Method, device and robot for controlling a clamping assembly

Abstract

The present specification provides a control method and device of a clamping assembly and a robot, wherein the method comprises: obtaining a current value of a predetermined variable of the clamping assembly when the clamping assembly clamps a target object, the predetermined variable being a variable associated with a clamping force output by the clamping assembly; determining a target parameter according to an attribute of the current target object; processing the value of the predetermined variable by using the target parameter to obtain a processing result; and adjusting an input control quantity of the clamping assembly according to the processing result, wherein the predetermined variable changes with the input control quantity. According to the present scheme, the parameter of feedback control is determined according to the attribute of the target object, which can improve the convergence speed and accuracy of feedback control, that is, the clamping force quickly approaches the control target value, thereby improving the control efficiency.

Description

Technical Field

[0001] This specification relates to the field of medical device technology, and in particular to control methods, devices and robots for clamping components. Background Technology

[0002] In existing technologies, when gripping components installed on control robot equipment grip a target object, it is generally desirable for the gripping force of the gripping component to quickly reach the control target value of the gripping force. Only when the control target value of the gripping force is reached will the target object not slip relative to the gripping component.

[0003] However, existing gripping components take a long time to reach the gripping force control target value, resulting in a slow robot operation process. Summary of the Invention

[0004] The purpose of this application is to provide a control method, device, and robot for a clamping component, so as to solve the problem that the clamping force of existing clamping components takes a long time to reach the clamping force control target value.

[0005] This specification provides a method for controlling a clamping component, comprising: when the clamping component clamps a target object, acquiring the current value of a predetermined variable of the clamping component, wherein the predetermined variable is a variable associated with the clamping force output by the clamping component; determining a target parameter based on the current attributes of the target object; processing the value of the predetermined variable using the target parameter to obtain a processing result; and adjusting the input control quantity of the clamping component based on the processing result; wherein the predetermined variable changes with the input control quantity.

[0006] In some embodiments, determining target parameters based on the attributes of the current target object includes: acquiring a current image of the clamping component clamping the current target object; identifying the attributes of the current target object from the current image; and inputting the attributes of the current target object into a pre-trained network model to obtain target parameters.

[0007] In some embodiments, the network model is trained by: acquiring a training sample set, the training sample set including multiple training samples, each training sample including a sample image of a sample object held by a clamping component and sample parameters corresponding to the sample image; training the network model by using the sample images of each training sample in the training sample set as input to the network model and the sample parameters of the training samples as output to the network model; wherein the network model includes a first sub-network and a second sub-network, wherein the first sub-network is used to identify the attribute information of the sample object from the sample image, and the second sub-network is used to determine multiple values ​​of the target parameter and the probability corresponding to each value based on the attribute information of the sample object.

[0008] In some embodiments, based on the processing result, when the clamping component clamps the target object, obtaining the current value of a predetermined variable of the clamping component includes: when the clamping component clamps the target object, using a target state observer to predict the current value of the predetermined variable of the clamping component; wherein, the target state observer is constructed using the input control quantity and output quantity of the clamping component as the input of the state observer, and the predetermined variable of the clamping component as the output of the state observer; the predetermined variable includes a mechanical quantity; correspondingly, processing the value of the predetermined variable using target parameters to obtain a processing result includes: substituting the predicted value of the predetermined variable into a pre-constructed objective function to determine the target input control quantity when the number of objects is minimized; the objective function is constructed using the predetermined variable of the clamping component and the input control quantity of the clamping component as variables.

[0009] In some embodiments, predetermined variables of the target clamping component include the clamping force of the target clamping component.

[0010] In some embodiments, when the clamping component clamps the target object, a target state observer is used to predict the current value of a predetermined variable of the clamping component, including: when the clamping component clamps the target object, a first target state observer is used to predict the first output torque of the first driven wheel that drives the first clamping piece to move; wherein the clamping component includes a first clamping piece and a second clamping piece, and the first clamping piece and the second clamping piece are connected by a rotating shaft; a second target state observer is used to predict the second output torque of the second driven wheel that drives the second clamping piece to move; and the clamping force of the clamping component is determined based on the minimum value of the first output torque and the second output torque.

[0011] In some embodiments, predetermined variables of the target clamping assembly include: tension in the thread connecting the driving wheel and the driven wheel; wherein, when the driven wheel rotates, it drives the clamping plates of the clamping assembly to move.

