KR20220090137A - Smart EOAT robot system - Google Patents

Abstract

The present invention relates to a smart EOAT (End Of Arm Tooling) robot system, and more specifically, by gripping a disk, which is a work object, which has a specific radius and width, and is stored in a plurality in a loading box, in the direction of the width, It relates to a smart EOAT robot system that can be loaded into a point. That is, the smart EOAT robot system approaches the disk in the direction of the width rather than the front (the direction in which the shape of the circle is seen), and receives it to accurately grip even when the contact area with the work object is narrow and the contact area is not flat. It is characterized in that it includes an additional receiving assistant that can assist.

Description

Smart EOAT robot system {Smart EOAT robot system}

The present invention relates to a smart EOAT robot system, and more particularly, a smart EOAT for loading a disk having a specific radius and width, a plurality of work objects stored in a loading box, in the width direction, and loading it at a desired target point. It is about robot systems.

In general, industrial robots refer to robots that are actually used in industrial sites such as lines in factories, and are attracting attention as one of the future means to overcome the physical limitations of humans.

In addition, it is an automatic machine that performs various tasks in the field centered on the manufacturing industry, and many have a built-in small computer, and is structurally composed of a manipulator that replaces the function of a human arm or hand.

The main uses of industrial robots are assembly, machining, warehousing, inspection and measurement, press, resin processing, and welding. have.

In addition, EOAT (End of Arm Tooling) refers to any product or accessory that can hold an object desired by a real operator or provide related applications through various products in the form of a gripper at the end of the robot. EOAT and accessories such as a vision or gripper that act as eyes are required to use it, and the accessory must be used cooperatively like a robot, but it can be used according to the actual manufacturing site.

In addition, in the case of EOAT, the word End Effector is also used equally/significantly, and End Effector mainly refers to a part (tool) that has a function that directly acts on a work object when a robot is working, a gripper, Examples include welding torches, spray guns, or nut runners.

Conventional industrial robots are manufactured with a structure that grips the side of the object, and space loss occurs in the pallet due to the limitations of the articulated robot, thereby reducing production efficiency and generating interference space when setting the vision coordinate system. to be.

In other words, when the work object is placed on the upright side (narrow width), the exact position of the work object may not be recognized, resulting in a problem that the position cannot be accurately grasped. Therefore, there was a problem in that it was difficult to access the work object, so precise control was difficult, and the contact area was small when receiving the work object, which is easily damaged due to its high sensitivity (fragile). There was a problem that could be damaged.

Republic of Korea Patent Publication No. 10-2019-0022559

The present invention has been devised in view of the above problems, and an object of the present invention is to hold an object from the front of the robot without gripping the side of the work object, that is, it is manufactured in a structure that can hold an upright object, space loss It is to provide a smart EOAT robot system to increase production efficiency because this does not occur and to reduce factors that may cause interference space when setting the Vision coordinate system.

Another object of the present invention is that, when the work object is a metal material, a sufficient force can be applied even if the contact area is narrow by utilizing gripping using magnetism, and when the work object is a non-metal material, magnetism is utilized. Since it is difficult to do so, it is to provide a smart EOAT robot system to apply sufficient force even in a small area such as spring, jaw, and adsorption.

The purpose of the embodiments of the present invention is not limited to the above-mentioned purpose, and other objects not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description. .

According to the features for achieving the above object, the present invention is a smart EOAT robot system 10000 that receives a work object 9000 from a loading box and loads it to a desired target point,

The smart EOAT robot system 10000 is,

EOAT unit 1000 for processing in contact with the work object 9000;

a vision imaging unit 2000 located at a remote location from the EOAT unit 1000 and imaging the work object 9000 and/or the EOAT unit 1000 and/or the target point;

a robot control unit 3000 for controlling the movement and operation of the EOAT unit 1000 and the vision imaging unit 2000; and

a communication unit 4000 responsible for transmitting and receiving data between the smart EOAT robot system 10000 and the outside;

The EOAT unit 1000 includes a plurality of finger units 1100,

Further comprising a receiving auxiliary unit 1200 that can help the receiving of the work object 9000 by adding an additional force to the finger unit 1100,

The receiving auxiliary unit 1200 is characterized in that it is provided in various ways according to the type and location of the work object (9000).

