KR101927132B1 - Learning-based Logistics Automation System, Device and Method - Google Patents

Abstract

The present invention relates to a learning-based logistics automation system, an apparatus and a method, in which a logistics automation apparatus judges the shape of an object to which a tag is attached, grasps the shape of the object, recognizes the tag in a reader, estimates the attachment position of the tag, And the tag attaching position of the object to determine the gripping position of the object, stores the shape information of the object and the gripping position information, determines the shape of the object, confirms the gripping position information corresponding to the determined shape, It is possible to recognize the tag by recognizing the tag for recognition attached to the object to be recognized and by learning the appropriate finger position according to the shape of the object.

Description

[0001] Learning-based Logistics Automation System, Device and Method [

More particularly, the present invention relates to a learning-based logistics automation system, apparatus, and method for recognizing a tag by learning a gripping position of an object to which the tag is attached and holding a similar type of object based on the position .

Attempts have been made to reduce manpower and improve accuracy by automating the whole process of logistics such as product production, shipping, transportation, unloading, packaging, and storage. In the case of automation of logistics, it is possible to reduce the cost due to the reduction of manpower and prevent the accident, and it is possible to shorten the time required for logistics and systematically manage it.

As a part of such a logistics automation system, a method of attaching a tag to a product and automatically reading the information of the product by reading the information contained in the tag is being promoted. However, the RFID (radio frequency identification) tag attached to the product is costly, and it is costly to prepare a tag corresponding to the number of products. In case of NFC (near field communication) tag, the recognition distance is short, There is a disadvantage even more than that.

Korean Patent Publication No. 10-2010-0050017 (published on May 13, 2010)

It is an object of the present invention to solve the above-mentioned problems, and it is an object of the present invention to provide a learning-based logistics automation system which learns a grip position suitable for recognizing a tag attached to an object, System, apparatus, and method.

According to another aspect of the present invention, there is provided a learning-based logistics automation system including a reader for recognizing a tag, a reader for determining a shape of the tag-attached object, And determines the grip position of the object in consideration of the shape of the object and the attachment position of the tag, stores the shape information and grip position information of the object, The present invention relates to a method and apparatus for determining a shape of a target object, confirming grip position information corresponding to the determined shape, gripping the object to be recognized according to an identified grip position and recognizing the reader tag attached to the object, And an automation device.

According to an aspect of the present invention, there is provided a learning-based logistics automation apparatus including a shape determination unit for determining a shape of an object to be gripped, a robot arm for holding the object, a storage unit for storing information, Controls the robot arm according to the shape of the object to grasp the object, recognizes the tag attached to the object to the reader, estimates the attachment position of the tag, and determines the shape of the object and the attachment position of the tag Determines the gripping position of the object, stores the shape information and grip position information of the object in the storage unit, and then stores the grip position information corresponding to the shape of the object determined by the shape determination unit in the storage unit And the robot arm is controlled in accordance with the identified grip position to grasp the object to be recognized, Chakdoen for the recognition tag and a controller for recognizing the reader.

In the learning-based logistics automation apparatus according to the present invention, the control unit controls the robot arm to grasp the object, approach the reader, rotate the object so that the exposed surface of the object exposed in the reader direction is changed, And if the tag is not recognized by the reader, the object is again gripped using another gripping position, the object is rotated so that the exposed surface of the object adjacent to the reader is changed, and the tag is recognized by the reader And estimates an attachment position of the tag according to an angle at which the object is rotated.

In the learning-based logistics automation apparatus according to the present invention, the control unit further stores the rotation angle information of the object for allowing the reader to recognize the tag in consideration of the estimated attachment position of the tag, in the storage unit .

In the learning-based logistics automation apparatus according to the present invention, the control unit controls the robot arm according to rotation angle information of the object, rotates the object to be recognized, and recognizes the recognition tag to the reader .

In the learning-based logistics automation apparatus of the present invention, the tag and the tag for recognition are bar codes or QR codes.

According to another aspect of the present invention, there is provided a learning-based logistics automation method for a logistics automation system, comprising the steps of: determining a shape of an object to which a tag is attached, the logistics automation device gripping the object according to the shape of the object; The method according to claim 1, further comprising the steps of: estimating an attachment position of the tag by recognizing the tag in a reader; determining the grip position of the object in consideration of the shape of the object and the attachment position of the tag; The method according to claim 1, further comprising the steps of: storing location information; determining the type of the object to be authenticated by the logistics automation apparatus and confirming the grip position information corresponding to the determined type; Recognizing the recognition tag attached to the object to be recognized by the reader .