[0012] In some embodiments, the tension on the wire is obtained by measuring the voltage between two surfaces of a piezoelectric material layer disposed in the first wire and the cross-sectional area of ​​the piezoelectric material layer; calculating the charge on one surface of the piezoelectric material layer based on the voltage and the cross-sectional area; and calculating the tension on the first wire based on the charge on the one surface and the piezoelectric effect coefficient.

[0013] In some embodiments, predetermined variables of the clamping component include: the static friction force when the clamping component clamps the target object.

[0014] In some embodiments, the static friction force is obtained by: determining the angle between the extension direction of the clamping component and the horizontal direction from an image of the clamping component clamping the target object; the horizontal direction being a direction perpendicular to the direction of gravity; determining the weight of the clamped portion of the target object; determining the static friction force between the clamping component and the target object based on the weight of the clamped portion of the target object and the angle between the extension direction of the clamping component and the horizontal direction, and using the static friction force as a predetermined variable of the clamping component.

[0015] In some embodiments, before substituting the values ​​of the state variables of the target clamping component into the objective function to determine the target input control quantity when the objective function value is minimized, the method further includes: real-time detection of whether the clamping component is performing a clamping action; when a clamping action is detected, determining the clamping state of the clamping component on the target object; the clamping state is determined based on the coverage of the target object on the clamping surface of the clamping component; if a predetermined clamping state is reached, obtaining the current value of a predetermined variable of the clamping component, the predetermined variable being a variable associated with the clamping force output by the clamping component; otherwise, presenting a prompt message to the operator, the prompt message being used to remind the operator to control the action of the clamping component to adjust the clamping state of the clamping component on the target object.

[0016] A second aspect of this specification provides a control device for a clamping assembly, comprising: an acquisition unit, configured to acquire the current value of a predetermined variable of the clamping assembly when the clamping assembly clamps a target object, the predetermined variable being a variable associated with the clamping force output by the clamping assembly; a first determination unit, configured to determine target parameters based on the attributes of the current target object; a processing unit, configured to process the value of the predetermined variable using the target parameters to obtain a processing result; and an adjustment unit, configured to adjust the input control quantity of the clamping assembly based on the processing result; wherein the predetermined variable changes with the change of the input control quantity.

[0017] In some embodiments, the first determining unit includes: an acquisition subunit, configured to acquire a current image of the clamping component clamping the current target object; an identification subunit, configured to identify the attributes of the current target object from the current image; and a first processing subunit, configured to input the attributes of the current target object into a pre-trained network model to obtain target parameters.

[0018] In some embodiments, the network model is trained by: acquiring a training sample set, the training sample set including multiple training samples, each training sample including a sample image of a sample object held by a clamping component and sample parameters corresponding to the sample image; training the network model by using the sample images of each training sample in the training sample set as input to the network model and the sample parameters of the training samples as output to the network model; wherein the network model includes a first sub-network and a second sub-network, wherein the first sub-network is used to identify the attribute information of the sample object from the sample image, and the second sub-network is used to determine multiple values ​​of the target parameter and the probability corresponding to each value based on the attribute information of the sample object.

[0019] In some embodiments, the acquisition unit includes: a first prediction subunit, configured to predict the current value of a predetermined variable of the clamping component when the clamping component clamps the target object using a target state observer; wherein the target state observer is constructed using the input control quantity and output quantity of the clamping component as the input of the state observer and the predetermined variable of the clamping component as the output of the state observer; the predetermined variable includes a mechanical quantity; correspondingly, the processing unit includes: a second processing subunit, configured to substitute the predicted value of the predetermined variable into a pre-constructed objective function to determine the target input control quantity when the number of objects is minimized; the objective function is constructed using the predetermined variable of the clamping component and the input control quantity of the clamping component as variables.

[0020] In some embodiments, predetermined variables of the target clamping component include the clamping force of the target clamping component.

[0021] In some embodiments, the first prediction subunit includes: a second prediction subunit, configured to predict, using a first target state observer, a first output torque of a first driven wheel that drives the first clamping plate when the clamping assembly clamps the target object; wherein the clamping assembly includes a first clamping plate and a second clamping plate, the first clamping plate and the second clamping plate being connected by a rotating shaft; a third prediction subunit, configured to predict, using a second target state observer, a second output torque of a second driven wheel that drives the second clamping plate; and a determination subunit, configured to determine the clamping force of the clamping assembly based on the minimum value of the first output torque and the second output torque.

[0022] In some embodiments, predetermined variables of the target clamping assembly include: tension in the thread connecting the driving wheel and the driven wheel; wherein, when the driven wheel rotates, it drives the clamping plates of the clamping assembly to move.

