JPS6193902A - Method for teaching specific position of target object in visual sensor system - Google Patents

Abstract

PURPOSE:To teach the specific position of the target object in a visual sensor system by teaching said position by the coordinate value of the object coordinate system XY of which the origine is the controid of the plane image of the target object and the main axis is the X-axis or Y-axis. CONSTITUTION:A microcomputer 14 calculates the characteristic value of a prescribed characteristic term and collates the same with the reference characteristic value stored in a RAM18 thereby discriminating the kind of the object of this time. The microcomputer determines the centroid and main axis of the target object, presumes the object coordinate system and calculates the coordinate value in the coordinate system of the visual sensor in the taught specific position from the coordinate value in the object coordinate system of the specific position stored in the RAM18. The microcomputer informs a robot of the information on the kind of the target object, the coordinate value in the visual sensor coordinate system of the specific position P, the position of the centroid and the attitude angle thetaob of the target object via an interface circuit 13. The teaching is thus executed simply and easily as the position of the target object is taught by the coordinate value of the X-Y coordinates.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of Industrial Application The present invention is suitable for a system that combines a visual sensor and a robot, which grasps an object based on specific position information of the object recognized by the visual sensor. This invention relates to a method for teaching the specific position of a target object in a visual sensor system.

Conventional technology For example, the coordinate system of the robot is XR as shown in FIG.

If YR and the visual sensor coordinate system are XS and YS in the same figure, the distance between the origin OR of the robot coordinate system and the origin O5 of the visual sensor coordinate system and the inclination θR3 of both coordinate systems should be taught to the robot in advance. For example, the robot can recognize the position of the center of gravity of the target object OB by notifying the robot of the coordinate values in the visual sensor coordinate system of the center of gravity Oob of the planar image of the target object OB captured by the visual sensor. becomes. In addition, the elevation θo of the main axis of the target object OB (equal to the long axis of the radius circle circumscribing the outline of the target object) Lob
By notifying the robot of b, the robot can recognize the orientation of the target object OB. By understanding the posture of the target object OB and the position ○Ob of the center of gravity, the robot can grasp the target object OB at the position of the center of gravity.

By the way, when having a robot grip a target object, there are many cases where it is desired to have the robot grip a position other than the center of gravity. In such a case, it is necessary to teach the visual sensor where the object should be gripped.

However, unlike the center of gravity, which can be uniquely determined from an image of a target object by a mathematical method, it is quite difficult to teach a visual sensor the arbitrary position of an object. Problems to be Solved by the Invention The present invention This was done in view of these circumstances,
The purpose is to be able to teach an arbitrary position of a target object to an operator in a simple and easy-to-understand manner.

Means for Solving the Problems In order to solve the above problems, the present invention processes an imaging signal obtained by imaging a target object with a visual sensor, and uses a visual sensor at a pre-designated specific position of the target object. In the teaching method of the specific position in the visual sensor system that notifies the robot of the coordinates in the coordinate system, the specific position is set such that the center of gravity of the planar image of the target object obtained by imaging in the teaching stage is the origin and the principal axis is the Y axis. Alternatively, the coordinate values of the object coordinate system XY, which is the Y axis, are used for teaching.

Embodiment FIG. 2 is a block diagram showing an example of the hardware configuration of a visual system implementing the present invention. 10 is a visual sensor having a solid-state image sensor such as a CCD, and the image signal is sent to a monitor television 11. The signal is input to the binarization circuit 12.

The binarization circuit 12 compares the image pickup signal with a predetermined darkness value, so that, for example, the object part is "1" and the background part is "'0".
A binarized imaging signal is generated, and the frame memory ratio is 1,a for one screen of this binarized imaging signal. Frame memo January 5 via microcomputer 14 bus, data bus, address bus, control bus 16
．． Ink face circuit 13. Keyboard 17. R.A.
Connected to M18°CRT19. The keyboard 17 has keys for inputting commands for changing the system to teaching mode and execution mode, various commands, and data.

The CRT 19 displays the binary image stored in the frame memory 15. Further, the RAM 18 is a memory having a storage area for teaching data and an area for temporarily storing feature values of the target object during execution, etc., and the ink face circuit 13 is used for receiving and receiving information from a robot (not shown) and for transferring information (not shown). The detection signal from the object position detector is received and passed on.

Next, the operation of this embodiment will be explained separately during teaching and during execution.

[When teaching]

(1) First, operate the keyboard 17 to change the system to teaching mode.

(2) Next, operate the keyboard 17 to input the type of object to be taught, for example, Xl. By inputting this type, an area is secured in the RAM 18 for storing the reference feature value and specific position corresponding to the type X1.

