Robot control method and device for smear sampling

Abstract

A control method and device for a smear sampling robot, wherein the method comprises the following steps: when the robot performs a first task on a first workbench, the robot enters a visual control mode, the visual control mode comprising the steps of: guiding actions according to a visual image received by a first visual sensor, the first visual sensor being arranged on the surface of the robot; when the robot needs to transfer from the first workbench to the second workbench, the robot enters a global guidance mode, and when the difference between a feature vector of global image information extracted by real-time analysis and an expected feature vector is less than a preset value, it is determined that the robot has entered a preset position, and the robot is switched back to the visual control mode; the above technical solution simultaneously judges the platform images by the first visual sensor and the second visual sensor, and after being analyzed by the control unit, the robot can switch between the first platform and the second platform more smoothly, thereby improving work efficiency.

Description

Technical Field

[0001] The present invention relates to the field of automation, and in particular to a method and a device for controlling a robot capable of smearing and sampling. Background Art

[0002] Recently, imported cold chain foods have been tested positive for the novel coronavirus nucleic acid many times. However, the flow of goods in the context of globalization is difficult to cut off. Therefore, the prevention and control policy must gradually transition from "preventing people as the main focus" to "preventing people and goods at the same time". Due to the impact of the epidemic, the following impacts have been caused on cold chain logistics: the order of the imported fresh food transportation chain is unbalanced, the inventory of some products has increased, and the cold storage is full; the domestic refrigerated truck transportation volume has decreased, resulting in idle transportation capacity; the refrigerated containers have been emptied and the turnover rate has decreased, which will accumulate and cause the phenomenon of refrigerated containers being stranded at the port; during the epidemic, many problems have occurred in port declaration, cold storage warehousing and distribution, such as a shortage of trailer capacity and a backlog of frozen containers, resulting in a sharp increase in additional costs and risks for refrigerated container transportation; due to the increase in the scope and items of testing, the customs clearance time for goods has been extended. In the existing technology, the main method of nucleic acid testing is to take swabs from the surface of items to detect viral nucleic acids. During the sampling process, the sampling operator needs to be in close contact with the items to be sampled, which will greatly increase the risk of cross-infection among personnel during the sampling process. The intelligent sampling robot developed in this project uses scientific and technological means to strengthen the epidemic prevention and control measures in cold chain logistics, replace manual nucleic acid sampling, improve the efficiency of new coronavirus nucleic acid testing, prevent quarantine personnel from being exposed to risks, and reduce the risk of cross-infection. Summary of the invention

[0003] To this end, it is necessary to provide a robotic method that can perform smear sampling on the surface of an object, so as to achieve the technical effect of more detailed control of the smearing action.

[0004] To achieve the above purpose, the inventor provides a robot control method for smear sampling, comprising the following steps:

[0005] When the robot performs the first task on the first workbench, the robot enters a visual control mode, the visual control mode comprising the steps of: guiding the action according to the visual image received by the first visual sensor, the first visual sensor being arranged on the surface of the robot;

[0006] When the robot needs to transfer from the first workbench to the second workbench, it enters the global guidance mode, and the global guidance mode includes the steps of: guiding the robot's movements according to the global image information captured by the second visual sensor, the second visual sensor is used to capture the first workbench, the second workbench and the robot, performing real-time analysis on the global image information, extracting feature vectors, and comparing them with expected feature vectors, guiding the movements according to the comparison results, and when the difference between the feature vector of the global image information extracted by real-time analysis and the expected feature vector is less than a preset value, it is determined that the robot has entered a preset position, and switching back to the visual control mode;

[0007] According to the visual image received by the first visual sensor, the robot is guided to perform smear sampling on the second workbench.

[0008] In some embodiments of the present application, when the robot performs smear sampling on the second workbench, force compliance control is performed, and the movement control amount of the force compliance control Δt=Δt1+Δt2, where Δt1 is the feature vector difference Δt between the visual image received by the first visual sensor and the expected image p The control increment, Δt2, is controlled by the difference between the desired contact force and the current real-time contact force Δ F control increment.