[0023] In some embodiments, the tension on the wire is obtained by measuring the voltage between two surfaces of a piezoelectric material layer disposed in the first wire and the cross-sectional area of ​​the piezoelectric material layer; calculating the charge on one surface of the piezoelectric material layer based on the voltage and the cross-sectional area; and calculating the tension on the first wire based on the charge on the one surface and the piezoelectric effect coefficient.

[0024] In some embodiments, predetermined variables of the clamping component include: the static friction force when the clamping component clamps the target object.

[0025] In some embodiments, the static friction force is obtained by: determining the angle between the extension direction of the clamping component and the horizontal direction from an image of the clamping component clamping the target object; the horizontal direction being a direction perpendicular to the direction of gravity; determining the weight of the clamped portion of the target object; determining the static friction force between the clamping component and the target object based on the weight of the clamped portion of the target object and the angle between the extension direction of the clamping component and the horizontal direction, and using the static friction force as a predetermined variable of the clamping component.

[0026] In some embodiments, the method further includes: a detection unit, configured to detect in real time whether the clamping component is performing a clamping action; a second determination unit, configured to determine the clamping state of the clamping component on the target object when a clamping action is detected; the clamping state is determined based on the coverage of the target object on the clamping surface of the clamping component; and, in the case of reaching a predetermined clamping state, to obtain the current value of a predetermined variable of the clamping component, the predetermined variable being a variable associated with the clamping force output by the clamping component; and a prompting unit, configured to present a prompting message to the operator if the predetermined clamping state is not reached, the prompting message being used to remind the operator to control the action of the clamping component to adjust the clamping state of the clamping component on the target object.

[0027] This specification provides a robot in a third aspect, comprising: a base; a first robotic arm disposed on the base; a gripping assembly disposed at the end of the first robotic arm; an adjustment assembly disposed on the gripping assembly for adjusting the gripping force of the gripping assembly; and a controller for acquiring, when the gripping assembly grips a target object, the current value of a predetermined variable of the gripping assembly, the predetermined variable being a variable associated with the gripping force output by the gripping assembly; determining target parameters based on the attributes of the current target object; processing the value of the predetermined variable using the target parameters to obtain a processing result; and adjusting the input control quantity of the gripping assembly based on the processing result; wherein the predetermined variable changes with the change of the input control quantity.

[0028] A fourth aspect of this specification provides a controller comprising: a memory and a processor, the processor and the memory being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to implement the steps of the method described in any of the first aspects.

[0029] A fifth aspect of this specification provides a computer storage medium storing computer program instructions that, when executed, implement the steps of the method described in any of the first aspects.

[0030] The control method, device, and robot for the clamping component provided in this specification process the clamping-related variables of the output of the clamping component using parameters, and controls the clamping component based on the processing results. In other words, a feedback control method is used to control the clamping force of the clamping component. The parameters of the feedback control are determined according to the attributes of the target object, which can improve the convergence speed and accuracy of the feedback control (that is, make the clamping force quickly approach the control target value) and improve the control efficiency. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0032] Figure 1 A schematic diagram of the surgical robot system is shown;

[0033] Figure 2 A schematic diagram of the control terminal device in the surgical robot system is shown.

[0034] Figure 3 A schematic diagram of the image terminal device in the surgical robot system is shown;

[0035] Figure 4 A schematic diagram of the execution end device in the surgical robot system is shown;

[0036] Figure 5 A schematic diagram of the clamping assembly is shown;

[0037] Figure 6 A schematic diagram of a scenario in which the clamping component manipulates a target object is shown;

[0038] Figure 7 A schematic diagram showing the degrees of freedom for the pose changes of the clamping assembly is provided.

[0039] Figure 8A schematic diagram of the wire drive model of one clamping piece of the clamping assembly is shown;

[0040] Figure 9 A flowchart of a control method for a clamping assembly provided in this specification is shown;

[0041] Figure 10 A schematic diagram of the feedback control of the clamping assembly is shown;

[0042] Figure 11 A flowchart is shown for another control method of the clamping component provided in this specification;

[0043] Figure 12 A schematic diagram of the feedback control principle of the clamping component control system is shown.

[0044] Figure 13 A schematic diagram of the improved filament structure is shown;

[0045] Figure 14 A schematic diagram illustrating the force analysis when the clamping component picks up the target object is shown;

[0046] Figure 15 A schematic block diagram of the control device for the clamping assembly provided in this specification is shown.

