learning sweeps, we also discuss the performance of the neural networks. We propose a method for solving the inverse kinematic problems by adding the error compensation neural networks(ECNN). And, we implement the neural networks proposed by Grossberg et al. for automatic trajectory generation and discuss the problems in detail. Applying the neural networks to the current trajectory generation problems, we can refute the computation time for trajectory generation.