[0009] In some embodiments of the present application, the force compliance control further performs a step of constructing a switching matrix S, wherein the switching matrix S is based on Δ F With Δ p The switching matrix S is a 6*6 diagonal matrix, and its six elements correspond to the F of the force signal F collected by the force sensing module. x 、F y 、F z 、m x 、m y 、m z . F x 、F y 、F z is the force component in the x-axis, y-axis, and z-axis directions in the Cartesian coordinate system, m x 、m y 、m z It is the torque value in the x-axis, y-axis, and z-axis directions in the coordinate system.

[0010] In some embodiments of the present application, when the visual control mode is fully adopted in a certain direction, the corresponding element of the switching matrix S is set to 0.

[0011] In some embodiments of the present application, the first task includes: the robot performs one or more of the following tasks: clamping the sampling sample preservation tube, rotating the tube cover, clamping the sampler, placing the sampler into the sampling sample preservation tube, and disinfecting and sealing the sampling sample preservation tube.

[0012] A robot control device for smear sampling comprises a robot, a first visual sensor, a control unit and a second visual sensor; the robot is used to asynchronously perform tasks on a first workbench and a second workbench, the first visual sensor is used to be arranged on the surface of the robot; the second visual sensor is used to record a global image including the first workbench, the second workbench and the robot; the control unit is used to receive images sent back by the first sensor and the second sensor, and is also used to control the robot.

[0013] The control unit is specifically used for the robot to enter a visual control mode when performing a first task on a first workbench, and the visual control mode includes the steps of: guiding an action according to a visual image received by a first visual sensor;

[0014] The control unit is also used to enter a global guidance mode when the robot needs to transfer from the first workbench to the second workbench, and the global guidance mode includes the steps of: guiding the robot to move according to the global image information captured by the second visual sensor, the control unit is used to perform real-time analysis on the global image information, extract feature vectors, and compare them with expected feature vectors, and guide the robot to move according to the comparison results, and when the difference between the feature vector of the global image information extracted by real-time analysis and the expected feature vector is less than a preset value, it is determined that the robot has entered a preset position and switched back to the visual control mode;

[0015] The control unit is also used to guide the robot to perform smear sampling on the second workbench according to the visual image received by the first visual sensor.

[0016] In some embodiments of the present application, the control unit is further used to: when the robot performs smear sampling on the second workbench, perform force compliance control, and the movement control amount of the force compliance control Δt=Δt1+Δt2, where Δt1 is the feature vector difference Δt between the visual image received by the first visual sensor and the expected image p The control increment, Δt2, is controlled by the difference between the desired contact force and the current real-time contact force Δ F control increment.

[0017] In some embodiments of the present application, the force compliance control further performs a step of constructing a switching matrix S, wherein the switching matrix S is based on Δ F With Δ pThe switching matrix S is a 6*6 diagonal matrix, and its six elements correspond to the F of the force signal F collected by the force sensing module. x 、F y 、F z 、m x 、m y 、m z . F x 、F y 、F z is the force component in the x-axis, y-axis, and z-axis directions in the Cartesian coordinate system, m x 、m y 、m z It is the torque value in the x-axis, y-axis, and z-axis directions in the coordinate system.

[0018] In some embodiments of the present application, when the visual control mode is fully adopted in a certain direction, the corresponding element of the switching matrix S is set to 0.

[0019] In some embodiments of the present application, the first task includes: the robot performs one or more of the following tasks: clamping the sampling sample preservation tube, rotating the tube cover, clamping the sampler, placing the sampler into the sampling sample preservation tube, and disinfecting and sealing the sampling sample preservation tube.