[0047] Figure 16 A schematic block diagram of the controller provided in this specification is shown. Detailed Implementation

[0048] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0049] Determining the target clamping force and quickly achieving it are crucial aspects of clamping component control method research. Existing methods primarily focus on determining this target value. For instance, when the target object is biological tissue, there exists a safety parameter threshold for each type of tissue to prevent severe clamping damage. Current methods mainly focus on studying this safety parameter threshold and determining the target clamping force value based on it. This ensures that when clamping tissue using this target clamping force value, the tissue is held in place without slipping, and without causing damage to the target object.

[0050] Existing technologies typically employ existing feedback control algorithms to quickly achieve the target clamping force value, manually adjusting various parameters to optimize control. This specification addresses this issue by providing a control method for clamping components that reduces the time required to reach the target value, enabling rapid response control.

[0051] The following uses a surgical robot system as an example to illustrate the control method of the clamping components provided in this manual.

[0052] It should be noted that the term "surgery" in this instruction manual includes not only medical procedures such as cutting and suturing of the patient's body using medical instruments, but also procedures such as cutting, clamping, or puncturing to remove diseased tissue from the patient's body for pathological examination (i.e., biopsy). In other words, the term "surgery" in this instruction manual refers to the means of treating the patient's body as needed for diagnosis and treatment.

[0053] Surgical robotic systems are systems that perform complex surgical procedures in a minimally invasive manner. For example... Figure 1 As shown, a surgical robot system typically consists of a control unit 100, an execution unit 200, and an imaging unit 300. The control unit 100, usually called the doctor's console, is located outside the sterile area of ​​the operating room and is used to send control commands to the execution unit 200. The execution unit 200, i.e., the surgical robot device (referred to as the surgical robot in this specification), is used to control the surgical instruments mounted on the end of its robotic arms to perform specific surgical operations on the patient according to the control commands. An endoscope can also be mounted on the surgical robot. The imaging unit 300, usually called an imaging cart, is used to process the information acquired by the endoscope to form a three-dimensional high-definition image and feed it back to the control unit 100, etc.

[0054] like Figure 2 As shown, the control unit 100, i.e., the doctor's console, is equipped with a main operator hand, an imaging device, and a main controller. The main operator hand detects the surgeon's hand movements, serving as the control signal for the entire surgical robot system. The imaging device provides the surgeon with three-dimensional images of the patient's body detected by the endoscope, providing reliable image information for the surgeon's surgical operations. During surgery, the surgeon sits at the doctor's console and controls the surgical robot and endoscope through the main operator hand. Based on the three-dimensional images of the cavity transmitted back by the imaging device, the surgeon uses hand movements to control the movement of the robotic arm mechanism and surgical instruments on the surgical robot to complete various operations, thereby achieving the goal of performing surgery on the patient. The main controller is the core control element of the surgical robot system, used to control various operations and functions of the surgical robot system.

[0055] like Figure 3As shown, the image terminal device 300 mainly includes an endoscope (not shown in the figure), an endoscope processor, and a display device. The endoscope includes a tube inserted into the patient's body, an observation lens and an illumination lens at the front end of the tube, an optical fiber, and an eyepiece, used to illuminate the inside of the cavity and acquire a stereoscopic image of the cavity. The endoscope processor is used to process the acquired stereoscopic image of the cavity, and the display device is used to display the processed image in real time.

[0056] like Figure 4 As shown, the execution device 200, i.e., the surgical robot device, includes a base 210 and a robotic arm mechanism 220. Located in the sterile area of ​​the operating room, the surgical robot device's main function is to carry surgical instruments mounted on its robotic arm end to perform specific surgical procedures on the patient according to control commands given by the surgeon, and to carry an endoscope. Within the sterile area, assistant surgeons are usually also present to change the surgical instruments mounted on the surgical robot and assist the surgeon in completing the operation. To ensure patient safety, assistant surgeons typically have higher priority in controlling the surgical robot.

[0057] like Figure 4 and Figure 5 As shown, gripping component A is a component installed at the end of the robotic arm mechanism, which can be used to grip tissue to assist in operations such as cutting and slicing. Figure 5 As shown, the clamping assembly includes a first clamping piece A1, a second clamping piece A2, and a second rotating shaft O2, with the first clamping piece A1 and the second clamping piece A2 fixed on the second rotating shaft O2.