In the learning-based logistics automation method of the present invention, the step of estimating the attachment position may include the steps of: the product automation device grasping the object and approaching the reader; Rotating the object so that the exposed surface of the object is changed, and if the automated logistics apparatus fails to recognize the tag by the reader, the object is again gripped using another gripping position, and the exposed surface of the object adjacent to the reader And estimating an attachment position of the tag according to an angle at which the object is rotated when the automatic recognition device recognizes the tag by the reader.

In the learning-based logistics automation method of the present invention, the storing step further stores the rotation angle information of the object for recognizing the tag to the reader in consideration of the estimated attachment position of the tag .

In the learning-based logistics automation method of the present invention, the recognizing step is characterized in that the logistics automation device rotates the object to be recognized according to rotation angle information of the object and recognizes the recognition tag to the reader do.

According to another aspect of the present invention, there is provided a learning-based logistics automation method for a logistics automation system, comprising the steps of: determining a shape of an object to which a tag is attached, the logistics automation device gripping the object according to the shape of the object; The method according to claim 1, further comprising the steps of: estimating an attachment position of the tag by recognizing the tag in a reader; determining the grip position of the object in consideration of the shape of the object and the attachment position of the tag; The method according to claim 1, further comprising the steps of: storing location information; determining the type of an object to be authenticated by the logistics automation device; and checking finger position information corresponding to the determined type, Recognizing the recognition tag attached to the object to be recognized by the reader, Wherein the reader comprises a step of outputting a recognition result for the recognition tag.

According to another aspect of the present invention, there is provided a computer-readable recording medium storing a program for performing the learning-based physical distribution method.

According to the learning-based logistics automation system, apparatus, and method of the present invention, when a tag is recognized by a robot arm by gripping it with a robot arm according to the shape of an object, It is possible to recognize the tag by learning the appropriate grip position for various types of objects by recognizing the tag by the robot arm according to the learned grip position and recognizing the tag by the reader.

In this way, even in the case of a tagged object with a two-dimensional image such as a bar code and a QR code, it is possible to position the tag at a recognizable position by gripping a proper position using the robot arm, The cost can be reduced.

1 is a view showing a learning-based logistics automation system according to an embodiment of the present invention.
2 is a block diagram of a learning-based logistics automation apparatus according to an embodiment of the present invention.
FIG. 3 is a flowchart illustrating a learning-based logistics automation method according to an exemplary embodiment of the present invention.

In the following description, only parts necessary for understanding the embodiments of the present invention will be described, and the description of other parts will be omitted so as not to obscure the gist of the present invention.

The terms and words used in the present specification and claims should not be construed as limited to ordinary or dictionary meanings and the inventor is not limited to the meaning of the term in order to describe his invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely preferred embodiments of the present invention, and are not intended to represent all of the technical ideas of the present invention, so that various equivalents And variations are possible.

The present invention relates to a method for automating logistics using a tag attached to an object. Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a view showing a learning-based logistics automation system according to an embodiment of the present invention, and FIG. 2 is a diagram illustrating a configuration of a learning-based logistics automation apparatus according to an embodiment of the present invention.

1 and 2, the logistics automation apparatus 100 includes a robot arm 20 for holding an object 1 and a reader 2 for recognizing a tag 2 attached to the object 1 Device.

When the object 1 placed on the conveyor 3 approaches, the automatic logistics apparatus 100 determines an appropriate gripping position according to the shape of the object 1, grasps the gripping position, approaches the reader 200, The reader 200 attempts to recognize the tag 2 attached to the tag 1. In this case, the tag 2 attached to the object 1 may include code information in the form of a two-dimensional image such as a bar code or a QR (Quick Response) code.

At this time, the logistics automation apparatus 100 controls the gripping position of the object 1 by adjusting the rotation angle of the joint 21, which controls the operation of the robot arm 20, Or the tag 2 can be recognized by the reader 200 by rotating the object 1 so that the exposed surface of the object 1 exposed to the reader 200 side is changed.

The automatic logistics apparatus 100 grasps the object 1 and if it succeeds in recognizing the tag 2 attached to the object 1 to the reader 200, When the similar object of the recognition object is found, the reader 200 grasps the recognition tag attached to the recognition object in accordance with the stored information.

