CN111531544B - Robot control system based on image geometric matching and control method thereof - Google Patents

Abstract

The invention relates to a robot control system based on image geometric matching and a control method thereof, wherein the system comprises a main controller, a robot, a camera control assembly and a plurality of cameras; the camera is used for collecting an operation image of the robot; the camera control component is used for performing image geometric matching on the operation images so as to obtain a matching result; the main controller outputs a corresponding control signal according to the matching result; the robot controller outputs a driving signal according to the control signal; the robot hand carries out the carrying work of the container according to the driving signal. According to the invention, the camera control assembly and the cameras are arranged to form the machine vision component, the camera control assembly and the cameras are utilized to perform image recognition, the camera control assembly performs image recognition in a geometric matching mode, the working process of the robot can be monitored in real time, an automatic monitoring module is added, and the operation state of the robot is monitored in real time, so that the operation efficiency and accuracy of the robot are improved.

Description

Robot control system based on image geometric matching and control method thereof

Technical Field

The invention relates to a machine control system, in particular to a robot control system based on image geometric matching and a control method thereof.

Background

The traditional stem cell preparation is basically finished by manually adding semi-automatic equipment, a large number of preparation personnel are needed to participate in the preparation process, and the defects of low efficiency, high infection probability, high error rate, difficult quality monitoring and the like exist in the manual preparation, so that the quality of stem cell products and the risk of pollution to the stem cell products are influenced.

Along with the introduction of full-automatic equipment in the stem cell preparation process, in particular to the application of a sterile manipulator, the artificial preparation operation can be realized by aiming at the complex and fussy preparation process through a flexible programming technology, and the risk of stem cell pollution caused by direct contact of preparation personnel with an appliance is solved. The sterile robot is mainly used for carrying important containers such as centrifuge tubes and cryopreservation tubes used in the stem cell preparation process, the process is relatively complex and the working procedure is long in the stem cell preparation process, and the working points comprise a centrifuge, a weighing platform, a centrifuge tube opening/closing cover platform, a cryopreservation tube opening/closing cover platform and the like. The instruction action process of the robot for carrying the container is as follows: the robot is positioned at a safety point and waits for a main controller instruction; the robot receives the carrying path number and the work enabling energy sent by the main controller, and judges that the carrying point is provided with materials and the placing point is not provided with materials by receiving signals of the position sensor; the robot moves to a carrying point to clamp materials, the materials are judged to be in the clamp by the clamp position sensor, then the robot moves to a placing point by a preset path, the clamping jaw is loosened, and the materials are judged to be placed by the clamp position sensor; and returning the robot to the safety point, feeding back the working result to the main controller, and repeating the steps.

The application of the sterile robot hand is efficient and safe, the problem that the stem cell preparation container is transferred at each station is solved, the pollution risk caused by manual operation of operators is avoided, the problem of safe operation of new equipment is solved, the robot hand works independently and automatically for a long time, besides enough instructions are exchanged with an upper controller, the upper controller can timely and accurately master the working state and the working result of the robot hand, and a third party monitoring feedback is needed, so that each step of operation of the robot hand is ensured to run according to a preset path, and misoperation of the robot hand caused by error of instruction interaction is prevented; because the related materials such as a centrifuge tube for transporting materials, a freezing storage tube and the like are very important materials, most of the materials are provided with cell suspension, and the transportation process is carried out even in a state that the container is not closed, a clamping hand position sensor on the robot can only judge whether the clamping hand clamps the container or not, and can not sense whether the container is in a horizontal state or not; the position sensors of the container conveying point and the placement point can only sense whether the container exists at the position, and can not judge whether the container is in a horizontal state and in an offset state, and the excessive displacement of the container at the working position has great influence on the automatic process operation before and after conveying; however, the present invention is not limited to the above-mentioned problems, and the present invention is applicable to the handling of containers by operating a robot after the monitoring.

Therefore, it is necessary to design a new system to increase the automatic monitoring module and monitor the operation state of the robot in real time, so as to improve the operation efficiency and accuracy of the robot.