[0058] In some embodiments, a micro motor may be provided inside the clamping assembly. Under the action of a control signal, the micro motor drives the first clamping piece A1 and the second clamping piece A2 to rotate along the second rotating shaft O2, so as to adjust the clamping force of the clamping assembly on the tissue.

[0059] In some embodiments, the first clamping plate A1 and the second clamping plate A2 of the clamping assembly operate within a narrow cavity. Therefore, the clamping assembly requires a very small size, making it unsuitable to house a micromotor within it. In this case, the motor can be positioned outside the narrow cavity, with a drive wheel located at the motor, and driven wheels located at the first clamping plate A1 and the second clamping plate A2 inside the narrow cavity. Figure 6 The transmission wire (i.e., the thread) inside the slender pipe shown transmits the torque output by the motor to the driven wheel, driving its rotation. The rotation of the driven wheel controls the positional changes of the clamping assembly. Figure 6 In the diagram, M represents the clamping component, T represents the image acquisition component, and X represents the target object.

[0060] Figure 7A schematic diagram of the degrees of freedom for the pose changes of the clamping assembly is shown, where the degrees of freedom include: rotation, pitch, yaw, and grip. Figure 8 A schematic diagram of the wire drive model of a clamping piece of the clamping assembly is shown. In this diagram, the circle containing W1 represents the driving wheel, which represents the output torque of the driving wheel, i.e., the input torque of the clamping assembly control system; the circle containing W2 represents the driven wheel, which represents the output torque of the driven wheel, i.e., the output torque of the clamping assembly control system; the remaining circles represent steering wheels; A1 represents a clamping piece of the clamping assembly; the component within the dashed box containing XOY can be located at the connection between the clamping assembly and the end of the robotic arm; the component within the dashed box containing YOZ can be located inside the aforementioned slender pipe; and the component within the dashed box containing XOZ can be located at the end of the clamping assembly.

[0061] In some embodiments, the clamping assembly may have more than three clamping pieces, and the control method for the clamping assembly provided in this specification is also applicable to clamping assemblies with more than three clamping pieces. In this specification, only a clamping assembly consisting of two clamping pieces is used as an example to illustrate the control method for the clamping assembly provided in this specification.

[0062] like Figure 9 and Figure 10 As shown, the control method for the clamping assembly provided in this specification includes the following steps:

[0063] S110: When the clamping component is clamping the target object, obtain the current value of a predetermined variable of the clamping component, which is a variable associated with the clamping force output by the clamping component.

[0064] Predetermined variables can be, for example, the clamping force itself, the static friction when clamping the target object, or the torque output by the motor that controls the position and orientation of the clamping plates on the clamping assembly. In other words, predetermined variables are variables that can reflect the magnitude of the clamping force.

[0065] S120: Determine the target parameters based on the attributes of the current target object.

[0066] The attributes of the current target object can refer to categories, sizes, thicknesses, hardness, elasticity, etc., that characterize the structural features of the target object.

[0067] In some embodiments, S120 may be: acquiring a current image of the clamping component clamping the current target object; identifying the attributes of the current target object from the current image; and inputting the attributes of the current target object into a pre-trained network model to obtain target parameters.

[0068] The network model can be trained as follows: A training sample set is obtained, comprising multiple training samples. Each training sample includes a sample image of a sample object held by a clamping component and corresponding sample parameters. The network model is trained by using the sample images from each training sample in the training sample set as input and the sample parameters as output. The network model includes a first sub-network and a second sub-network. The first sub-network is used to identify the attribute information of the sample object from the sample image, and the second sub-network is used to determine multiple values ​​of the target parameter and the probability corresponding to each value based on the attribute information of the sample object.

[0069] Image recognition systems can be used to identify image attributes. These systems generally consist of two processes: image processing and image recognition. Image processing includes preprocessing and image segmentation, while image recognition includes feature extraction and image classification. Preprocessing addresses the noise introduced during image acquisition, conversion, and transmission. To improve recognition accuracy, noise reduction is performed before image processing, such as using two-dimensional wavelet filtering. Other steps include smoothing, binarization, and amplitude normalization. Image segmentation divides the image into sets of connected regions that satisfy certain similarity criteria or possess homogeneous characteristics, based on features such as grayscale, texture, and edges, thus creating conditions for further image recognition. Feature extraction involves extracting and selecting image features in pattern recognition. Common feature detection methods include Harris corner detection, SIFT feature detection, FAST feature detection, and SURF feature detection. Image classification involves designing an image classifier and making classification decisions to perform pattern matching and output recognition results. The method based on artificial neural networks has the advantages of allowing samples to have large defects and distortions, continuously improving the model during the process, having autonomous learning capabilities, fast running speed, good adaptive performance, and high resolution, and is suitable for image recognition in the narrow and complex environment of the abdominal cavity.