[0020] Different from the existing technology, the above technical solution simultaneously judges the platform image through the first visual sensor and the second visual sensor, and after analysis by the control unit, it can make the robot switch between the first platform and the second platform smoother, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of the robot control method for smear sampling according to a specific embodiment of the present invention;

[0022] Figure 2 A flowchart of comparing expected images according to another embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the first task flow described in a specific implementation manner of the present invention;

[0024] Figure 4 It is a schematic diagram of the structure of the device described in a specific embodiment of the present invention;

[0025] Figure 5 This is a module diagram of a robot control device for smear sampling described in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to explain the technical content, structural features, achieved objectives and effects of the technical solution in detail, the following is a detailed description in conjunction with specific embodiments and accompanying drawings.

[0027] In some Figure 1 In the embodiment shown, a robot control method for smear sampling is introduced, comprising the following steps:

[0028] When the S1 robot performs the first task on the first workbench, the visual control mode enters, the visual control mode comprising the steps of: guiding the action according to the visual image received by the first visual sensor, the first visual sensor being arranged on the surface of the robot;

[0029] S2 When the robot needs to transfer from the first workbench to the second workbench, it enters the global guidance mode, and the global guidance mode includes the steps of: guiding the robot's movements according to the global image information captured by the second visual sensor, the second visual sensor is used to capture the first workbench, the second workbench and the robot, performing real-time analysis on the global image information, extracting feature vectors, and comparing them with expected feature vectors, guiding the movements according to the comparison results, and when the difference between the feature vector of the global image information extracted by real-time analysis and the expected feature vector is less than a preset value, it is determined that the robot has entered a preset position and switched back to the visual control mode;

[0030] S3 guides the robot to perform smear sampling on the second workbench according to the visual image received by the first visual sensor.

[0031] Here, the robot can be a mechanical component that is controlled by an automated program and performs mechanical activities by responding to electrical signals. It can be a humanoid, or a simple robotic arm, robotic claw, etc. The first visual sensor can be set on the surface of the robot, and the direction of the visual sensor can be the main working direction of the robot, achieving the effect of eyes on hands. The first visual sensor can be a CMOS, a camera, etc. The robot needs to switch the working state between the first workbench and the second workbench. The first visual sensor on the robot alone cannot meet the input requirements of the switching action. Therefore, a second visual sensor is needed to record the global image of the first workbench, the second workbench and the robot. By comparing and analyzing the global image with the image of the first visual sensor, it is possible to quickly switch between multiple modes of the console. In a specific application example, Figure 2As shown, step S20 can be performed by comparing the picture recorded in the working state when the robot turns to the second workbench as the expected picture, and the feature vector extracted from the expected picture can be used as the feature vector, and then compared with the global image information. When the feature vector difference is less than the threshold, the control unit can determine that the robot has entered the preset station in the second workbench, and then it can switch back to the visual control mode guided by the first visual sensor to work. The existing technology can be used to guide the action through the visual image of the eye on the hand. The technical solution of extracting feature vectors from pictures can also be applied to the analysis algorithm of the existing technology, or the neural network model. Through the above method, the present application achieves the technical effect of controlling the robot to switch between the first workbench and the second workbench, which is safer and has a high fault tolerance rate compared to the existing technology.

[0032] In some embodiments of the present application, the first task includes: the robot performs one or more of the following tasks: gripping the sample storage tube, rotating the tube cover, gripping the sampler, placing the sampler into the sample storage tube, and disinfecting and sealing the sample storage tube. Figure 3 In some specific embodiments shown, the visual control mode can guide the first task, including the following steps:

[0033] S30 Sampling sample storage tube identification and confirmation. The robot end gripper grabs the sampling sample storage tube, scans and identifies the barcode through the image recognition module, compares the sampling sample storage tube information, and confirms that the sampling sample storage tube corresponds to the required collection item.