Disclosure of Invention

The invention aims to overcome the defects of the prior art and provide a robot control system based on image geometric matching and a control method thereof.

In order to achieve the above purpose, the present invention adopts the following technical scheme: the robot control system based on image geometric matching comprises a main controller, a robot, a camera control assembly and a plurality of cameras; the camera is used for collecting an operation image of the robot; the camera control component is used for carrying out image geometric matching on the operation images so as to obtain a matching result; the main controller is used for outputting a corresponding control signal according to the matching result; the robot controller is used for outputting a driving signal according to the control signal; and the robot arm is used for carrying out the container carrying work according to the driving signal.

The further technical scheme is as follows: the camera control component comprises an image acquisition unit, an image preprocessing unit, a geometric matching unit and a result output unit; the image acquisition unit is used for acquiring an operation image acquired by the camera; the image preprocessing unit is used for converting the operation image into a gray level image and carrying out image noise reduction and smoothing processing to obtain a preprocessed image; the geometric matching unit is used for detecting the comparison sequence number of the preprocessed image and carrying out geometric matching by combining with a preset template so as to obtain a matching result; the result output unit is used for outputting a matching result.

The further technical scheme is as follows: the camera control assembly further comprises a template setting unit; the template setting unit is used for creating a template, extracting geometric characteristic information of the template, organizing the spatial relationship between the characteristics and the features, and storing the spatial relationship in the template to form a preset template.

The further technical scheme is as follows: the main controller is connected with the robot controller through an Ethernet port.

The further technical scheme is as follows: the robot controller is connected with the camera control assembly through Socket protocol.

The further technical scheme is as follows: the model of the main controller is R04EN.

The further technical scheme is as follows: the main controller is provided with a plurality of connection interfaces, and the connection interfaces are RJ45 interfaces.

The further technical scheme is as follows: the main controller is connected with the camera control assembly through Socket protocol.

The invention also provides a control method of the robot control system based on image geometric matching, which comprises the following steps:

the camera collects an operation image of the robot;

the camera control component performs image geometric matching on the operation images to obtain matching results;

the main controller outputs a corresponding control signal according to the matching result;

the robot controller outputs a driving signal according to the control signal;

and the robot hand carries out the carrying work of the container according to the driving signal.

The further technical scheme is as follows: the camera control component performs image geometric matching on the operation images to obtain matching results, and the method comprises the following steps:

acquiring an operation image acquired by a camera;

converting the operation image into a gray image, and performing image noise reduction and smoothing treatment to obtain a preprocessed image;

detecting the comparison sequence number of the preprocessed image, and carrying out geometric matching by combining with a preset template to obtain a matching result;

and outputting a matching result.

Compared with the prior art, the invention has the beneficial effects that: according to the invention, the camera control assembly and the cameras are arranged to form the machine vision component, the camera control assembly and the cameras are utilized to perform image recognition, the camera control assembly performs image recognition in a geometric matching mode, the working process of the robot can be monitored in real time, an automatic monitoring module is added, and the operation state of the robot is monitored in real time, so that the operation efficiency and accuracy of the robot are improved.

The invention is further described below with reference to the drawings and specific embodiments.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic block diagram of a robot control system based on geometric matching of images provided in an embodiment of the present invention;

FIG. 2 is a schematic block diagram of a camera control assembly of a robot control system based on geometric matching of images provided in accordance with an embodiment of the present invention;

fig. 3 is a flowchart of a control method of a robot control system based on geometric matching of images according to an embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the drawings and the detailed description, in order to make the objects, technical solutions and advantages of the present invention more apparent.

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.

In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be attached, detached, or integrated, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.

In the present invention, unless expressly stated or limited otherwise, a first feature "above" or "below" a second feature may include both the first and second features being in direct contact, as well as the first and second features not being in direct contact but being in contact with each other through additional features therebetween. Moreover, a first feature being "above," "over" and "on" a second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature includes the first feature being directly under and obliquely below the second feature, or simply means that the first feature is less level than the second feature.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms should not be understood as necessarily being directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, one skilled in the art can combine and combine the different embodiments or examples described in this specification.