[0070] In some embodiments, the target parameter value corresponding to the maximum probability output by the second sub-network can be directly determined as the output value of the network model; while in other embodiments, the probabilities corresponding to each value output by the second sub-network can be used as weights, and the values ​​can be weighted and summed, with the summation result used as the output of the network model.

[0071] The target parameter in S120 can be a single parameter or a parameter matrix containing multiple sub-parameters. When the target parameter includes multiple sub-parameters, each sub-parameter is obtained according to the above method for obtaining the target parameter.

[0072] In some embodiments, the attributes of the current target object can also be input by a person based on the current image. In some embodiments, there can also be a one-to-one correspondence between the attributes of the current target object and the target parameters, so the corresponding target parameters can be obtained after obtaining the attributes of the current target object.

[0073] S130: The values ​​of the predetermined variables are processed using the target parameters to obtain the processing results.

[0074] The term "processing" here is determined based on the control algorithm used. For example, the processing performed using a PID control algorithm is different from that performed using an LQR control algorithm.

[0075] S140: Based on the processing result, adjust the control amount of the clamping component, wherein a predetermined variable changes with the change of the control amount.

[0076] The control quantities of the clamping component can be, for example, the control current and input torque of the motor that controls the position and orientation of the clamping plates on the clamping component. Of course, the structure of robot equipment and robot system is more complex, and there will be other control quantities that affect the clamping force of the clamping component, which will not be listed in this manual.

[0077] The control method for the clamping component provided in this specification processes the clamping-related variables of the output of the clamping component using parameters, and controls the clamping component based on the processing results. In other words, a feedback control method is used to control the clamping force of the clamping component. The parameters of the feedback control are determined according to the attributes of the target object, which can improve the convergence speed and accuracy of the feedback control (that is, make the clamping force quickly approach the control target value) and improve control efficiency.

[0078] In some embodiments, the feedback control algorithm can employ either a PID (proportional-integral-derivative) control algorithm or an LQR (linear quadratic regulator) control algorithm. For example... Figure 11 As shown, the control method for the clamping component may further include the following steps:

[0079] S210: When the clamping component clamps the target object, the target state observer is used to predict the current value of the predetermined variable of the clamping component.

[0080] The target state observer is constructed using the input control quantities and output quantities of the clamping component as the input of the state observer, and the predetermined variables of the clamping component as the output of the state observer.

[0081] Input control quantity refers to the control quantity input to the clamping component to control the movement of the clamping component. For example, the input control quantity can be... Figure 8 The output torque of the drive wheel.

[0082] Each of the input control quantities, output quantities, and predetermined variables mentioned in this specification can be a matrix composed of multiple variables. Furthermore, the predetermined variables of the clamping assembly can include mechanical quantities, such as the clamping force (i.e., compressive force) of the clamping components on the tissue, and the static friction force between the clamping components and the tissue.

[0083] The subsystem comprising the various components used for controlling the clamping assembly can be called the clamping assembly control system. For example, Figure 8 The output torque of the drive wheel shown can be used as the input to the clamping component control system, and the clamping force (i.e., squeezing force) of the clamping component on the target object can be used as the output of the clamping component control system.

[0084] Based on modern control theory, the clamping component control system can be described by the following state-space expression:

[0085]

[0086] y=Cx+Du——(2)

[0087] In this equation, (1) is the state equation, (2) is the output equation, x represents the state variable matrix of the clamping component control system, A is the state coefficient matrix, B is the control coefficient matrix, C is the output coefficient matrix, and D is the direct transfer matrix or feedforward coefficient matrix. For a given control system, the above matrices A, B, C, and D can be determined. Therefore, the clamping component control system can adopt... Figure 12 The diagram shown is used to represent this.

[0088] Feedback control can improve the accuracy of the controlled target quantity and is a commonly used control method in control systems. However, this control method requires feeding the output of the control system back to the front end. But for the aforementioned clamping component control system, many predetermined variables (such as clamping force) are unobservable, that is, these predetermined variables are unobservable variables. The so-called "unobservable variables" refer to variables whose values ​​cannot be measured (for example, the clamping force of the clamping component on the target object cannot be measured because no force sensor is installed on the clamping plate of the clamping component), or variables whose measurement cost is high (for example, due to the limitation of the clamping component's small working space, the cost of installing a force sensor on the clamping plate of the clamping component is high).