[0034] S31 sampler dips into the preservation solution. After confirming the sample preservation tube, use the end clamp to unscrew the sample preservation tube cap. Use the visual sensor installed at the end of the robotic arm for visual guidance, clamp the sampler, and insert the sampler into the preservation solution in the sample preservation tube to fully soak it. The sampler image features are collected through the visual sensor. If the sampler dips into too much preservation solution, gently squeeze the sampler against the wall of the sample preservation tube to remove the excess preservation solution.

[0035] S32 sampler smear sampling (completed on the second platform). The end gripper of the robotic arm grabs the sampler and samples the pre-set sampling area according to the set sampling parameters. The sampling process is controlled by the visual control module and the force compliance control module to ensure accurate sampling position and reasonable sampling contact force.

[0036] The S33 sampler is placed in the sample storage tube. After sampling is completed, the end gripper of the robotic arm takes the sampler and places it in the sample storage tube, and breaks the swab along the breaking point of the sampler, and the end of the sampler falls into the sample storage tube. The end gripper tightens the sample storage tube cap.

[0037] S34 The sampling sample storage tube is disinfected and sealed. The end gripper of the robotic arm clamps the sampling sample storage tube to the disinfection device, and the disinfection device sprays disinfectant on the sampling sample storage tube and the end gripper. The disinfected sampling sample storage tube is sealed in a sealed bag.

[0038] The above steps can be combined Figure 4 The schematic diagram of the components of the first and second workbenches and the robot is shown in the figure. After completing the first task, the operator can also mark the outer packaging of the items. The inspected items are manually assisted in packaging and sent to the marking station to mark the outer packaging as sampled. The sampling process is then recorded and archived. The system records the video data collected by the visual sensor during the sampling process, marks the sampled item information, and archives the sampling process data.

[0039] In some embodiments of the present application, the image information of the first visual sensor can also be used to identify the items to be detected. The contents of cold chain items include various types of aquatic products, meat products, fruits and vegetables, etc. Due to different contents and different surface flatness, different nucleic acid sampling parameter settings will be used. The identification of the items to be detected is completed by a visual sensor fixed above the detection platform. After the sensor collects the image of the item to be detected, the image recognition module identifies the information of the item to be detected. The specific item identification method can be obtained by borrowing the existing item recognition model. And the nucleic acid sampling parameters are set according to the specific contents. The correspondence between the item and the corresponding parameter set can be pre-stored. Through the identified information of the item to be detected, the system can call the default sampling parameters, such as: sampler smearing area, sampling times, sampling contact force setting, etc. The sampling parameters can be set and adjusted according to the on-site conditions to ensure that the sampling area is close to the area of ​​the item to be detected, and to ensure that the sampler is in full contact with the item during the sampling process, and the sampler is not broken due to external force.

[0040] In some other embodiments of the present application, in order to better perform motion control, when the robot performs smear sampling on the second workbench, force compliance control is performed, and the movement control amount of the force compliance control Δt=Δt1+Δt2, where Δt1 is the feature vector difference Δt between the visual image received by the first visual sensor and the expected image p The control increment, Δt2, is controlled by the difference between the desired contact force and the current real-time contact force Δ F By designing the above-mentioned force compliance control module, the movement control amount of smear sampling can be made smoother, and the force is not easy to be too large to cause problems such as breaking of the sampling cotton swab.

[0041] In some other further embodiments, the force compliance control further performs a step of constructing a switching matrix S, wherein the switching matrix S is based on Δ F With Δ pThe switching matrix S is a 6*6 diagonal matrix, and its six elements correspond to the F of the force signal F collected by the force sensing module. x 、F y 、F z 、m x 、m y 、m z . F x 、F y 、F z is the force component in the x-axis, y-axis, and z-axis directions in the Cartesian coordinate system, m x 、m y 、m z is the torque value in the x-axis, y-axis, and z-axis directions in the coordinate system. By constructing a switching matrix for force compliance control, the transformation from electronic control to robot motion behavior can be made more intuitive. Furthermore,

[0042] Δt1=(IS)J P Δp

[0043] Δt2=SJ F ΔF

[0044] Where I is the unit diagonal matrix, J p is the parameter matrix mapping image features to robot control parameters, J F is a parameter matrix that maps force parameters to robot control parameters. In some embodiments of the present application, when the visual control mode is fully adopted in a certain direction, the corresponding element of the switching matrix S is set to 0. This means that all the compliant control in a certain direction is replaced by the visual control mode, making the conversion between control modes more convenient and saving computing resources.