As shown in the specific embodiments of fig. 1 to 3, the robot control system 100 based on geometric matching of images provided in this embodiment may be applied in an environment with a robot 103, such as a stem cell culturing process.

Referring to fig. 1, a robot control system 100 based on image geometry matching includes a main controller 101, a robot controller 102, a robot 103, a camera control assembly 104, and a plurality of cameras 105; a camera 105 for acquiring an operation image of the robot 103; a camera control component 104 for performing image geometric matching on the operation images to obtain a matching result; a main controller 101 for outputting a corresponding control signal according to the matching result; a robot controller 102 for outputting a driving signal according to the control signal; and a robot 103 for carrying the container according to the driving signal.

The camera 105 and the camera control component 104 complete the content of a machine vision part, the machine vision is a branch of rapid development of artificial intelligence, in the automatic production process, the machine vision is commonly used to replace the artificial vision, the machine vision is used for improving the flexibility and the automation degree of production, the handling work of the robot 103 in the stem cell preparation process needs to be similar to the monitoring means of the artificial vision, the images of the robot and the materials are collected, the values of the current material position and the calibrated material position on the horizontal offset and the vertical rotation angle are detected in a mode of image geometric matching through preprocessing, whether the path of the robot 103 in the handling process is correct or not and whether the container is in a safe state or not is identified, and the safety and the reliability of the stem cell preparation process are ensured.

The main controller 101 mainly controls the whole system in the system, various carrying tasks are issued to the robot controller 102 according to a preset production process, the robot 103 adopts a history Tao Bier TX60 stereolean robot, the maximum load of the robot is 9 kg, the working radius is 670mm, the robot 103 adopts a special joint and full-closed structure, the protection level IP65 can cope with the disinfection process in a VHP environment, and the robot controller 102CS9 provides a communication port supporting EtherCAT, modbus TCP and Ethernet Socket protocols.

In this embodiment, the number of cameras 105 is three, and the robot 103 and the material may be subjected to image capturing from both sides and the top. The camera 105 adopts the allied LXG-250C, the camera 105 is a 2500 ten thousand pixel color camera 105, and the sensor shutter is of a global type, can simultaneously capture images of the whole picture, and is suitable for shooting moving objects. The camera control assembly 104 employs an industrial computer in which LabVIEW software and an IMAQ Vison module, which is a built-in visual development kit of LabVIEW, are installed for triggering the camera 105 to capture images and process images.

In an embodiment, referring to fig. 2, the camera control assembly 104 includes an image acquisition unit 1041, an image preprocessing unit 1042, a geometry matching unit 1043, and a result output unit 1044; wherein, the image acquisition unit 1041 is used for acquiring an operation image acquired by the camera 105; an image preprocessing unit 1042 for converting the operation image into a gray image, and performing image noise reduction and smoothing processing to obtain a preprocessed image; the geometric matching unit 1043 is configured to detect a comparison sequence number of the preprocessed image, and perform geometric matching in combination with a preset template to obtain a matching result; and a result output unit 1044 for outputting a matching result.

The preset templates mainly comprise templates which are integrated by the collected characteristic information when the robot 103 is safe, reliable and accurate in carrying process. After the image processing is operated, the matching is performed by means of the preset template, and when the matching result shows that the matching degree is high, the current operation state of the robot 103 is correct. When the matching result shows that the matching degree is not high, corresponding reminding can be carried out, whether the working process of carrying the sterile robot 103 is safe and reliable or not is monitored by utilizing the image recognition technology, and the accuracy is high.

The working scene of monitoring the handling of the sterile robot 103 by the image recognition technique is divided into three parts: and detecting the form and position of the material before carrying, detecting the posture and the horizontal state of the material of the manipulator 103 in the carrying process, and detecting the form and position of the material after carrying. In the carrying process, the robot 103 can continuously change the posture of the robot according to the actual path, the image of the robot 103 is shot without time, only special path points on the path are needed to be shot, the image of the robot 103 is compared and matched with a pre-stored graphic template, so that the states of the robot 103 and materials are judged, and the calculation workload of the camera control assembly 104 is reduced.