The logistics automation apparatus 100 for performing the above operation comprises a type determination unit 10, a robot arm 20, a storage unit 30, and a control unit 40.

The shape determination unit 10 determines the shape of the object 1 to be gripped and includes a camera, a stereo camera, a scanner, and the like. The shape determination unit 10 can determine the boundary of the object 1 according to the change of the pixel value in the photographed image of the camera or determine the three-dimensional shape of the object 1 using the photographed image or the scanned image of the stereo camera . The shape determination unit 10 transmits the result of the determination of the shape of the object 1 to the control unit 40. [

The robot arm 20 moves the position so that the reader 2 can recognize the tag 2 by grasping the object 1. The robot arm 20 moves on the conveyor 3 by the rotation of the joint 21 under the control of the control unit 40 to grasp the adjacent object 1 to approach the reader 200, 1 attached to the object 1 is rotated with the rotation of the joint 21 so as to be close to the reader 200 so that the exposed surface of the object 1 exposed in the direction of the reader 200 is changed, 2) can be recognized by the reader 200.

The storage unit 30 is a storage for storing information. The control unit 40 controls the robot arm 20 to grip the object 1 and recognize the tag 2 in the reader 200. The storage unit 30 stores the object 2 1) and the grip position information when the reader 200 recognizes the tag 2 are stored.

The control unit 40 generally controls the operation of the logistics automation apparatus 100 including the type determination unit 10, the robot arm 20 and the storage unit 30, and includes a calculation unit, a memory, Program storage, and the like.

The control unit 40 determines the gripping position of the object 1 according to the shape of the object 1 determined by the shape determining unit 10 and controls the robot arm 20 so that the object 1 ). The control unit 40 recognizes the tag 2 attached to the gripped object 1 to the reader 200 and estimates the position of the tag 2 attached to the object 1. [

The control unit 40 controls the robot arm 20 to grasp the object 1 to approach the reader 200 and then controls the robot arm 20 to move the object 1 exposed in the direction of the reader 200, The object 1 is rotated so that the tag 2 is recognized. If the control unit 40 does not recognize the tag 2 by the reader 200, the control unit 40 controls the robot arm 20 to lower the object 1 held by the robot arm 20, And again grasps the tag 2 by rotating the object 1 so that the exposed surface of the object 1 exposed in the direction of the reader 200 is controlled by controlling the robot arm 20. [ When the control unit 40 recognizes the tag 2 to the reader 200 through the above process, the control unit 40 sets the rotation angle of the object 1 at the time of recognizing the tag 2 to the reader 200 The attachment position of the tag 2 can be estimated.

The control unit 40 estimates the position of the tag 2 attached to the object 1 in such a manner that the shape of the object 1 determined by the shape determination unit 10 and the attachment position of the tag 2 are considered, 2) of the object (1) to be recognized by the reader (200). The control unit 40 stores the gripping position information of the determined object 1 in the storage unit 30 together with the type information of the object 1 determined by the shape determination unit 10 and stores the gripping position information corresponding to the shape of the object 1 Learn the grip position.

The control unit 40 may store the rotation angle information of the object 1 for allowing the reader 200 to recognize the tag 2 in the storage unit 30 in consideration of the attachment position of the estimated tag 2. For example, when the object 1 is rotated to recognize the tag 2 attached to the object 1 by the reader 200, the control unit 40 controls the rotation of the joint 21 included in the robot arm 20 It is possible to grasp the motion and store the rotation angle information by grasping the rotation angle of the object 1 according to the rotation motion of the joint 21 when the tag 2 is recognized by the reader 200. [

Thereafter, the control unit 40 utilizes the learning result to recognize the tag for recognition attached to another object to be recognized by the reader 200. [

That is, the control unit 40 recognizes the shape of the object to be recognized through the type determination unit 10, refers to the storage unit 30 with the type information corresponding to the recognized shape, and stores the corresponding grip position information in the storage unit 30 ).

Then, the control unit 40 controls the robot arm 20 according to the identified finger position to grasp the object to be recognized, and recognizes the recognition tag attached to the object to be grasped by the reader 200. [

If the control unit 40 stores the rotation angle information of the object 1 for allowing the reader 200 to recognize the tag 2 attached to the object 1 in the storage unit 30, The reader 200 can recognize the tag for recognition attached to the object by rotating the gripped object by controlling the robot arm 20 according to the previously stored rotation angle information. In this case, the control unit 40 rotates the joint 21 of the robot arm 20 according to the rotation angle information of the object 1 stored in the storage unit 30, thereby recognizing the recognition tag in the reader 200 The reader 2 can be efficiently recognized by the reader 200. In this case,

The reader 200 recognizing the recognition tag attached to the object to be recognized can output the recognition result to a screen of the user device and confirm the recognition result.