[0045] In some Figure 5In the illustrated embodiment, a robot control device 5 for smear sampling is also shown, including a robot 51, a first visual sensor 52, a control unit 53, and a second visual sensor 54; the robot is used to asynchronously perform tasks on a first workbench and a second workbench, and the first visual sensor is used to be arranged on the surface of the robot; the second visual sensor is used to record a global image including the first workbench, the second workbench and the robot; the control unit is used to receive images sent back by the first sensor and the second sensor, and is also used to control the robot. The control unit is specifically used to enter a visual control mode when the robot performs a first task on the first workbench, and the visual control mode includes the steps of: performing dynamic control according to the visual image received by the first visual sensor for guidance; the control unit is also used to enter the global guidance mode when the robot needs to transfer from the first workbench to the second workbench, and the global guidance mode includes the steps of: guiding the robot to perform actions according to the global image information captured by the second visual sensor, the control unit is used to perform real-time analysis on the global image information, extract feature vectors, and compare them with expected feature vectors, and guide actions according to the comparison results, when the difference between the feature vector of the global image information extracted by real-time analysis and the expected feature vector is less than a preset value, it is determined that the robot has entered the preset position and switched back to the visual control mode; the control unit is also used to guide the robot to perform smear sampling on the second workbench according to the visual image received by the first visual sensor.

[0046] Through the above-mentioned device, the present application achieves the technical effect of controlling the robot to switch between the first workbench and the second workbench, which is safer and has a higher fault tolerance rate than the existing technology.

[0047] In some embodiments of the present application, the control unit is further used to: when the robot performs smear sampling on the second workbench, perform force compliance control, and the movement control amount of the force compliance control Δt=Δt1+Δt2, where Δt1 is the feature vector difference Δt between the visual image received by the first visual sensor and the expected image p The control increment, Δt2, is controlled by the difference between the desired contact force and the current real-time contact force Δ F By designing the above-mentioned force compliance control module, the movement control amount of smear sampling can be made smoother, and the force is not easy to be too large to cause problems such as breaking of the sampling cotton swab.

[0048] In some embodiments of the present application, the force compliance control further performs a step of constructing a switching matrix S, wherein the switching matrix S is based on Δ F With Δ p The switching matrix S is a 6*6 diagonal matrix, and its six elements correspond to the F of the force signal F collected by the force sensing module.x 、F y 、F z 、m x 、m y 、m z . F x 、F y 、F z is the force component in the x-axis, y-axis, and z-axis directions in the Cartesian coordinate system, n x 、m y 、m z is the torque value in the x-axis, y-axis, and z-axis directions in the coordinate system. By constructing a switching matrix for force compliance control, the transformation from electronic control to robot motion behavior can be more intuitive.

[0049] Further,

[0050] Δt1=(IS)J P Δp

[0051] Δt2=SJ F ΔF

[0052] Where I is the unit diagonal matrix, J p is the parameter matrix mapping image features to robot control parameters, J F It is the parameter matrix that maps force parameters to robot control parameters.

[0053] In some embodiments of the present application, when the visual control mode is fully adopted in a certain direction, the corresponding element of the switching matrix S is set to 0. This means that the compliant control in a certain direction is completely replaced by the visual control mode, making the conversion between control modes more convenient and saving computing resources.

