Abstract: Upon reception of a work sensing command from a robot controller, an image processing unit obtains a two-dimensional image of thee whole work pallet including a work, with a CCD camera (a first sensor means). A line of sight is calculated based on the work position on the sensed two-dimensional image. The robot controller determines the destination of movement of the robot such that a crossing line LC of slit beams LB1, LB2 of a laser sensor (a second sensor means) can agree with the calculated line of eight. The image processing unit operates the laser sensor so as to surely irradiate the laser slit beams LB1, LB2 to the target work, permitting the laser sensor to sense the three-dimensional positional and orientation of the target work.

Abstract: A position detecting device and a takeout apparatus capable of obtaining information on height or stage number of an object in a stack of objects by a two-dimensional image capturing device for an operation of taking out the object by a robot. A CCD camera is arranged at a position above a place where workpieces stacked in multiple stages are provided. An image processing device determines a size of the image of the uppermost workpiece in a two-dimensional image captured by the camera. The height or stage number of the workpiece is determined from the size of the workpiece image using a stored relation table or arithmetic expression representing relationship between the height or stage number of the workpiece and the size of the workpiece. For a plurality of kinds of workpieces, the relation table/arithmetic expression is stored for each kind of workpiece and selectively used in accordance of a mark on the workpiece which indicate the kind of workpiece.

Abstract: A teaching position correcting device which can easily correct, with high precision, teaching positions after shifting at least one of a robot and an object worked by the robot. Calibration is carried out using a vision sensor (i.e., CCD camera) that is mounted on a work tool. The vision sensor measures three-dimensional positions of at least three reference marks not aligned in a straight line on the object. The vision sensor is optionally detached from the work tool, and at least one of the robot and the object is shifted. After the shifting, calibration (this can be omitted when the vision sensor is not detached) and measuring of three-dimensional positions of the reference marks are carried out gain. A change in a relative positional relationship between the robot and the object is obtained using the result of measuring three-dimensional positions of the reference marks before and after the shifting respectively.

Abstract: To simply correct the positional data in the teaching program for the robot at a stable precision. The working tool (such as a spot welding gun 13 or others) is mounted to an arm of the robot 10 and imaging means 14 is detachably attached to the arm by a magnet 17 or others so that the optical axis coincides with the working direction (the opening/closing direction of the gun 13). When the positional data correcting program starts, the points P1 to P3 on the jig 1 or the workpiece 2 are imaged at a plurality of image positions D1, D2 and D3, and the position of the respective point is detected. Based on the detected result, the correction is made on the positional data in the teaching program, corresponding to the deviation (in comparison with the off-line data or positional data prior to the transfer of the system) of position and posture of the jig 1 (or the workpiece 2). The tool may be a laser beam machining nozzle, an arc welding torch or a sealing gun.

Abstract: (1) Orthogonal transformation is applied to sample images based on the images of a normalized orthogonal system, and component groups are determined. A plurality of comparison target images are selected from an input image, and a partial normalized orthogonal system is created from the normalized orthogonal system by decreasing the dimensions. (2) Based on the partial normalized orthogonal system, orthogonal transformation is applied to the comparison target images, so as to determine the partial component group for each comparison target image. A comparison target image having high consistency with one of the sample images is extracted by comparison and collation between these partial component groups and the partial component groups which include each element of each partial normalized orthogonal system among component groups of each sample image.

Abstract: A robot automatically moving a distal end portion of a robot arm to an arbitrary target position, and method therefor. A camera mounted at the distal end portion of the robot arm captures an image of an object. A position R1 corresponding to the target Q is specified in the image. Assuming that the number of pixels between the position R1 and the center of an image screen is equal to N1, a distance W1 observed at a distance L0 at the time of calibration is determined as W1=C0·N1, where C0 is a transformation coefficient. The camera is moved by the distance W1 in an X axis direction toward the target Q. A position R2 corresponding to the target W is specified in the image. The number, N2, of pixels between the position R2 and the screen center is determined. A motion vector q is determined from C0, N1, N2 and L0. The camera is moved according to the motion vector q. The robot is positioned at a position where the camera center is opposed to the target Q at the distance L0.