(2) Next, an object of type x1 is placed within the field of view of the visual sensor lO (Fig. 3 is a diagram showing an example of a binary image of the target object obtained during teaching.

(2) Next, operate the keyboard 17 to input a teaching start command. As a result, the microcomputer 14 imports one screen worth of binary images into the frame memory 15, calculates pre-specified feature items from the content, such as feature values such as area 2 perimeter, etc., and stores this in RAM 1B. Remember.

Calculation of such feature values is repeated a necessary number of times, and the average and variance thereof are stored in the RAM 18 as reference feature values.

0 Next, the specific position of the target object OB to be notified to the robot is taught. For example, if the specific position to be taught is point P shown in FIG. Input.In addition,
The scale of the object coordinate system is the same as the scale of the visual sensor coordinate system. Here, the object coordinate systems OX, OY have the center of gravity of the plane image of the target object OB as the origin Oo, and the main axis as the Y-axis (
or Y-axis), and the axis perpendicular to the Y-axis is the Y-axis (or Y-axis).
It is a coordinate system with axes).

The coordinates (x, y) of point P are recorded in the area corresponding to the object type X1 in the RAM 18.1. a.

0 Next, the above operation is performed on multiple objects X2 of different types.
.about.

(Execution time) ② A transition to execution time is performed by pressing the execution key on the keyboard 17.

(2) When the execution key is pressed, the microcomputer 14 enters a waiting state for a detection signal from the ink face circuit 13, as shown in FIG. When the target object is transported by a transporter (not shown) and enters the field of view of the visual sensor 10, it is detected by a detector (not shown), and the ink face circuit 1
A detection signal is input to 3. As a result, the microcomputer 14 loads one screen worth of binary images into the frame memory 15. Figure 5 shows the target object OB 2 during execution.
It is a figure showing an example of a value image. Microcomputer 1
4 then calculates the feature value of a predetermined feature item and stores it in RAM1.
The type of the current object is determined by comparing it with the reference feature values stored in step 8. In addition, the center of gravity and principal axis of the target object are determined and an object coordinate system is assumed, and the visual perception of the taught specific position is determined from the coordinate values in the object coordinate system of the specific position stored in the RAM 18 corresponding to the determined object type. Calculate coordinate values in the sensor coordinate system. Then, the type information of the target object, the position of the coordinate value 1 center of gravity in the visual sensor coordinate system of the specific position P shown in Fig. 5, and the attitude angle of the target object (the angle formed by the principal axis and XS of the visual sensor coordinate system) θob. The robot is notified via the ink face circuit 13.

In the above embodiments, the operator himself/herself obtains the coordinate values of the object coordinate system at a specific position of the target object, and uses the keyboard 17
The binarized image of the target object is input via a CRT.
19, move the cursor to a specific position on the displayed binary image using the cursor operation keys on the keyboard 17,
The keyboard 17 instructs that the position is the teaching position, the microcomputer 14 calculates the coordinate values in the object coordinate system of the position indicated by the cursor, and
18 may be stored.

As described in detail, the present invention assumes object coordinates XY in which the center of gravity of a planar image of the target object obtained by imaging in the teaching stage is the origin and the principal axis is the X axis or the Y axis, and The position of the target object is taught using the coordinate values of the coordinates, and the operator can easily know the coordinates of any position of the target object in the object coordinate system XY from the drawing of the target object. There is an advantage that teaching can be performed simply and easily.

[Brief explanation of the drawing]

Figure 1 shows the specific position of the target object OB and the object coordinate system ox, o.
2 is a block diagram showing an example of the hardware configuration of a visual system implementing the present invention, FIG. 3 is a diagram showing an example of a binary image during teaching, and FIG. 4 is a diagram showing an example of a binary image during teaching. A flowchart showing an example of processing performed by the microcomputer 14 during execution, FIG.
FIG. 6 is an explanatory diagram of the relationship between the visual sensor coordinate systems XS, YS and the robot coordinate systems XR, YR, and the center of gravity and principal axis of the target object. 10 is a visual sensor, 12 is a binarization circuit, 13 is an ink face circuit, 14 is a microcomputer, 15 is a frame memory for storing binary images, 17 is a keyboard, 1
8 is a RAM, and 19 is a CRT.

Claims (1)

[Claims] In a method for teaching a specific position in a visual sensor system that processes an imaging signal obtained by capturing an image of a target object with a visual sensor and notifies a robot of coordinates in a visual sensor coordinate system of a pre-designated specific position of the target object. ,
The specific position is taught using coordinate values of an object coordinate system XY in which the center of gravity of a plane image of the target object obtained by imaging in the teaching step is the origin and the main axis is the X axis or the Y axis. A method for teaching the specific position of a target object in a visual sensor system.