In addition, the receiving auxiliary unit 1200 includes a magnetic adhesive member 1210 capable of tensioning the work object by magnetic force when the work object 9000 is a material attached to a magnet, and the magnetic adhesive member 1210 ) is characterized in that it is formed on a surface in contact with the work object 9000 at the end of the finger part 1100 .

In addition, the receiving auxiliary unit 1200 is a chemical adhesive member on the surface in contact with the work object 9000 so that the work object 9000 is a material that does not stick to the magnet, so that the work object can be tensioned by a chemical action. and 1220, wherein the chemical adhesive member is formed of a pad adhesive part and a wedge part formed on the pad adhesive part.

In addition, when the receiving auxiliary unit 1200 is a material through which a current can flow in the work object 9000, it is electrically attached to the surface in contact with the work object 9000 so that the work object can be tensioned by an electrical action. It is characterized in that it includes a member (1230).

In addition, the electrical adhesive member 1230 includes an insulating member in contact with the finger part 1100 and a conductive member formed on an upper surface of the insulating member, and applying a voltage to the conductive member, the work object 9000 It is characterized by using static electricity generated by inducing an electrical opposite polarity to the

In addition, the receiving auxiliary unit 1200 applies a negative pressure to the work object 9000 so as to tension the work object, a single or a plurality of adsorption members 1240 on the surface in contact with the work object 9000. characterized in that

In addition, the robot information data transmitted from the communication unit 4000 is an image captured by the vision capturing unit 2000, an image capturing time of the image, and a target point or a receiving point recorded by the robot controller 3000 at the capturing time. It is characterized in that it includes offset information of and.

In addition, the smart EOAT robot system 10000 is,

It is located in a remote location of the robot, characterized in that it further comprises a backend server unit (6000) that can transmit and receive data from the smart EOAT robot system (10000).

In addition, the back-end server unit 6000,

a server communication unit 6300 for receiving the robot information data of the communication unit 4000;

a neural network learning unit 6100 that adds, stores and/or manages robot identification information to the received robot information data, and applies a predetermined neural network learning method to the robot information data;

and a determination unit 6200 for estimating and determining the state of the robot system 10000 through the learning result learned by the neural network learning unit 6100.

In addition, the neural network learning unit 6100 learns a plurality of data obtained from the backend server unit 6000, and estimates whether the data is noise using a suitable neural network according to the type of each data. do it with

In addition, the neural network learning unit 6100 uses an LSTM (Long Short Term Memory)-based model, which is an unsupervised learning model, when the type of data is offset information, and R- when the type of data is image data. Using CNN and Fast R-CNN, it is characterized in that it recognizes objects in image data.

In addition, the determination unit 6200 learns and predicts the operation method of the EOAT unit 1000 and the reception and landing of the work object 9000 through the neural network learning unit 6100, and the work object 9000 When it is estimated that the landing prediction point of the target point deviates from the reference threshold, data indicating that the landing of the work object 9000 will fail is transmitted to the robot controller 3000 .

In addition, the EOAT unit 1000 further includes an actuator 1300 that converts an energy source provided from the outside into a mechanical force,

The actuator 1300 is controlled by the robot control unit 3000,

The actuator 1300 is characterized in that it receives the work object 9000 using a pneumatic or hydraulic method.

In addition, the EOAT unit 1000 further includes a grip unit 1400 that grips the work object 9000 by using the mechanical force received from the actuator 1300,

The grip part 1400 is characterized in that it grips the work object 9000 by using a driving link and an operation link, and further includes an elastic auxiliary part to apply a gripping force.

According to the smart EOAT robot system of the present invention, it is manufactured in a structure that can hold an object from the front of the robot without gripping the side of the work object, that is, an upright object, so that there is no space loss, so production efficiency is increased, When setting the Vision coordinate system, there is an effect of reducing the factor that may cause an interference space.

In addition, when the work object is a metal material, a sufficient force can be applied even if the contact area is narrow by utilizing gripping using magnetism, and when the work object is a non-metal material, it is difficult to utilize magnetism, It has the effect of applying sufficient force even in a narrow area such as a spring, jaw, and adsorption.