A method of recognizing a tag attached to an object and automating the logistics based on learning according to the present invention will be described in detail with reference to FIG.

FIG. 3 is a flowchart illustrating a learning-based logistics automation method according to an exemplary embodiment of the present invention.

Referring to FIG. 3, the logistics automation device determines the shape of the tagged object (S1).

The logistics automation device in step S1 can determine the shape of an object using a camera, a stereo camera, a scanner, or the like.

A tag attached to an object may include code information in the form of a two-dimensional image such as a bar code or a QR code.

The logistics automation device grasps the object using the robot arm according to the shape of the object, recognizes the tag attached to the object, and estimates the tag attachment position (S2).

In step S2, the logistics automation apparatus grasps an object using a robot arm, approaches the reader, rotates the object so that the exposed surface of the object exposed in the direction of the reader is changed using the robot arm holding the object, Try to make the tag recognizable. If the logistics automation device does not recognize the tag in the reader, the logistics automation device can use the robot arm to lower the object held by the robot arm, grasp it again using another gripping position, and use the robot arm to move the object exposed in the direction of the reader The tag is recognized again by rotating the object so that the exposed surface is changed. If the logistics automation device recognizes the tag in the reader, the logistics automation device can estimate the tag attachment position according to the rotation angle of the object when the tag is recognized in the reader.

Then, the logistics automation apparatus determines the gripping position of the object suitable for recognizing the tag in the reader in consideration of the shape of the object determined in step S1 and the attachment position of the tag estimated in step S2 (S3) And the finger position information for tag recognition are stored and learned (S4).

In step S4, the logistics automation device may store the rotation angle information of the object for recognizing the tag in the reader in consideration of the attachment position of the tag estimated in step S2.

Then, the logistics automation device utilizes the learning result to recognize the recognition tag attached to another recognition object to the reader. First, the logistics automation device uses a camera, a stereo camera, a scanner, And confirms the grip position information corresponding to the type determined in the information stored in step S4 (S5).

Then, the logistics automation apparatus grasps the object to be recognized by using the robot arm according to the grip position confirmed in step S5, and recognizes the recognition tag attached to the object to be recognized in the reader (S6).

If the logistics automation device of step S4 stores the rotation angle information of the object for recognizing the tag attached to the object to the reader, the logistics automation device of step S6 stores the rotation angle information of the robot arm The recognition tag attached to the object to be recognized can be recognized by the reader by rotating the object to be recognized.

The reader recognizing the tag for recognition attached to the object to be recognized outputs the recognition result to a screen of the user apparatus and confirms the recognition result (S7).

The learning-based logistics automation method according to the embodiment of the present invention can be implemented in a form of a readable program through various computer means and recorded in a computer-readable recording medium.

It should be noted that the embodiments disclosed in the present specification and drawings are only illustrative of specific examples for the purpose of understanding, and are not intended to limit the scope of the present invention. It will be apparent to those skilled in the art that other modifications based on the technical idea of the present invention are possible in addition to the embodiments disclosed herein. Furthermore, although specific terms are used in this specification and the drawings, they are used in a generic sense only to facilitate the description of the invention and to facilitate understanding of the invention, and are not intended to limit the scope of the invention.

1: object
2: Tag
3: Conveyor
10:
20: Robot arm
30:
40:
100: Logistics automation equipment
200: reader

Claims (12)