In an embodiment, referring to fig. 2, the camera control assembly 104 further includes a template setting unit 1045; the template setting unit 1045 is configured to create a template, extract geometric feature information of the template, organize spatial relationships between features, and store the spatial relationships in the template to form a preset template.

The geometric matching of the images is firstly to create one or more templates which can represent the search targets, secondly to lift the geometric feature information of the templates, and then to organize the spatial relationships between the features and the features, and to store them in the templates. Algorithms for image geometry matching fall into two categories, one edge-based and the other feature-based. When the sterile robot 103 is detected to work, the posture of the robot 103 and the carried materials are required to be checked, the materials are not shifted to be accurately placed, the edges of the materials are only required to be detected, and then the materials are compared with a preset template to judge the positions and the rotation angles of the materials.

The content mainly set by the template design unit creates a standard template in an NI Vison template editor, learns, extracts a geometrically matched template curve, and sets parameters in the process including an extraction mode, namely a common mode and a uniform mode; an edge threshold; the edge filtering size is divided into fine mode and normal mode, and the precision of the fine mode is higher; minimum length, i.e. lift edge minimum pixel length; line search pitch, pixel unit; column search pitch, pixel unit.

In addition, some parameters may be defined manually: shielding some areas which need not to be detected; some custom lines are added manually.

The template design unit also sets the curve parameters to be searched and sets an image searching method, wherein the image searching method is used for finding out images similar to the learned template from the detected images, and the images comprise the matching quantity, the rotation angle, the score, the proportion range, the algorithm and the like. The higher the score is from 0 to 1000, which means that the higher the similarity is, the setting process of the image searching method includes the following parameters: the number of matches; matching the minimum score; sub-pixel searching; the contrast is reversed and divided into an original mode, a reverse mode and a two-mode; searching strategies; setting a search rotation range; setting a search change proportion range; setting a closing range; the algorithm is divided into an edge-based algorithm and a feature-based algorithm, and the edge-based algorithm is currently selected.

In this embodiment, the matching result includes a qualified number, a position, a rotation angle, a size ratio, a matching score, and the like.

For example: the matching results of pictures shot at different shooting sequence numbers according to geometric matching are shown in table 1.

TABLE 1 matching results of pictures taken with different taking sequence numbers

The camera 1051 is mainly used for shooting whether the material is placed horizontally or not, and as can be seen from the test image number 2, the material inclination angle is too large, and the material can be judged to be placed in an error state, so that the aseptic robot 103 is prevented from performing related carrying work by mistake.

In one embodiment, the main controller 101 and the robot controller 102 are connected through an ethernet port.

In one embodiment, the robot controller 102 and the camera control assembly 104 are connected by a Socket protocol.

In an embodiment, the model number of the main controller 101 is R04EN.

In an embodiment, the main controller 101 is provided with a plurality of connection interfaces, and the connection interfaces are RJ45 interfaces.

In an embodiment, the above-mentioned main controller 101 and the camera control component 104 are connected through Socket protocol.

The main controller 101 uses the Mitsubishi latest generation R series medium-large programmable controller, the model is R04EN, the program memory with 160K bytes is provided, the fastest processing time of instructions is 0.98ns, and simultaneously, three RJ45 interfaces are provided, and the industrial bus functions such as Ethernet, CC-Link IE and the like are provided. The main controller 101 and the camera 105 communicate with each other using an ethernet Socket communication system.