[0089] Because the predetermined variable is not observable, existing technologies generally do not consider using force feedback control systems in clamping assembly control systems. To address this issue, this specification incorporates a state observer into the existing open-loop clamping assembly control system, such as... Figure 12 As shown, the input control quantity and output quantity of the clamping component control system are used as the input of the state observer, and the predetermined variable of the clamping component control system is used as the output of the state observer. Here, the input control quantity and output quantity of the clamping component control system are also the input control quantity and output quantity of the clamping component; the predetermined variable of the clamping component control system is also the predetermined variable of the clamping component.

[0090] A state observer can predict the values ​​of unobservable predetermined variables (such as clamping force) of a clamping component, given that the input control and output quantities of the clamping component are already determined. The input control quantity is typically calculated from measured parameters. For example, the input control quantity can be the input torque, which can be determined based on the drive... Figure 8 The output can be calculated from measurable parameters such as the current of the motor driving the central drive wheel and the motor's driving efficiency. The output can be calculated from the output equation of the clamping component control system (i.e., equation (2) above).

[0091] S220: Determine the target parameters based on the attributes of the current target object.

[0092] Please refer to step S120 for this step, which will not be repeated here.

[0093] S230: Substitute the predicted values ​​of the predetermined variables into the pre-constructed objective function to determine the target input control quantity when the number of objects is minimized; the objective function is constructed using the predetermined variables of the clamping component and the input control quantity of the clamping component as variables.

[0094] In some embodiments, the objective function is: Where J represents the value of the objective function, x is the predetermined variable matrix of the clamping component, u is the input control matrix of the clamping component, k represents time, and Q and R are coefficient matrices.

[0095] Q and R can be diagonal matrices, where the elements correspond to the weights of different predetermined variables and input control quantities. A larger weight indicates greater importance placed on the corresponding predetermined variable or input control quantity, and a greater desire to maintain a smaller value for that variable during changes. Theoretically, there exists an optimal combination of weights for different predetermined variables and input control quantities that results in the fastest convergence. This specification focuses on "how to determine the weight values" to provide a clamping component control method that enables rapid convergence.

[0096] Since the objective function is constructed using the predetermined variables of the clamping component and the input control quantity of the clamping component as variables, after replacing the predetermined variables of the clamping component with the predicted values ​​of the state observer, the only variable in the objective function is the input control quantity, thus making it easy to find the minimum value of the objective function.

[0097] The input control quantity of the objective function minimizes the value of the objective function, which means that the closer the predetermined variable of the clamping component is to the control target value, the closer the output quantity is to the control target value, thereby improving the control accuracy of the clamping component.

[0098] In some embodiments, the objective function can also be constructed based on the PID control method. For example, the theoretical state value is calculated based on the input control quantity of the clamping component, and the square of the difference between the theoretical state value and the observed state value (i.e., the state value predicted by the state observer) is used as the objective function.

[0099] S240: Adjust the input control amount of the clamping component according to the target input control amount.

[0100] The structures of robotic devices and gripping components are often quite complex, making it difficult to apply sophisticated control algorithms in the gripping component control system. The most challenging aspect is modeling the gripping component control system and establishing the relationships between input control variables and predetermined variables.

[0101] In some embodiments, predetermined variables that can be defined for the clamping component include the clamping force of the clamping component.

[0102] In some embodiments, sensors or sensor arrays may be provided on the clamping surface of the clamping assembly to collect clamping force through the sensors.

[0103] However, considering the structural complexity of installing sensors, as well as issues related to sensor sensitivity detection and replacement, it may be impossible to install sensors on the surface of the clamping plates of the clamping assembly. Therefore, a first target state observer can be used to predict the first output torque of the first driven wheel that moves the first clamping plate, and a second target state observer can be used to predict the second output torque of the second driven wheel that moves the second clamping plate. The clamping force of the clamping assembly is determined based on the minimum value between the first and second output torques. The clamping assembly includes a first clamping plate and a second clamping plate, which are connected by a rotating shaft.

[0104] Figure 8 A wire drive model with a clamp is shown, such as Figure 5 As shown, the clamping assembly consists of at least two clamping plates. According to mechanical principles, the clamping force on the target object should be determined by the minimum clamping force applied by each clamping plate. Therefore, the expression for the clamping force can be:

[0105] in, This represents the predicted value of the clamping force. For the first output torque, For the second output torque, r g r is the length of the clip. g / 2 represents the equivalent moment.

