Abstract: An object recognizer recognizes a position and an attitude of a target object based on data measured by a sensor. A safe distance calculator calculates a distance from the target object to a certain object which is other than an object manipulation apparatus and the target object. A manipulation controller controls the pickup device based on the position and the attitude of the target object, and based on the distance from the target object to the certain object. When there are a plurality of target objects to be selected by the object manipulation apparatus, the manipulation controller selects one of the target objects having distances to the certain object longer than a predetermined threshold, and manipulates the selected target object using the pickup device.

Abstract: A robot operation evaluation device includes: an operational state calculator for calculating an operational state of an evaluation region that is a movable region of a robot, based on an operational state of the robot; a shape-feature quantity calculator for calculating a shape-feature quantity depending on an operation direction of the evaluation region corresponding to the operational state calculated; and an evaluation value calculator for calculating an evaluation value representing a risk degree of the operational state of the evaluation region with respect to the operation direction, based on the shape-feature quantity.

Abstract: A method and system detects and localizes multiple instances of an object by first acquiring a frame of a three-dimensional (3D) scene with a sensor, and extracting features from the frame. The features are matched according to appearance similarity and triplets are formed among matching features. Based on 3D locations of the corresponding points in the matching triplets, a geometric transformation is computed. Matching triplets are clustered according to the computed geometric transformations. Since the set of features coining from two different object instances should have a single geometric transform, the output of clustering provides the features and poses of each object instance in the image.

Abstract: A tool shape measurement device includes: a contour detection unit that detects a tool contour from an image of a rotating tool that is taken; an axis direction calculation unit that calculates a tool axis direction that is an axis direction of the rotating tool on the basis of the tool contour; a tool diameter measurement unit that calculates an apparent tool diameter of the rotating tool on an imaging surface on the basis of a calibrated positional and postural relationship between an imaging device and the rotating tool, the tool axis direction, and the tool contour; and a tool diameter correction unit that calculates a distance between the imaging device and the rotating tool using the tool axis direction, and corrects the apparent tool diameter to an actual tool diameter by correcting distortion in the tool contour on the basis of the distance.

Abstract: A storage device stores capturing conditions including a viewpoint position and a shooting direction of the camera, model data including a shape of a segmented mirror, and feature point data representing a positional relationship among a viewpoint position and feature points. A camera captures the segmented mirror having a reflective surface to obtain a captured image including at least a part of the reflective surface. A marker object has feature points, and is fixed at a predetermined position with respect to the camera. A feature-point extracting unit extracts multiple feature points from a captured image in which the feature points are reflected in the reflective surface, and determines positions of the feature points within the captured image. A position measuring unit calculates a position of the segmented mirror, based on the capturing conditions, the model data, the feature point data, and the positions of the feature points within the captured image.

Abstract: A method and system detects and localizes multiple instances of an object by first acquiring a frame of a three-dimensional (3D) scene with a sensor, and extracting features from the frame. The features are matched according to appearance similarity and triplets are formed among matching features. Based on 3D locations of the corresponding points in the matching triplets, a geometric transformation is computed. Matching triplets are clustered according to the computed geometric transformations. Since the set of features coining from two different object instances should have a single geometric transform, the output of clustering provides the features and poses of each object instance in the image.

Abstract: A component supply apparatus capable of aligning components of various shapes, which are supplied in bulk, within a short period of time with general means. The apparatus includes a three-dimensional vision sensor measuring a depth map, a bulk component box, a robot picking up a component from the bulk component box, a temporary placing table onto which components are rolled, a two-dimensional vision sensor measuring a profile of the components, a robot group picking up the component rolled on the temporary placing table, and changing a position and orientation of the component into a position and orientation that involve an error of a certain level or less with respect to a position and orientation that are specified in advance, while changing the position and orientation of the component, and a control device controlling those portions.

Abstract: A workpiece pick-up apparatus including: a hand for gripping a workpiece; a robot for bringing the hand into a desired gripping position or posture; a sensor for performing three-dimensional measurement of the workpiece to obtain workpiece measurement data; a storage medium for accumulating at least hand profile data; an information processing unit for calculating the gripping position or posture based on data from the sensor and data from the storage medium; and a control unit for controlling the robot based on the gripping position or posture calculated by the information processing unit. The information processing unit includes an optimum gripping candidate creating section for directly deriving the gripping position or posture based on the workpiece measurement data and the hand profile data.

Abstract: A component supply apparatus capable of aligning components of various shapes, which are supplied in bulk, within a short period of time with general means. The apparatus includes a three-dimensional vision sensor measuring a depth map, a bulk component box, a robot picking up a component from the bulk component box, a temporary placing table onto which components are rolled, a two-dimensional vision sensor measuring a profile of the components, a robot group picking up the component rolled on the temporary placing table, and changing a position and orientation of the component into a position and orientation that involve an error of a certain level or less with respect to a position and orientation that are specified in advance, while changing the position and orientation of the component, and a control device controlling those portions.

Abstract: A workpiece pick-up apparatus including: a hand for gripping a workpiece; a robot for bringing the hand into a desired gripping position or posture; a sensor for performing three-dimensional measurement of the workpiece to obtain workpiece measurement data; a storage medium for accumulating at least hand profile data; an information processing unit for calculating the gripping position or posture based on data from the sensor and data from the storage medium; and a control unit for controlling the robot based on the gripping position or posture calculated by the information processing unit. The information processing unit includes an optimum gripping candidate creating section for directly deriving the gripping position or posture based on the workpiece measurement data and the hand profile data.