1 is a schematic diagram showing a smart EOAT robot system according to an embodiment of the present invention;
2 is a block diagram illustrating a smart EOAT robot system according to an embodiment of the present invention;
3 is a block diagram illustrating an EOAT unit of a smart EOAT robot system according to an embodiment of the present invention.

The following objects, other objects, features and advantages of the present invention will be readily understood through the following preferred embodiments in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms.

Rather, the embodiments introduced herein are provided so that the disclosed subject matter may be thorough and complete, and that the spirit of the present invention may be sufficiently conveyed to those skilled in the art.

Embodiments described and illustrated herein also include complementary embodiments thereof.

In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, the terms 'comprise' and/or 'comprising' do not exclude the presence or addition of one or more other components.

Hereinafter, the present invention will be described in detail with reference to the drawings. In describing the specific embodiments below, various specific contents have been prepared to more specifically explain and help the understanding of the invention. However, those skilled in the art enough to understand the present invention can recognize that it can be used without these various specific contents. In some cases, it is mentioned in advance that parts that are commonly known and not largely related to the invention in describing the invention are not described in order to avoid confusion in describing the invention.

1 is a schematic diagram illustrating a smart EOAT robot system according to an embodiment of the present invention, FIG. 2 is a block diagram illustrating a smart EOAT robot system according to an embodiment of the present invention, and FIG. It is a block diagram illustrating an EOAT unit of a smart EOAT robot system according to an embodiment.

1 to 3, the smart EOAT robot system 10000 according to an embodiment of the present invention receives the work object 9000 from the loading box, and loads the work object 9000 to the desired target point. ) is about

The smart EOAT robot system 10000 according to the present invention includes an EOAT unit 1000 that contacts and processes the work object 9000, and the EOAT unit 1000 and is located at a remote location and the work object 9000 and / Alternatively, the EOAT unit 1000 and/or the vision imaging unit 2000 for imaging the target point, and the robot controller 3000 for controlling the movement and operation of the EOAT unit 1000 and the vision imaging unit 2000 ; and a communication unit 4000 responsible for data transmission/reception between the smart EOAT robot system 10000 and the outside, and the EOAT unit 1000 includes a plurality of finger units 1100 and additional force to the finger units 1100. In addition, it further includes a receiving auxiliary unit 1200 that can help to receive the work object 9000, wherein the receiving auxiliary unit 1200 is provided in various ways depending on the type and location of the work object 9000. .

Here, the receiving auxiliary unit 1200 may be manufactured in various forms in consideration of the shape, size, etc. of the work object 1200 to facilitate receipt of the work object 1200, and the smart EOAT robot system 10000 may be coupled to one side of the robot arm unit 5000 installed on one side of the work object 9000 .

In addition, the receiving auxiliary unit 1200 includes a magnetic adhesive member 1210 capable of tensioning the work object by magnetic force when the work object 9000 is a material attached to a magnet, and the magnetic adhesive member ( 1210 may be formed at the end of the finger part 1100 on a surface in contact with the work object 9000 .

More specifically, the magnetic adhesive member 1210 may be formed of a permanent magnet or an electromagnet.

In addition, when the magnetic adhesive member 1210 is in the form of an electromagnet, power may be supplied to the magnet member according to a control command of the robot controller 3000 .

In addition, the receiving auxiliary unit 1200, when the work object 9000 is a material that does not stick to the magnet, chemically adheres to the surface in contact with the work object 9000 so as to tension the work object by a chemical action It includes a member 1220, and the chemical adhesive member 1220 may be formed of a pad adhesive part and a wedge part formed on the pad adhesive part.

More specifically, the chemical adhesive member 1220 may be formed in a plurality of stacked structures, and is in contact with the pad adhesive part in contact with the finger part 1100 and the work object 9000, and is located on the pad adhesive part, and a plurality of It may be made of a wedge made of a fine protrusion structure.

As a result, the wedge portion uses the frictional force against the work object 9000 by the material characteristics of the wedge portion comprising the plurality of fine protrusion structures (having a length of 50 to 80 um) as described above. The receiving auxiliary unit 1200 may stably receive, pick up, or grip the work object 9000 .

Preferably, the wedge portion uses silicone rubber to form the fine protrusion structure, and the pad bonding portion may be formed of a polyimide thin film.

