JP2000065533A - Method for gripping ring-shaped object and its aligning device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To securely grip a flexible ring-shaped object by picking up and capturing its image, binarizing it, performing the labeling processing for recognizing its state, and determining the gripping position for gripping. SOLUTION: A camera C1 is arranged on a ring-shaped object for capturing the entire object, and cameras C2 and C3 are mounted to a robot band 1 and the ring-shaped object can be partially captured obliquely. The ring-shaped object is captured by the camera C1, and an image is binarized for labeling. The overlapped state is recognized according to the area and distribution of the label, a gripping position where the robot hand 1 can be inserted is determined, and the height there is detected by the cameras C2 and C3, thus determining the gripping height. In this case, the ring-shaped object is lifted to cancel overlapping. In this manner, by recognizing the height of the ring-shaped object in each state, overlapping can be canceled by gripping only the highest part even if the ring-shaped object overlaps for alignment.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus and a method for gripping and aligning a ring-shaped elastic member made of an example of a flexible elastic body.

[0002]

2. Description of the Related Art Conventionally, when mounting or inspecting a flexible ring-shaped object, for example, a sealing made of synthetic rubber, it is necessary to remove the overlap or entanglement of the objects. . Automating these operations will be an effective method for the automation of the system as well as the development of many flexible object handling methods.

[0003]

However, a system for recognizing the mounting state of such a ring-shaped object which is rich in flexibility and whose shape is uncertain has not yet been established. For an object whose shape is determined, pattern matching is performed with a pre-teached image of a non-defective product, and shape recognition of the object is performed. It is a system that cannot do it. The present invention proposes an apparatus and a method for aligning a ring-shaped object including a band-shaped object by using a robot and image processing, for example, an object having an original shape as shown in FIG. .

[0004]

SUMMARY OF THE INVENTION The present invention relates to a gripping method for recognizing and holding a state of a ring-shaped object having a high flexibility and an uncertain shape. Captured as an image, binarizing the image, performing labeling to recognize the state of the ring-shaped object, determining the gripping position of the recognized ring-shaped object, and causing the ring-shaped object to be gripped. .

[0005] Further, there is provided an alignment apparatus which recognizes and aligns a state of a ring-shaped object which is rich in flexibility and whose shape is uncertain,
The ring-shaped object is captured as an image by an imaging device, the image is binarized, the binarized image is labeled, the state of the ring-shaped object is recognized, and the recognized ring-shaped object is recognized. Is characterized in that the gripping position is determined, gripped and aligned in a certain direction.

[0006]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The prerequisites for implementing the present invention will be described below with reference to the drawings. The apparatus shown in FIG. 1 is an image processing apparatus, and includes one 6-axis articulated robot and three cameras. The camera C1 is disposed above the ring-shaped object, and can capture the entire ring-shaped object. The cameras C2 and C3 are attached to the robot hand 1, and can partially capture the ring-shaped object from an oblique direction.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Measuring Method First, the overlapping state is recognized from the label area and distribution from the image of the camera C1, and the gripping position where the robot hand 1 can be inserted is determined. The height at that position is detected by the two cameras C2 and C3 attached to the robot hand 1, and the gripping height is determined. Here, the ring-shaped object is lifted to eliminate the overlap. Recognition of overlap pattern A ring-shaped object is captured by the camera C1, the image is binarized, and labeling is performed. NU is the number of labels LU1 whose number of pixels is TU or more, and (F
SXi, FSYi) and the coordinates at the lower right
i, FEYi), (i = 1, 2, 3,..., NU).
When NU = 1, since the ring-shaped objects do not overlap, the ring-shaped objects are aligned in the next step. N
When U ≧ 2, the ring-shaped objects overlap, and it is necessary to eliminate the overlap. Label LU1
Let LUMAX be the largest in the area. Robot hand 1
In order to determine the insertion position, the overlapping pattern is divided.

Pattern 1 A case where the label LUmax is not surrounded by other labels LU1 is a pattern 1 as shown in FIG. 2 and satisfies the condition of equation (1).

[0009]

(Equation 1)

Pattern 2 In the case other than the pattern 1, the case where the label LUmax is surrounded by the other label LU1 is the pattern 2 as shown in FIG. 3 and the condition of the expression (2) is satisfied.

[0011]

(Equation 2)

Method for Determining the Position of Holding the Ring-shaped Object In the case of Pattern 1 The following processing is performed to detect the position where the robot hand 1 can be inserted. Contour tracking processing is performed on the label LUmax. The coordinates of each point on the contour are represented by (DXk, DY
k), (k = 1, 2, 3,..., NC). A point (DXmax, DYmax) on the contour line farthest from the center of gravity (GX, GY) of the ring-shaped object is calculated by Expression 3.