A reader that recognizes the tag; And
A robot arm for holding the object, a storage unit for storing information, and a robot arm for controlling the robot arm according to the shape of the object determined by the shape determination unit to grasp the object, The tag attached to the object is recognized by the reader to estimate the attachment position of the tag and the grip position of the object is determined in consideration of the shape of the object and the attachment position of the tag, The control unit checks the grip position information corresponding to the type of the object determined by the type determination unit in the storage unit and controls the robot arm according to the identified grip position to determine whether the recognition object And a controller for holding the object and recognizing the tag for recognition attached to the object to be recognized by the reader Automation equipment; Lt; / RTI >
Wherein,
Controlling the robot arm to grasp the object and approach the reader, rotate the object so that the exposed surface of the object exposed in the reader direction is changed, and if the reader can not recognize the tag, The tag is re-gripped using another grip position and the object is rotated so that the exposed surface of the object adjacent to the reader is changed. When the tag is recognized by the reader, Learning based logistics automation system. A shape determination unit for determining the shape of the object to be gripped;
A robot arm for gripping the object;
A storage unit for storing information; And
The robot arm is controlled according to the shape of the object determined by the shape determination unit to grasp the object and the tag attached to the object is recognized by the reader to estimate the attachment position of the tag, Determines the gripping position of the object in consideration of the attachment position of the object, stores the shape information and grip position information of the object in the storage unit, and then stores the grip position information corresponding to the shape of the object determined by the shape determination unit A control unit which is recognized by the storage unit and controls the robot arm according to the identified grip position to grasp the object to recognize the recognition tag attached to the object to be recognized by the reader; Lt; / RTI >
Wherein,
Controlling the robot arm to grasp the object and approach the reader, rotate the object so that the exposed surface of the object exposed in the reader direction is changed, and if the reader can not recognize the tag, The tag is re-gripped using another grip position and the object is rotated so that the exposed surface of the object adjacent to the reader is changed. When the tag is recognized by the reader, Based on the result of the analysis. delete 3. The method of claim 2,
Wherein,
And further stores the rotation angle information of the object for recognizing the tag in the reader in consideration of the estimated attachment position of the tag, in the storage unit. 5. The method of claim 4,
Wherein,
And the recognition tag is recognized by the reader by controlling the robot arm in accordance with rotation angle information of the object to rotate the recognition object. 3. The method of claim 2,
The tag and the tag for recognition,
Bar code, or QR code. The method comprising the steps of: determining the type of the tagged object;
Estimating an attachment position of the tag by holding the object according to the shape of the object and recognizing the tag in the reader;
Determining the grip position of the object in consideration of the shape of the object and the attachment position of the tag and storing the shape information and grip position information of the object;
Determining the shape of the object to be recognized by the automatic logistics apparatus and confirming the grip position information corresponding to the determined shape; And
Recognizing the recognition tag attached to the recognition object to the reader by grasping the recognition object according to the identified finger position; Lt; / RTI >
The step of estimating the attachment position includes:
The automated logistics device grasping the object and accessing the reader;
Rotating the object such that the automated control apparatus changes the exposed surface of the object exposed in the reader direction;
Holding the object again using another gripping position and rotating the object so that the exposed surface of the object adjacent to the reader is changed when the automatic control device does not recognize the tag by the reader; And
Estimating an attachment position of the tag according to an angle at which the object is rotated when the RFID tag recognizes the RFID tag by the reader;
Wherein the learning-based logistics automation method comprises: delete 8. The method of claim 7,
Wherein the storing step comprises:
Further comprising storing the rotation angle information of the object for allowing the reader to recognize the tag in consideration of the estimated attachment position of the tag. 10. The method of claim 9,
Wherein the recognizing comprises:
And the logistics automation device rotates the object to be recognized in accordance with rotation angle information of the object to recognize the recognition tag to the reader. The method comprising the steps of: determining the type of the tagged object;
Estimating an attachment position of the tag by holding the object according to the shape of the object and recognizing the tag in the reader;
Determining the grip position of the object in consideration of the shape of the object and the attachment position of the tag and storing the shape information and grip position information of the object;
Determining the shape of the object to be recognized by the automatic logistics apparatus and confirming the grip position information corresponding to the determined shape;
Recognizing the recognition tag attached to the recognition object to the reader by grasping the recognition object according to the identified finger position; And
Outputting a recognition result of the recognition tag by the reader; Lt; / RTI >
The step of estimating the attachment position includes:
The automated logistics device grasping the object and accessing the reader;
Rotating the object such that the automated control apparatus changes the exposed surface of the object exposed in the reader direction;
Holding the object again using another gripping position and rotating the object so that the exposed surface of the object adjacent to the reader is changed when the automatic control device does not recognize the tag by the reader; And
Estimating an attachment position of the tag according to an angle at which the object is rotated when the RFID tag recognizes the RFID tag by the reader;
Wherein the learning-based logistics automation method comprises: A computer-readable recording medium recording a program for performing the learning-based logistics automation method according to claim 7 or 11.

Images