The robot controller 102 is connected with the main controller 101 through an ethernet port, the Modbus TCP protocol is used, the robot controller 102 uses the Modbus TCP as a communication server, the main controller is used as a communication client, the main controller 101 is actively connected with the robot controller 102, and according to the requirement of the action control of the robot 103, the robot 103 defines a plurality of input and holding registers at the communication port as carriers for the instruction and information feedback of the system controller and the robot 103. The robot controller 102 is connected with the camera control component 104 through the Ethernet and Socket protocol, the robot controller 102 is actively connected with the camera control component 104 in an Active mode, the communication content is a self-defined ASCII code, and the correspondence between the ASCII code and the request sent by the robot controller to the camera 105 controller is as follows: with a start symbol & start, the middle is camera 105 shooting enabled (Y is shooting, N is not needed); finally, the end symbol% is used to form ASCII code.

After photographing, image processing and image detection, the camera control component 104 responds to the information of the robot controller 102 as follows: starting with a start symbol, wherein the middle is the detection result of the camera 105 (O is passing and N is not passing) and the contrast sequence number of the detected image shot by the camera 105, specifically three digits; finally, the end symbol% is used to form ASCII code.

The transfer flow after the sterile robot 103 adds the image detection is as follows: the robot 103 is at a safe point and waits for the instruction of the main controller 101; the robot 103 receives the carrying path number and the work enabling sent by the main controller 101, and judges that the carrying point has materials and is correctly placed and the placing point has no materials by receiving the signals of the position sensor and the detection result of the camera 105; the robot 103 moves to the carrying point to clamp the material, the material is judged to be in the clamping hand through the clamping hand position sensor, whether the material is horizontal on the clamping hand is judged through image detection, then the material moves to the placing point through a preset path, and in the path of the robot 103, a specific image detection position is selected to check whether the material is in a horizontal state in the carrying process. After being carried to a placement point, the clamping jaw is loosened, the material is judged to be placed through the clamping hand position sensor, and finally whether the placed material is at a correct position is judged through image detection; the robot 103 returns to the safety point, and feeds back the working result to the system controller, and the above steps are repeated. Each step of work of the robot 103 is performed under the visual detection and monitoring, so that the robot 103 can run and detect at the same time, and the safety and accuracy of executing tasks by the robot are ensured.

According to the robot control system 100 based on geometric matching of images, the camera control assembly 104 and the cameras 105 are arranged to form the machine vision component, the camera control assembly 104 and the cameras 105 are utilized to conduct image recognition, the camera control assembly 104 conducts image recognition in a geometric matching mode, the working process of the robot 103 can be monitored in real time, an automatic monitoring module is added, the operation state of the robot 103 is monitored in real time, and therefore the operation efficiency and accuracy of the robot 103 are improved.

In an embodiment, referring to fig. 3, a control method of the robot control system 100 based on image geometric matching is further provided, including steps S110 to S150.

S110, the camera 105 acquires an operation image of the robot 103.

In the present embodiment, the operation image refers to an image taken by the robot 103 at a specific path point on the path, such as an image of the position where the container is grasped.

S120, the camera control component 104 performs image geometric matching on the operation images to obtain a matching result.

In this embodiment, the matching result refers to the matching degree of geometric matching between the photographed operation image and a preset image.

In one embodiment, the step S120 may include steps S121 to S124.

S121, acquiring an operation image acquired by the camera 105;

s122, converting the operation image into a gray image, and performing image noise reduction and smoothing treatment to obtain a preprocessed image;

s123, detecting the comparison sequence number of the preprocessed image, and carrying out geometric matching by combining with a preset template to obtain a matching result;

s124, outputting a matching result.

In this embodiment, the preprocessed image refers to an image formed by converting the image into gray scale and performing image noise reduction and smoothing processing.

S130, the main controller 101 outputs a corresponding control signal according to the matching result;

s140, the robot controller 102 outputs a driving signal according to the control signal;

and S150, carrying the container by the robot 103 according to the driving signal.

It should be noted that, as will be clearly understood by those skilled in the art, the specific implementation process of the control method of the robot control system 100 based on image geometric matching may refer to the corresponding description in the embodiment of the robot control system 100 based on image geometric matching, and for convenience and brevity of description, the description is omitted herein.