In addition, when the receiving auxiliary unit 1200 is a material through which a current can flow in the work object 9000, it is electrically attached to the surface in contact with the work object 9000 so that the work object can be tensioned by an electrical action. A member 1230 may be included.

The electrical adhesive member 1230 includes an insulating member in contact with the finger part 1100 and a conductive member formed on an upper surface of the insulating member, and applying a voltage to the conductive member, the work object 9000 It is also possible to use static electricity generated by inducing an electrically opposite polarity to the

More specifically, the electrical adhesive member 1230 may be implemented such that the tensile force of the work object 9000 is strengthened by using a static force.

More specifically, the electrical adhesive member 1230 includes a plurality of insulating members and a conductive member installed on the insulating member, and applies a voltage to the conductive member, resulting in an electrical opposite to the work object 9000 . It is possible to induce polarity.

In addition, the receiving auxiliary unit 1200 applies a negative pressure to the work object 9000 so as to tension the work object, a single or a plurality of adsorption members 1240 on the surface in contact with the work object 9000. You may.

Here, the magnetic adhesive member, the chemical adhesive member, the electrical adhesive member, and the adsorption member may be used singly or in combination with each other according to the type, material, weight, etc. of the work object.

In one embodiment, based on the plurality of contacts in contact with the work object, at one end of the gripping part, a magnetic adhesive member is located at some of the plurality of contacts, and at some of the contacts at other positions, a chemical adhesive member and It should be noted that / or an electric adhesive member is located to assist in receiving in a hybrid form.

In addition, the robot information data transmitted from the communication unit 4000 is an image captured by the vision capturing unit 2000, an image capturing time of the image, and a target point or a receiving point recorded by the robot controller 3000 at the capturing time. It may include offset information of

Here, when the robot information data is transmitted/received between the EOAT robot system 1000 and the outside through the communication unit 4000 , in order to secure it safely, encryption suitable for wired/wireless communication may be used.

More preferably, the encryption uses a lightweight hash function suitable in such an embedded computing environment.

The lightweight hash function is a function that consumes relatively low computing power designed to ensure the integrity of transmitted or received data, excluding features that require high computing power in standard cryptographic hash algorithms such as SHA-3. It is a hash function (one-way function).

More specifically, among these lightweight hash functions, it is preferable to use a sponge algorithm that enables permutation of data without a key (unkeyed).

More specifically, the sponge makes the original message (here, the original data of the random key) a certain size (padding), and then converts it to a specific standard size that only the creator of the key can know (for example, the original message divided into a specific bit size). After dividing into plural pieces, random data is exchanged using several update functions at the rear end of the divided data (segmented original message), and on the other side, it is implemented to decode using a known reference size.

That is, by utilizing such a lightweight hash function, while securing the security of the hash function, relatively less computing power is required than the use of a general hash function, resulting in reduced power consumption and long-term use.

Meanwhile, the smart EOAT robot system 10000 may further include a backend server unit 6000 located at a remote location of the robot and capable of transmitting and receiving data from the smart EOAT robot system 10000 .

The back-end server unit 6000 includes a server communication unit 6300 that receives the robot information data of the communication unit 4000, and adds identification information of the robot to the received robot information data and stores and/or The state of the robot system 10000 through the neural network learning unit 6100 that manages and learns the robot information data by applying a predetermined neural network learning method, and the learning result learned in the neural network learning unit 6100 It is a configuration including a determination unit 6200 for estimating and determining.

At this time, the neural network learning unit 6100 learns the plurality of data obtained from the backend server unit 6000, and depending on the type of each data, it can be estimated whether the data is noise using a suitable neural network. .

As such, the neural network learning unit 6100 uses an LSTM (Long Short Term Memory)-based model, which is an unsupervised learning model, when the type of data is offset information, and R when the type of data is image data. -CNN and Fast R-CNN can be used to recognize objects in image data.

Here, the determination unit 6200 learns and predicts the operation method of the EOAT unit 1000 and the reception and landing of the work object 9000 through the neural network learning unit 6100, and the work object 9000 When it is estimated that the landing prediction point of the target point deviates from the reference threshold, data indicating that the landing of the work object 9000 is estimated to fail may be transmitted to the robot controller 3000 .

