http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
유황열,김무림,유기성,최진태 제어로봇시스템학회 2011 제어로봇시스템학회 각 지부별 자료집 Vol.2011 No.12
Factory automation have been effectively acting on the existing infrastructure of the steel industry in the perspective of increasing production, reducing cost, increasing customer satisfaction and to sustain the global competition. Many workers, however, have still complained about their hard work due to the two twelve-hour shifts and continuously repetitive jobs under an unstructured environment. To make the unstructured process or jobs automated, much research has gone into how industry robots could function autonomously. As a result, many jobs and processes that have routinely operated before have been done without human intervention in the terms of fully automated or semi-automated way. In this paper, we introduce an interactive and cooperative system being capable of complementing various and unstructured tasks between human operator and the industrial robot. The industrial robot understands what the human operators’ intention is through a force/torque sensor mounted in the end of robot end-effector and helps them to construct the heavy refractory bricks inside the converter. By doing so, the human operator can reduce painful musculoskeletal disease. This paper presents application of the human-robot cooperative system for constructing the refractory bricks in the converter.
유황열,임태규,임승현,한준희 제어로봇시스템학회 2011 제어로봇시스템학회 각 지부별 자료집 Vol.2011 No.12
We propose a novel background subtraction algorithm for the videos captured by a mobile vision system. In our technique, spatio-temproal approach is used to generate foreground and background models, and likelihood maps are computed based on the models. After that, an energy minimization technique is applied to the likelihood maps for segmentation. Block-wise models are propagated form the previous frame using motion information, and pixel-wise foreground/background likelihoods and labels in the current frame are estimated based on these models. A graph-cut algorithm performs segmentation based on the foreground/background likelihood maps, and the segmentation result is employed to update the motion of each segment in a block. We tested our framework with various challenging videos involving large camera and object motions, significant background changes and clutters.
유황열(HwangRyol Ryu),김무림,유기성 제어로봇시스템학회 2010 제어로봇시스템학회 각 지부별 자료집 Vol.2010 No.12
This paper presents the successfully developed visual servoing robot that must satisfy less than ±1㎜ accuracy and ±0.5㎜ repeatability requirements in the process of changing rolls used to deform the diameter of rod in steel work. To achieve research objectives, visual servo controller is developed to enable a robot end-effector to track a desired position as determined by a sequence of images from pin-hole camera mounted in the center of end-effector. To do this, 3D alignment task using a ring pattern is developed to compensate for end-effector position errors and the practically efficient line segment detection method is developed to determine an insertion angle for an elaborate locking between insert pin and unit with the less than ±0.5° accuracy as well.