A system and method identifying an object, such as a transparent object, to be picked up by a robot from a bin of objects. The method includes obtaining a 2D red-green-blue (RGB) color image and a 2D depth map image of the objects using a 3D camera, where pixels in the depth map image are assigned a value identifying the distance from the camera to the objects. The method generates a segmentation image of the objects using a deep learning mask R-CNN (convolutional neural network) that performs an image segmentation process that extracts features from the RGB image and assigns a label to the pixels so that objects in the segmentation image have the same label. The method then identifies a location for picking up the object using the segmentation image and the depth map image.

A geometric model-based evaluation method, system, and apparatus for a key performance indicator in a production procedure are disclosed. The method includes extracting a geometric characteristic and a characteristic attribute thereof from a product model; converting the geometric characteristic into a process characteristic so as to obtain the steps of a process related to a whole production procedure of producing a product, and devices corresponding to the steps of the process; and based on the steps of the process related to the production procedure and the devices corresponding to the steps of the process, simulating the whole industrial manufacturing procedure of the product, and outputting the KPI of the industrial manufacturing. At least one embodiment can evaluate the KPI of the whole industrial manufacturing procedure of the product according to the product model.

A postprocessor device outputs a machining program for controlling a CNC machine tool. The postprocessor device includes: a characteristic shape recognition unit configured to read information about a characteristic shape to be machined from cutter location data including information about a characteristic shape; a section setting unit configured to set one or more set sections on a tool path in response to the information about the characteristic shape; and a motion generation unit configured to generate a machining program including instruction for changing at least one parameter to be used for controlling at least one axis of the CNC machine tool outside the set section and inside the set section.

A method of identifying and retrieving component digital images for component fault analysis includes generating a known-fault database of digital images of known faults of a previously analyzed component and corresponding remedial actions. The method also includes accessing the known-fault database with a digital image of a current fault of a new component. The method additionally includes comparing the digital image of the current fault with the digital images in the known-fault database based on a computed target characteristic. The method also includes sorting the digital images in the known-fault database in order based on a magnitude of the computed target characteristic for each respective digital image in the known-fault database relative to the digital image of the current fault. The method further includes outputting the sorted digital images to facilitate correlation of the current fault to a particular known fault and identifying the corresponding remedial action.

A method of identifying and retrieving component digital images for component fault analysis includes generating a known-fault database of digital images of known faults of a previously analyzed component and corresponding remedial actions. The method also includes accessing the known-fault database with a digital image of a current fault of a new component. The method additionally includes comparing the digital image of the current fault with the digital images in the known-fault database based on a computed target characteristic. The method also includes sorting the digital images in the known-fault database in order based on a magnitude of the computed target characteristic for each respective digital image in the known-fault database relative to the digital image of the current fault. The method further includes outputting the sorted digital images to facilitate correlation of the current fault to a particular known fault and identifying the corresponding remedial action.

A workpiece display assistance device according to one aspect includes: a first model generation unit that obtains shape data of a workpiece to be set, and generates an original model based on the shape data; a second model generation unit that generates a plurality of matching models by rotating and/or inverting the original model; an extraction unit that matches each matching model to the original model and extracts aligned portions of the respective matching models with the original model as matching sections; a model creation unit that creates a matching aggregate model by aggregating the matching sections in a state conforming to the original model and synthesizing the matching sections aggregated; a determination unit that compares the original model and the matching aggregate model and makes a determination of a feature point on the workpiece; and a display unit that displays the feature point in a highlightable manner, along with an image of the workpiece, on a display screen based on the determination result.

A postprocessor device outputs a machining program for controlling a CNC machine tool. The postprocessor device includes: a characteristic shape recognition unit configured to read information about a characteristic shape to be machined from cutter location data including information about a characteristic shape; a section setting unit configured to set one or more set sections on a tool path in response to the information about the characteristic shape; and a motion generation unit configured to generate a machining program including instruction for changing at least one parameter to be used for controlling at least one axis of the CNC machine tool outside the set section and inside the set section.

A system and method identifying an object, such as a transparent object, to be picked up by a robot from a bin of objects. The method includes obtaining a 2D red-green-blue (RGB) color image and a 2D depth map image of the objects using a 3D camera, where pixels in the depth map image are assigned a value identifying the distance from the camera to the objects. The method generates a segmentation image of the objects using a deep learning mask R-CNN (convolutional neural network) that performs an image segmentation process that extracts features from the RGB image and assigns a label to the pixels so that objects in the segmentation image have the same label. The method then identifies a location for picking up the object using the segmentation image and the depth map image.

Technologies are generally described for orientation-based hashing to determine item orientation. In some examples, a conveyance system may be configured to adjust the orientations of various types of items before sorting. The conveyance system may include a computer vision system that determines whether the orientation of an item should be adjusted based on an item-feature hash table that relates item image features to item orientations or actuator signals. In other examples, the computer vision system may determine item image features associated with a particular item and perform an item-feature hash table lookup using the item image features to determine an item orientation or actuator action. The item-feature hash table may be separately trained, allowing the computer vision system to rapidly determine the appropriate item orientation or actuator action.