Abstract: A workpiece gripping device includes a primary catching mechanism having a suction pad adapted to hold a workpiece by suction power and a rod-like part having the suction pad mounted on one end thereof, gripping pawls sandwiching and gripping the workpiece, a drive unit for supplying a drive power, and a transmission mechanism transmitting the drive power of the drive unit to the gripping pawls. The transmission mechanism moves the gripping pawls along an axis of the rod-like part between a gripping position where the gripping pawls are projected beyond the suction pad and a retreated position where the gripping pawls are retreated from the suction pad toward the base plate. The gripping pawls are moved to the gripping position along the axis of the rod-like part while shortening the distance between the gripping pawls.

Abstract: 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.

Abstract: A screw portion inspection apparatus for inspecting, by image processing, a screw portion provided in an object. The apparatus includes an imaging section for picking up an image of a region, including a screw portion, in an object along a direction inclined with respect to a center axis of the screw portion, and obtaining a two-dimensional image of the object; an image processing section for subjecting image data of the screw portion in the two-dimensional image obtained by the imaging section to a filtering process; and a thread judging section for judging whether a thread exists in the screw portion, based on output image data, of the screw portion, resulting from the filtering process. The filtering process performed by the image processing section includes an edge detection process, and the output image data of the screw portion includes edge data in the screw portion.

Abstract: An image processing device for detecting an object whose position and orientation are unknown and for recognizing three dimensional position and/or orientation of the object. A model pattern used for a pattern matching is stored and subject to N geometrical transformations. After initial setting of an index i that specifies the i-th geometrical transformation, the i-th transformed model pattern is prepared, and, using this pattern, a pattern matching is performed. A local maximum point having a similarity equal to or higher than a preset value is searched for. The image coordinate of such a point, if any, is extracted and stored together with information on a three dimensional relative orientation used for the preparation of the transformed model pattern concerned. Based on the information on the three dimensional relative orientation corresponding to the pattern having the best similarity, the three dimensional position and/or orientation is recognized.

Abstract: An image of a reference object is captured using a camera and displayed. A measurement starting point is pointed by an image position pointing device. A corresponding view line is obtained using a position on the image and a position and a direction of the camera, a robot approaches to the reference object such that it does not deviate from a projecting direction to move to a position suitable for measurement. A light is projected on the reference object and measurement of an inclination of a face of the object in the vicinity of a measuring point is started. An image including a bright line image on the reference object is photographed and 3-dimensional positions of points sequentially measured along a working line. A movement path of a robot is created using these positions as teaching points for a working robot.

Abstract: An image of a reference work is captured using a camera and the image is displayed on an image display device. A measurement starting point is pointed by an image position pointing device. A corresponding view line is obtained using a position on the image and a position and a direction of the camera, a robot approaches to the reference work such that it does not deviate from a projecting direction to move to a position suitable for measurement. A slit light is projected and measurement of an inclination of a face in the vicinity of a measuring point is started. An image including a bright line image on the reference work is photographed and 3-dimensional positions of points sequentially measured along a working line. A movement path of a robot is created using these positions as teaching points.

Abstract: A method of setting a coordinate system to an automatic machine with a stable accuracy in a non-contact manner. The desired coordinate system can be set even if it exists outside a moving range of the automatic machine. The operator operates a robot control device to move a robot to a first position A1 where a coordinate system setting jig is within the field of view of a camera supported by the robot. Matrix data [A1] representing the robot position A1 is stored and the jig is photographed by the camera. The image of a group of dots on the jig are analyzed by an image processor to obtain picture element values of the individual points. Based on the picture element values of the individual points and jig data (data of distances between and number of the points), matrix data [D1] representing a position and a posture of a coordinate system &Sgr;c to be set with respect to a sensor coordinate system &Sgr;s is obtained.

Abstract: A visual sensor coordinate system setting jig comprising a jig including a plurality of feature points arranged at known intervals in an array state corresponding to a visual sensor coordinate system, and a visual sensor to receive an image of the plurality of feature points of the jig, at least three of the plurality of feature points each having a distinguishing appearance which the visual sensor recognizes to discriminate the at least three feature points from the other of the plurality of feature points, the at least three feature points representing an origin and coordinate axes of the visual sensor coordinate system, and the visual sensor to identify the origin and the coordinate axes of the visual sensor coordinate system based on the array state of the plurality of feature points and the distinguishing appearance of the at least three feature points.

Abstract: A method for automatically effecting calibration between an image processing apparatus and a control device of an automatic machine. Jig data for calibration and the position of a robot, fitted with a jig which can be photographed by a camera at the time of calibration, are previously given as instructions. In response to a calibration command, the robot, fitted with the jig, moves to a point of instruction, the image processing apparatus photographs the jig and fetches an image after the movement. A calibration process is executed in accordance with data of the photographed image, set jig data, and robot position. When the jig data and the instruction point are first set and given once as instructions, the calibration thereafter can be automatically effected only by mounting the jig on the robot and inputting the calibration command.

Abstract: A robot coordinate system setting method is provided which facilitates the setting of a common coordinate system with respect to each of robots in a robot system or a robot installed in substitution for one of the robots. A coordinate transformation matrix for transforming a provisional coordinate system (X2Y2Z2), which a first robot has recognized by accessing a second jig, into a common coordinate system (X1Y1Z1), which the first robot has recognized by accessing a first jig, is calculated, and using this coordinate transformation matrix, a provisional coordinate system which a second robot has recognized by accessing the second jig is transformed into the common coordinate system which is to be recognized by the second robot, and is set with respect to the second robot.

Abstract: After a calibration process has been carried out once for a sensor with respect to a certain position, the position of an object can be detected by the sensor in any other positions, so that the object can positionally be detected in a wide range. Specifically, calibration data (CDA) (32) is produced by calibration process in a position A before a camera moves, and calibration data (CDB) (33) for the camera after it is moved is calculated based on distance data CM (12) with respect to the position and attitude of the camera (3). Then, the position of an object (30) is detected on the basis of the calibration data (CDB) (33) and image data (WDB) (31) of the object (30) imaged by the camera (3) which is in the position B.