• Special Issue of the Society of Naval Architects of Korea
• /
• 2011.09a
• /
• pp.32-35
• /
• 2011

Template has been widely used for hull forming process in most of shipyards. It is used to estimate the curvature of deformed shape in comparison with design shape. SHI (Samsung Heavy Industry) had used AutoKon system for ship manufacturing design in the past. The AutoKon used the global coordinate system of ship (frame, water line and so on) to create template data. It brought the mismatched angles between templates and a curved shell plate. The mismatched angle is measured by forming worker to place template on shell forming stage. However, the mismatched angle is difficult to place template with exactly required angle because the shell plates have various curvature and size. It causes incorrect shape of formed shell plates. The attached angle of template should be 90 degree to place template easily on forming shell plates. Currently, SHI has been applied GSCAD for ship manufacturing design process which is 3D solid modeling system. The GSCAD is the rule-based system which can automate 3D modeling and control the manufacturing data by rule. The rule can easily provide methods to create and automate template object with regular attached angle in comparison with AutoKon system. Therefore, SHI developed new template rule which it can automatically create template object with regular attached angle in GSCAD.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.839-846
• /
• 2016

Bin picking is a task of picking a small object from a bin. For accurate bin picking, the 3D pose information, position, and orientation of a small object is required because the object is mixed with other objects of the same type in the bin. Using this 3D pose information, a robotic gripper can pick an object using exact distance and orientation measurements. In this paper, we propose a 3D vision technique for accurate measurement of 3D position and orientation of small objects, on which a paper label is stuck to the surface. We use a maximally stable extremal regions (MSERs) algorithm to detect the label areas in a left bin image acquired from a stereo camera. In each label area, image features are detected and their correlation with a right image is determined by a stereo vision technique. Then, the 3D position and orientation of the objects are measured accurately using a transformation from the camera coordinate system to the new label coordinate system. For stable measurement during a bin picking task, the pose information is filtered by averaging at fixed time intervals. Our experimental results indicate that the proposed technique yields pose accuracy between 0.4~0.5mm in positional measurements and $0.2-0.6^{\circ}$ in angle measurements.