The foregoing examples are provided to further illustrate the technical contents of the present invention for the convenience of the reader, but are not intended to limit the embodiments of the present invention thereto, and any technical extension or re-creation according to the present invention is protected by the present invention. The protection scope of the invention is subject to the claims.

Claims (8)

1. The robot control system based on image geometric matching is characterized by comprising a main controller, a robot, a camera control assembly and a plurality of cameras; the camera is used for collecting an operation image of the robot; the camera control component is used for carrying out image geometric matching on the operation images so as to obtain a matching result; the main controller is used for outputting a corresponding control signal according to the matching result; the robot controller is used for outputting a driving signal according to the control signal; the robot is used for carrying out container carrying work according to the driving signals;

the camera control component comprises an image acquisition unit, an image preprocessing unit, a geometric matching unit and a result output unit; the image acquisition unit is used for acquiring an operation image acquired by the camera; the image preprocessing unit is used for converting the operation image into a gray level image and carrying out image noise reduction and smoothing processing to obtain a preprocessed image; the geometric matching unit is used for detecting the comparison sequence number of the preprocessed image and carrying out geometric matching by combining with a preset template so as to obtain a matching result; the result output unit is used for outputting a matching result;

the camera control assembly further comprises a template setting unit; the template setting unit is used for creating a template, extracting geometric characteristic information of the template, organizing the spatial relationship between the characteristics and the features, and storing the spatial relationship in the template to form a preset template;

the content mainly set by the template setting unit creates a standard template in an NI Vison template editor, learns, extracts a geometric matching template curve, and sets parameters in the process including an extraction mode, namely a common mode and a uniform mode; an edge threshold; the edge filtering size is divided into fine mode and normal mode, and the precision of the fine mode is higher; a minimum length, a lift edge minimum pixel length; line search pitch, pixel unit; column search pitch, pixel unit; by manually defining some parameters: shielding some areas which need not to be detected; manually adding some custom lines;

the template setting unit is also used for setting the searched curve parameters and setting an image searching method, wherein the image searching method is used for finding out images similar to the learned template from the detected images, and the images comprise the matching quantity, the rotation angle, the score, the proportion range and the algorithm; the higher the score is from 0 to 1000, which means that the higher the similarity is, the setting process of the image searching method includes the following parameters: the number of matches; matching the minimum score; sub-pixel searching; the contrast is reversed and divided into an original mode, a reverse mode and a two-mode; searching strategies; setting a search rotation range; setting a search change proportion range; setting a closing range; the algorithm is divided into an edge-based algorithm and a feature-based algorithm, and the edge-based algorithm is currently selected.

2. The robot control system based on geometric matching of images of claim 1, wherein the master controller is connected to the robot controller through an ethernet port.

3. The robot control system based on geometric matching of images of claim 1, wherein the robot controller and the camera control assembly are connected by a Socket protocol.

4. The image geometry matching based robot control system of claim 1, wherein the master controller is model R04EN.

5. The robot control system based on geometric matching of images according to claim 1, wherein the main controller is provided with a plurality of connection interfaces, and the connection interfaces are RJ45 interfaces.

6. The robot control system based on geometric matching of images of claim 1, wherein the master controller and the camera control assembly are connected by a Socket protocol.

7. A control method of a robot control system based on image geometric matching, the method being applied to the robot control system based on image geometric matching according to any one of claims 1 to 6, comprising:

the camera collects an operation image of the robot;

the camera control component performs image geometric matching on the operation images to obtain matching results;

the main controller outputs a corresponding control signal according to the matching result;

the robot controller outputs a driving signal according to the control signal;

and the robot hand carries out the carrying work of the container according to the driving signal.

8. The method for controlling a robot control system based on geometric matching of images according to claim 7, wherein the camera control unit performs geometric matching of images on the operation images to obtain a matching result, comprising:

acquiring an operation image acquired by a camera;

converting the operation image into a gray image, and performing image noise reduction and smoothing treatment to obtain a preprocessed image;

detecting the comparison sequence number of the preprocessed image, and carrying out geometric matching by combining with a preset template to obtain a matching result;

and outputting a matching result.

Images