Abstract: The entire region of variation in the viewing range of the attitude of a workpiece is divided roughly, and images of the workpiece are captured from each direction. The images are stored together with imaging direction data as a first teaching model. Images captured by varying the imaging direction at a narrow pitch within a predetermined range of attitude variation in the workpiece are then stored together with imaging direction data as a second teaching model. An image of the workpiece is then captured and compared with the first teaching model, whereupon the first teaching model most closely resembling the captured image is selected. A camera is then moved in accordance with the selected teaching model to a target moving position to obtain an image to be used in a comparison with the second teaching model, whereupon an image of the workpiece is captured. The captured image is compared with the second teaching model, and the second teaching model most closely resembling the captured image is selected.

Abstract: A first masking image of an input image is created by assuming that pixels in an area including the area of a target in all sample images are valid pixels while pixels in the remaining area are invalid pixels. The first masking image is used in a first comparison between the input image and each sample image to select an image that provides a best match as a provisionally selected sample image. In a second comparison, a second masking image corresponding to the provisionally selected sample image is used to select a final sample image. The second masking image is created from an individual sample image by assuming that pixels in an area including the area of the target are valid pixels while pixels in the remaining area invalid pixels.

Abstract: A robot flexure correction device and method in which flexure amount correction can be automatically performed on taught points. For each robot model and for each of loads that are different in weight and center-of-gravity position, flexure amounts representing deviations of a robot front end are measured at a plurality of positions in a robot operating area, and stored as flexure amount data. When a robot is used, flexure amount data about the model of the used robot and about the load that is close in weight and center-of-gravity position to a used tool is designated from flexure amount data 1-1 to 1-m with a designation means. A program is designated from programs 2-1 to 2-n with an operation program designation means. With a flexure amount calculation means, a flexure amount for each of taught point positions/orientations in the program is calculated using the flexure amount data.

Abstract: An work tool mounted on an arm tip end of a robot is allowed to move toward a teaching point of a robot operation program, and to stop the work tool before it reaches the teaching point. The robot is moved by jog feeding from the stopped position to a target position. In this manner, the teaching point of the robot operation program is corrected.

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: A workpiece is gripped and unloaded by moving workpiece unloading means based on the results of measuring the workpiece position and orientation with a visual sensor. When a plurality of loaded workpieces are unloaded in a regular order one by one, or in groups, the position and orientation of the workpiece which is to be unloaded next change for each unloading. However, since a visual sensor is moved when necessary to the position appropriate for measuring the workpiece position and orientation, measurements of the workpieces with the visual sensor are conducted accurately. Therefore, the workpiece unloading is conducted reliably.

Abstract: A position detecting device and a takeout apparatus capable of obtaining information on height or stage number of an object in a stack of objects by a two-dimensional image capturing device for an operation of taking out the object by a robot. A CCD camera is arranged at a position above a place where workpieces stacked in multiple stages are provided. An image processing device determines a size of the image of the uppermost workpiece in a two-dimensional image captured by the camera. The height or stage number of the workpiece is determined from the size of the workpiece image using a stored relation table or arithmetic expression representing relationship between the height or stage number of the workpiece and the size of the workpiece. For a plurality of kinds of workpieces, the relation table/arithmetic expression is stored for each kind of workpiece and selectively used in accordance of a mark on the workpiece which indicate the kind of workpiece.

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 workpiece is gripped and unloaded by moving workpiece unloading means based on the results of measuring the workpiece position and orientation with a visual sensor. When a plurality of loaded workpieces are unloaded in a regular order one by one, or in groups, the position and orientation of the workpiece which is to be unloaded next change for each unloading. However, since a visual sensor is moved when necessary to the position appropriate for measuring the workpiece position and orientation, measurements of the workpieces with the visual sensor are conducted accurately. Therefore, the workpiece unloading is conducted reliably.

Abstract: Upon reception of a work sensing command from a robot controller, an image processing unit obtains a two-dimensional image of thee whole work pallet including a work, with a CCD camera (a first sensor means). A line of sight is calculated based on the work position on the sensed two-dimensional image. The robot controller determines the destination of movement of the robot such that a crossing line LC of slit beams LB1, LB2 of a laser sensor (a second sensor means) can agree with the calculated line of eight. The image processing unit operates the laser sensor so as to surely irradiate the laser slit beams LB1, LB2 to the target work, permitting the laser sensor to sense the three-dimensional positional and orientation of the target work.