In addition, the EOAT unit 1000 further includes an actuator 1300 that converts an energy source provided from the outside into a mechanical force, the actuator 1300 is controlled by the robot control unit 3000, the actuator ( 1300 is a configuration for receiving the work object 9000 using a pneumatic or hydraulic method.

That is, the actuator 1300 is controlled by the robot control unit 3000 to operate the EOAT unit 1000 , and various methods of operation of the actuator may be utilized.

More specifically, the actuator 1300 may grip and receive the work object 9000 using a pneumatic or hydraulic method.

In addition, the EOAT unit 1000 further includes a grip unit 1400 that grips the work object 9000 using the mechanical force received from the actuator 1300 , and the grip unit 1400 operates with a drive link. Using the link, doedoe grab the work object 9000, by further including an elastic auxiliary part, it is also possible to add a gripping force.

More specifically, the grip unit 1400 may be configured to grip the work object 900 by using a plurality of driving links and a plurality of operation links to form a kind of finger.

In addition, the grip part 1400 includes an elastic auxiliary part that applies a force to the surface to be adhered through elasticity at the moment of starting to grip the work object 900 so as to supplement the grip force using the link structure, The gripping force can be added.

The elastic auxiliary part may be implemented to add an elastic force when a predetermined force is applied in a specific direction by using a leaf spring in an embodiment.

In one embodiment, the EOAT unit 1000 further includes a grip unit 1400 for gripping the work object 9000, wherein the grip unit 1400 uses a plurality of driving links and a plurality of operation links, Formed in the form of a kind of finger, it is configured to grip the work object 9000, and the last link structure of the finger portion of the small grip part 1400, that is, the link structure portion closest to the surface in contact with the work object is composed of a leaf spring The gripping force can be increased by providing an elastic auxiliary part.

However, in this structure of the plate spring elastic auxiliary tool, an additional force is applied to the work object 9000 at the time when the leaf spring starts to operate, and scratches or scratches on the outer surface of the work object 9000 through the grip part 1400, etc. may cause problems with

In preparation for this case, the above-described chemical adhesive member 1220 may be formed on a surface in contact with the work object 9000 due to the operation of the leaf spring.

More specifically, it is possible to prevent a problem from occurring on the outer surface of the work object 9000 while adding an auxiliary gripping force by adding the pad bonding portion and the wedge portion of the chemical adhesive member 1220 .

Therefore, according to the smart EOAT robot system of the present invention, it is manufactured in a structure that can grip the object from the front of the robot without gripping the side of the work object, that is, an upright object, so that there is no space loss, so production efficiency is increased In addition, there is an effect of reducing the factor that may cause an interference space when setting the Vision coordinate system.

In addition, when the work object is a metal material, a sufficient force can be applied even if the contact area is narrow by utilizing gripping using magnetism, and when the work object is a non-metal material, it is difficult to utilize magnetism, It has the effect of applying sufficient force even in a narrow area such as a spring, jaw, and adsorption.

The embodiments described in this specification and the configurations shown in the drawings are merely the most preferred embodiment of the present invention and do not represent all the technical spirit of the present invention, so various equivalents that can be substituted for them at the time of the present application It should be understood that there may be variations and examples.

10000: smart EOAT robot system 1000: EOAT unit
1100: finger part 1200: receiving auxiliary part
2000: vision imaging unit 3000: robot control unit
4000: communication unit 6000: back-end server unit
6100: neural network learning unit 6200: judgment unit
6300: server communication unit 9000: work object

Claims (14)