[0054] In some embodiments of the present application, the first task includes: the robot performs one or more of the following tasks: clamping the sampling sample preservation tube, rotating the tube cover, clamping the sampler, placing the sampler into the sampling sample preservation tube, and disinfecting and sealing the sampling sample preservation tube.

[0055] In some other embodiments, a robot control device 5 for smear sampling may also include an information interaction module, which provides interactive functions such as sampling task setting, sampling parameter setting, sampling work information viewing, and diversified data interfaces. The sampling and recording module uses the video sensing data of the dual visual sensors to grasp the global image information and detailed image information of the robot system performing nucleic acid sampling work, and records the contact force information collected by the force sensor to ensure the effectiveness of each sampling task performed by the robot sampling system. The mobile chassis module realizes the movement and automatic addressing of the first working platform and the mechanical arm it carries, and adapts to sampling tasks at different working positions. The spraying and disinfection module sprays and disinfects the end clamp of the mechanical arm, the matching tooling fixture, the sampling sample storage tube, etc. by spraying disinfectant.

[0056] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "include..." or "comprise..." do not exclude the existence of other elements in the process, method, article or terminal device including the elements. In addition, in this article, "greater than", "less than", "exceed" and the like are understood to exclude the number itself; "above", "below", "within" and the like are understood to include the number itself.

[0057] Those skilled in the art should understand that the above embodiments can be provided as methods, devices, or computer program products. These embodiments can be in the form of complete hardware embodiments, complete software embodiments, or embodiments combining software and hardware. All or part of the steps in the methods involved in the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a storage medium readable by a computer device for executing all or part of the steps described in the above embodiments. The computer device includes, but is not limited to: personal computers, servers, general-purpose computers, special-purpose computers, network devices, embedded devices, programmable devices, smart mobile terminals, smart home devices, wearable smart devices, in-vehicle smart devices, etc.; the storage medium includes, but is not limited to: RAM, ROM, disk, tape, CD, flash memory, U disk, mobile hard disk, memory card, memory stick, network server storage, network cloud storage, etc.

[0058] The above embodiments are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a computer device to generate a machine, so that the instructions executed by the processor of the computer device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program instructions may also be stored in a computer device readable memory capable of directing a computer device to operate in a specific manner, so that the instructions stored in the computer device readable memory produce a manufactured product including an instruction device, the instruction device implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer device so that a series of operating steps are executed on the computer device to produce a computer-implemented process, whereby the instructions executed on the computer device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0061] Although the above embodiments have been described, once those skilled in the art know the basic creative concepts, they can make additional changes and modifications to these embodiments. Therefore, the above description is only an embodiment of the present invention and does not limit the patent protection scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the specification and drawings of the present invention, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A robot control method for smear sampling, characterized in that: The following steps are included: When the robot performs the first task on the first workbench, the robot enters a visual control mode, the visual control mode comprising the steps of: guiding the action according to the visual image received by the first visual sensor, the first visual sensor being arranged on the surface of the robot; When the robot needs to transfer from the first workbench to the second workbench, it enters the global guidance mode, and the global guidance mode includes the steps of: guiding the robot's movements according to the global image information captured by the second visual sensor, the second visual sensor is used to capture the first workbench, the second workbench and the robot, performing real-time analysis on the global image information, extracting feature vectors, and comparing them with expected feature vectors, guiding the movements according to the comparison results, and when the difference between the feature vector of the global image information extracted by real-time analysis and the expected feature vector is less than a preset value, it is determined that the robot has entered a preset position, and switching back to the visual control mode; According to the visual image received by the first visual sensor, the robot is guided to perform smear sampling on the second workbench.

2. The robot control method for smear sampling according to claim 1 is characterized in that: When the robot performs smear sampling on the second workbench, force compliance control is performed, and the movement control amount of the force compliance control Δt=Δt1+Δt2, where Δt1 is the feature vector difference Δt between the visual image received by the first visual sensor and the expected image. p The control increment, Δt2, is controlled by the difference between the desired contact force and the current real-time contact force Δ F control increment.

