Fanuc Corporation

Keisuke Watanabe

Kazunori Ban

Fumikazu Warashina

Ichiro Kanno

Yasuhiro Shibasaki

Katsutoshi Takizawa

Taro Arimatsu

Mitsunori Watanabe

Gang Shen

Kenshirou Oono

Disclosed is an inspection device including: a machine learning device that performs machine learning on the basis of state data acquired from an inspection target and label data indicating an inspection result related to the inspection target to generate a learning model; a learning model evaluation index calculation unit that calculates a learning model evaluation index related to the learning model generated by the machine learning device as an evaluation index used to evaluate the learning model; an inspection index acquisition unit that acquires an inspection index used in an inspection; and an index value determination unit that determines whether the learning model generated by the machine learning device satisfies the inspection index on the basis of the learning model evaluation index and the inspection index and outputs a result of the determination.

Inspection device and machine learning method

An inspection apparatus includes a group data creation unit configured to create group data obtained by dividing a plurality of samples into a plurality of groups, a statistical state calculation unit configured to perform a statistical process for the samples divided into each of the groups to calculate data indicating a statistical state of a predetermined data item between the groups, and a user interface unit configured to display the statistical state in a display format enabling recognition of the statistical state between the groups on the basis of the data indicating the statistical state of the predetermined data item between the groups calculated by the statistical state calculation unit.

Method for displaying, user interface unit, display device and inspection apparatus

An inspection apparatus of the present disclosure includes: a machine learning device that performs machine learning on a basis of state data acquired from an inspection target and label data indicating an inspection result related to the inspection target to generate a learning model; a learning model evaluation index calculation unit that calculates a learning model evaluation index related to the learning model generated by the machine learning device as an evaluation index to be used to evaluate the learning model; an inspection index acquisition unit that acquires an inspection index to be used in the inspection; and a learning model selection unit that displays the learning model evaluation index and the inspection index so as to be comparable with each other regarding the learning model generated by the machine learning device, receives selection of the learning model by an operator, and outputs a result of the selection.

Inspection apparatus and machine learning method

An appearance inspection device creates a combination of a first image which is a normal product image and a second image which is a product image as a comparison object, on the basis of a reference data set and a learning data set, and a machine learning device learns classification of a product corresponding to the second image as normal or not normal for the combination. The machine learning device observes the combination of the first image and the second image as a state variable representing a current state of an environment, acquires a label given to the second image as label data, and performs learning by associating the state variable with the label data.

Appearance inspection device

An inspection condition determination device comprises: an addition unit that adds data mimicking a flaw assumed to occur in an inspection target to a designated position of a three-dimensional model of the inspection target; a generation unit that generates an image without a flaw by replicating an optical condition for capturing an image of the inspection target on the three-dimensional model, and an image with the flaw by replicating the optical condition on the three-dimensional model to which the data mimicking the flaw is added; a determination unit that determines whether or not a difference between the image without a flaw and the image with the flaw at the designated position exceeds a threshold that allows detection of the flaw in the inspection target; and an extraction unit that extracts an optical condition available for detecting flaws of multiple designated patterns from multiple optical conditions.

Inspection condition determination device, inspection condition determination method, and inspection condition determination program

A robot system which is inexpensive and can easily measure a position of a target point. The system stores feature quantities of an image of a target mark included in an image acquired as reference data when the target mark is placed at a known first target mark position at the robot coordinate system and stores the first target mark position with respect to an arm tip as the position of the tool center point. The system compares the feature quantities obtained from the image acquired when the target mark is arranged at a second target mark position and the feature quantities of the reference data to make the arm tip move and calculates the second target mark position at the robot coordinate system based on a second robot position corresponding to the position of the arm tip after movement and the position of the tool center point.

Robot system equipped with camera for capturing image of target mark

The robot system includes: a robot for performing predetermined operations on an object placed at a first object position; a first robot position storage configured to store the position of an arm end arranged in a predetermined positional relationship relative to the first object position; a target arrival state data storage configured to store feature quantities of the object on the camera image; a robot movement amount calculator configured to calculate the amount of movement in order to make the feature quantities of the object placed at a second object position coincide with the feature quantities of the target arrival state data; and a correction data calculator configured to calculate correction data based on the difference between the second robot position when the arm end has been moved based on the amount of movement and the first robot position.

Robot system using visual feedback

A calibrating device for calibration of an image measurement system. The calibrating device includes a main body having an upper surface, and a characteristic portion, which serves as a benchmark for calibration and is in the form of a recess formed in the upper surface of the main body, wherein the characteristic portion includes a side surface extending in a direction crossing the upper surface, and a bottom surface extending in a direction crossing the side surface, the bottom surface has an optical reflectance lower than an optical reflectance of the upper surface in relation to light identical to each other. This can provide a calibrating device for calibration of an image measurement system, which can detect the characteristic portion on the calibrating device stably, precisely and independent of the illumination conditions, which is less costly and can be easily handled.

Calibrating device for calibration and image measurement system comprising calibrating device

An object picking device, which is inexpensive and capable of speedily and accurately picking one object at a time from a random pile state. A target detecting part of an image processing part processes an image captured by a camera and detects objects. A target selecting part selects an object among the detected objects based on a certain rule. A view line direction calculating part calculates the direction of a view line extending to the selected object. A target position estimating part estimates the position including the height of the selected object based on size information of the object in the image. Then, a grip correction calculating part calculates an amount of correction of the movement of a robot so as to grip the object by using the robot.

Object picking device

A workpiece picking device and method for reducing the cycle time of a picking operation of workpieces, by omitting or reducing the movement of a robot manipulator when an image of the workpieces is captured. An image processor of the picking device includes a camera controlling part for reading image data from a camera, a memory for storing the image data, a workpiece detecting part for extracting one or more images from the memory and detecting one or more workpieces in the image, and a workpiece selecting part for selecting a workpiece to be picked among the workpieces detected by the workpiece detecting part. The image processor further includes a stacked condition judging part for determining whether the condition of the stacked workpieces in a container is changed.

Workpiece picking device and method

A workpiece picking apparatus includes a robot, a workpiece recognition device for recognizing the workpieces located in a wide area, an accurate measurement device for accurately measuring the three-dimensional position of the workpiece, a workpiece select device for selecting the workpiece to be picked, and an NG workpiece storage device for storing information on the rough position of an failed NG workpiece when the measurement of the three-dimensional position or the picking for the workpiece has failed. The workpiece select device excludes the NG workpiece stored in the NG workpiece storage device and selects the next workpiece to be measured. The robot picks the selected workpiece based on the three-dimensional position of the workpiece measured by the accurate measurement device.

Workpiece picking apparatus

A workpiece picking device capable of correctly detecting the size of a workpiece. The picking device has a robot capable of picking the same kind of workpieces contained in a work container, a robot controller for controlling the robot, a video camera positioned above the work container so as to widely image the workpieces and an image processor for processing an image obtained by the video camera. The three-dimensional position and posture of each workpiece is measured by a three-dimensional vision sensor arranged on a wrist element of the robot.

Growing community of inventors

Yamanashi, Japan

Keisuke Watanabe