[0013]

(Equation 3)

When the sizes of the robot hand 1 and the captured image are made to correspond to each other, the opening width from the center of the robot hand 1 is PA pixels, the vertical and horizontal sizes of the robot hand 1 are PB pixels and PC pixels. I do. Points (DXmax, DYmax
The normal line of the contour line in ()) is obtained. Inward of normal, P
From the point of the A pixel, the presence or absence of the target inside the rectangle of the vertical PB pixel and the horizontal PC pixel is checked. If the object is confirmed on the left side of the center, the pixel is moved one pixel to the right on the contour line, and the normal at that point is searched for. Similarly, the search is performed in the outward direction of the normal. Points on the contour line where no object is detected on both the inside and the outside are defined as gripping positions. The normal direction is the gripping direction. (See Fig. 4)

In the case of pattern 2, contour tracing is performed on the label LUmax and the outer periphery of the ring-shaped object. Each coordinate is (DIXm, DIY
m), (DOXn, DOYn), the total number of pixels is set to NI and NO, and the closest point (DOXmin, DOYmin) of the two points is calculated by equation 4, and this point is set as the gripping position.

[0016]

(Equation 4)

The normal of the contour line at the point (DOXmin, DOYmin) is determined, and this is set as the gripping direction.

Calculation of the height of the gripping position The height of the ring-shaped object at the gripping position determined using the cameras C2 and C3 is calculated. The gripping height is determined so that can be gripped. As shown in FIG. 5, when the image of the camera C2 appears to be shifted by D2 from when the ring-shaped object is viewed from directly above, assuming that the height of the ring-shaped object is H and the width of the ring-shaped object is W, Become like

[0019]

H = CH · D2 / (CW + D2) If the coordinates of the right and left ends of the ring-shaped object viewed from the camera C2 are R2 and L2, and the views from the camera C3 are R3 and L3, D2 is Equation 6 can be expressed.

[0020]

D2 = R3-R2 Equation 7 is obtained by substituting Equation 6 into Equation 5.

[0021]

H = CH · (R3-R2) / (CW + R3-R2)

At the calculated gripping position and gripping height, the robotic hand 1 grips the ring-shaped object, and lifts the ring-shaped object upward until it separates from the worktable, as shown in FIG. Thus, it is possible to eliminate the overlap of the ring-shaped objects and return to the original shape. When lowering the ring-shaped object from this state,
Lower and align the diagonally lower plane so that it does not overlap again.

In order to accurately align the ring-shaped objects, a method of accurately specifying a gripping position and determining a characteristic portion of the ring-shaped object is possible. In this method, extraction of characteristic portion information, A database of the characteristic portions, matching of the characteristic portions, and the like are performed to determine a gripping position and perform alignment.

[0024]

According to the present invention, it is possible to reliably hold a flexible ring-shaped object. The overlapping state of the ring-shaped objects can be recognized using the area and arrangement of the labels. By recognizing the height of the ring-shaped objects in each state, even when the ring-shaped objects are overlapped, only the uppermost part can be gripped, and the overlap can be eliminated and aligned.

[Brief description of the drawings]

FIG. 1 is a schematic diagram showing an image processing apparatus of the present invention.

FIG. 2 is a plan view of a pattern 1;

FIG. 3 is a plan view of a pattern 2;

FIG. 4 is a plan view showing a gripping position of a pattern 1;

FIG. 5 is an explanatory diagram showing a positional relationship for calculating a height.

FIG. 6 is a plan view showing an original shape (that is, an aligned shape) of a ring-shaped object.

[Explanation of symbols]

 1 Robot hand C1 camera C2 camera C3 camera

Claims (2)

[Claims] 1. A gripping method for recognizing and holding a state of a ring-shaped object having a high flexibility and an uncertain shape, wherein the ring-shaped object is captured as an image by an imaging device, and the image is binarized. A method for gripping a ring-shaped object, comprising performing processing and performing labeling processing to recognize the state of the ring-shaped object, determining a gripping position of the recognized ring-shaped object, and causing the object to be gripped. 2. An aligning apparatus for recognizing, grasping and aligning a state of a ring-shaped object having a high flexibility and an uncertain shape, wherein the ring-shaped object is captured as an image by an imaging device, and Labeling the binarized image to recognize the state of the ring-shaped object, determining a gripping position of the recognized ring-shaped object, gripping and aligning in a certain direction. Ring alignment device.