3. The robot control method for smear sampling according to claim 2 is characterized in that: The force compliance control further performs the steps of constructing a switching matrix S, wherein the switching matrix S is based on Δ F With Δ p The switching matrix S is a 6*6 diagonal matrix, and its six elements correspond to the F of the force signal F collected by the force sensing module. x 、F y 、F z 、m x 、m y 、m z 、F x 、F y 、F z is the force component in the x-axis, y-axis, and z-axis directions in the Cartesian coordinate system, m x 、m y 、m z It is the torque value in the x-axis, y-axis, and z-axis directions in the coordinate system.

4. The robot control method for smear sampling according to claim 3 is characterized in that: When the visual control mode is fully adopted in a certain direction, the corresponding element of the switching matrix S is set to 0.

5. The robot control method for smear sampling according to claim 1 is characterized in that: The first task includes: the robot performs one or more of the tasks of clamping the sampling sample preservation tube, rotating the tube cover, clamping the sampler, placing the sampler into the sampling sample preservation tube, and disinfecting and sealing the sampling sample preservation tube.

6. A robot control device for smear sampling, characterized in that: It includes a robot, a first visual sensor, a control unit, and a second visual sensor; the robot is used to asynchronously perform tasks on a first workbench and a second workbench, the first visual sensor is used to be arranged on the surface of the robot; the second visual sensor is used to record a global image including the first workbench, the second workbench and the robot; the control unit is used to receive images sent back by the first sensor and the second sensor, and is also used to control the robot, The control unit is specifically used for the robot to enter a visual control mode when performing a first task on a first workbench, and the visual control mode includes the steps of: guiding an action according to a visual image received by a first visual sensor; The control unit is also used to enter a global guidance mode when the robot needs to transfer from the first workbench to the second workbench, and the global guidance mode includes the steps of: guiding the robot to move according to the global image information captured by the second visual sensor, the control unit is used to perform real-time analysis on the global image information, extract feature vectors, and compare them with expected feature vectors, and guide the robot to move according to the comparison results, and when the difference between the feature vector of the global image information extracted by real-time analysis and the expected feature vector is less than a preset value, it is determined that the robot has entered a preset position and switched back to the visual control mode; The control unit is also used to guide the robot to perform smear sampling on the second workbench according to the visual image received by the first visual sensor.

7. The robot control device for smear sampling according to claim 6, characterized in that: The control unit is also used to: when the robot performs smear sampling on the second workbench, perform force compliance control, and the movement control amount of the force compliance control Δt=Δt1+Δt2, where Δt1 is the feature vector difference Δt between the visual image received by the first visual sensor and the expected image p The control increment, Δt2, is controlled by the difference between the desired contact force and the current real-time contact force Δ F control increment.

8. The robot control device for smear sampling according to claim 7, characterized in that: The force compliance control further performs the steps of constructing a switching matrix S, wherein the switching matrix S is based on Δ F With Δ p The switching matrix S is a 6*6 diagonal matrix, and its six elements correspond to the F of the force signal F collected by the force sensing module. x 、F y 、F z 、m x 、m y 、m z 、F x 、F y 、F z is the force component in the x-axis, y-axis, and z-axis directions in the Cartesian coordinate system, m x 、m y 、m z It is the torque value in the x-axis, y-axis, and z-axis directions in the coordinate system.

9. The robot control device for smear sampling according to claim 8, characterized in that: When the visual control mode is fully adopted in a certain direction, the corresponding element of the switching matrix S is set to 0.

10. The robot control device for smear sampling according to claim 6, characterized in that: The first task includes: the robot performs one or more of the tasks of clamping the sampling sample preservation tube, rotating the tube cover, clamping the sampler, placing the sampler into the sampling sample preservation tube, and disinfecting and sealing the sampling sample preservation tube.

Images