In the smart EOAT robot system 10000 for receiving the work object 9000 from the loading box and loading it at a desired target point,
The smart EOAT robot system 10000 is,
EOAT unit 1000 for processing in contact with the work object 9000;
a vision imaging unit 2000 located at a remote location from the EOAT unit 1000 and imaging the work object 9000 and/or the EOAT unit 1000 and/or the target point;
a robot control unit 3000 for controlling the movement and operation of the EOAT unit 1000 and the vision imaging unit 2000; and
a communication unit 4000 responsible for transmitting and receiving data between the smart EOAT robot system 10000 and the outside;
The EOAT unit 1000 includes a plurality of finger units 1100,
Further comprising a receiving auxiliary unit 1200 that can help the receiving of the work object 9000 by adding an additional force to the finger unit 1100,
The receiving auxiliary unit 1200 is a smart EOAT robot system, characterized in that provided in various ways according to the type and location of the work object (9000).
The method according to claim 1,
The receiving auxiliary unit 1200 includes a magnetic adhesive member 1210 capable of tensioning the work object by magnetic force when the work object 9000 is a material attached to a magnet, and the magnetic adhesive member 1210 is Smart EOAT robot system, characterized in that formed on a surface in contact with the work object (9000) at the end of the finger part (1100).
The method according to claim 1,
The receiving auxiliary unit 1200 is a chemical adhesive member 1220 on the surface in contact with the work object 9000 so that the work object 9000 is a material that does not stick to the magnet, so that the work object can be tensioned by a chemical action. ), wherein the chemical adhesive member is a smart EOAT robot system, characterized in that it is formed of a pad adhesive part and a wedge formed on an upper part of the pad adhesive part.
The method according to claim 1,
When the receiving auxiliary unit 1200 is a material through which a current can flow in the work object 9000, an electrical adhesive member ( 1230), characterized in that it comprises a smart EOAT robot system.
5. The method according to claim 4,
The electrical adhesive member 1230 includes an insulating member in contact with the finger part 1100 and a conductive member formed on an upper surface of the insulating member, and applies a voltage to the conductive member to electrically connect the work object 9000. Smart EOAT robot system, characterized in that it uses static electricity generated by inducing opposite polarity.
The method according to claim 1,
The receiving auxiliary unit 1200 applies a negative pressure to the work object 9000 so as to tension the work object, a single or a plurality of adsorption members 1240 on the surface in contact with the work object 9000. Smart EOAT robot system featuring.
The method according to claim 1,
The robot information data transmitted from the communication unit 4000 includes the image captured by the vision imaging unit 2000, the imaging time of the image, and the target point or the receiving point recorded by the robot control unit 3000 at the imaging time. Smart EOAT robot system comprising offset information.
8. The method of claim 7,
The smart EOAT robot system 10000 is,
The smart EOAT robot system, located at a remote location of the robot, further comprising a backend server unit (6000) capable of transmitting and receiving data from the smart EOAT robot system (10000).
9. The method of claim 8,
The back-end server unit 6000,
a server communication unit 6300 for receiving the robot information data of the communication unit 4000;
a neural network learning unit 6100 that adds, stores and/or manages robot identification information to the received robot information data, and applies a predetermined neural network learning method to the robot information data;
The smart EOAT robot system, characterized in that it comprises a determination unit (6200) for estimating and determining the state of the robot system (10000) through the learning result learned by the neural network learning unit (6100).
10. The method of claim 9,
The neural network learning unit 6100 learns a plurality of data obtained from the backend server unit 6000, and according to the type of each data, it is characterized in that it is estimated whether the data is noise using a suitable neural network. Smart EOAT robot system.
11. The method of claim 10,
The neural network learning unit 6100 uses an LSTM (Long Short Term Memory)-based model, which is an unsupervised learning model, when the type of data is offset information, and R-CNN, A smart EOAT robot system that uses Fast R-CNN to recognize objects in image data.
12. The method of claim 11,
The determination unit 6200 learns and predicts the operation method of the EOAT unit 1000 and the reception and landing of the work object 9000 through the neural network learning unit 6100, and the landing of the work object 9000 When the predicted point is estimated to deviate from the reference threshold from the target point, the smart EOAT robot system, characterized in that it transmits data indicating that the landing of the work object (9000) will fail to the robot control unit (3000).
13. The method according to any one of claims 1 to 12,
The EOAT unit 1000 further includes an actuator 1300 that converts an energy source provided from the outside into a mechanical force,
The actuator 1300 is controlled by the robot control unit 3000,
The actuator 1300 is a smart EOAT robot system, characterized in that receiving the work object (9000) using a pneumatic (pneumatic) or hydraulic (hydraulic) method.
14. The method of claim 13,
The EOAT unit 1000 further includes a grip unit 1400 that grips the work object 9000 by using the mechanical force received from the actuator 1300,
The grip unit 1400 uses a driving link and an operating link to grip the work object 9000, and further includes an elastic auxiliary unit to apply a gripping force to the smart EOAT robot system.

Images