[0106] exist Figure 8 In the wire drive model shown, the work done by the elastic deformation of the transmission wire (i.e., the thread) is neglected, and the frictional energy loss f of the wire drive system is considered. r Input torque τ m With output torque τ j Can be derived from τ j =f(τ) m ,f r τ is used to represent this. m yes Figure 8 The output torque of the driving wheel in the wire drive model shown can be calculated based on the control current of the motor, τ. j It can be predicted using a state observer, where τ j As the output of the state observer, τ m This serves as an input to the state observer. In this embodiment, the predetermined variable is the output torque of the driven wheel, and the input control quantity is the control current of the driving wheel. The state observer can be a Luenberger observer, a Kalman filter observer, or similar device.

[0107] In some embodiments, predetermined variables of the target clamping assembly include: tension on the wire connecting the driving wheel and the driven wheel; and rotation of the driven wheel causing the clamping plates of the clamping assembly to move.

[0108] For example, Figure 8 The tension in the thread between the driving wheel W1 and the driven wheel W2 can be used as a predetermined variable.

[0109] In some embodiments, the method for obtaining the tension on the wire can be: setting a tension gauge on the wire and collecting the measurement value of the tension gauge.

[0110] In some embodiments, the following can be adopted: Figure 13 The method shown improves the structure of the yarn, and based on the improved yarn structure, the tension on the yarn is determined.

[0111] Figure 13 A schematic cross-sectional view of the wire is shown, wherein the area indicated by 1 represents the first material layer, the area indicated by 2 represents the second material layer, and the area indicated by 3 represents the piezoelectric material layer. The first and second material layers can be material layers of the wire in the prior art. Figure 13The difference between the structure shown and the prior art is that a piezoelectric material layer is added to the wire material. Figure 13 This is merely a schematic diagram showing the newly added piezoelectric material layer. In actual products, the cross-sectional shapes of the first and second material layers can also be other shapes. Of course, it can also include only one of the first and second material layers, or include more material layers. This specification does not specifically limit the cross-sectional shape of the wire.

[0112] based on Figure 13 The tension in the piezoelectric material layer in the wire shown can be determined by the following method: measuring the voltage between two surfaces of the piezoelectric material layer disposed in the first wire and the cross-sectional area of ​​the piezoelectric material layer; calculating the charge on one surface of the piezoelectric material layer based on the voltage and cross-sectional area; and calculating the tension in the first wire based on the charge on one surface and the piezoelectric effect coefficient.

[0113] In other words, by utilizing the positive piezoelectric effect of the piezoelectric material layer, the elastic deformation of the material is converted into an electrical signal. Charge is generated on the two plates in the direction of force, so the piezoelectric material is equivalent to a capacitor, and the amount of charge can be obtained by measuring the voltage. Among them, U a ε is the voltage across the piezoelectric material, which can be measured using an amplifier circuit; q is the charge on the piezoelectric material's plates; A is the cross-sectional area of ​​the piezoelectric material; and ε is the voltage across the piezoelectric material. r Let ε0 be the relative permittivity of the piezoelectric material, and ε0 be the vacuum permittivity. Then, by using the relationship between charge and force, the tension in the wire can be determined. Where F is the tension in the wire, q is the charge on the piezoelectric electrode, and d 33 This is the piezoelectric effect coefficient.

[0114] In some embodiments, predetermined variables of the clamping component include: the static friction force when the clamping component clamps the target object.

[0115] Figure 14 The diagram illustrates the force analysis when the clamping component picks up the target object, from which the following expression can be obtained: f inst sin(α)+F h sin(θ) = mg, f inst cos(α)+F h cos(θ)=0, where, f inst For static friction, F h Let F be the pulling force exerted by the clamping component on the target object, m be the mass of the clamped portion of the target object, and g be the acceleration due to gravity. When the clamping component is stationary and clamping the target object, the pulling force F is... h The direction of static friction f inst The direction is perpendicular; when the clamping component clamps the tissue, the tension F hThe direction of the static friction is consistent with the direction of motion. Assuming the angles θ and α, and the mass m of the part of the target object being clamped, are known, then the static friction force...

[0116] Therefore, static friction can be obtained by the following method: determining the angle between the extension direction of the clamping component and the horizontal direction from the image of the clamping component holding the target object; the horizontal direction is the direction perpendicular to the direction of gravity; determining the weight of the clamped part of the target object; and determining the static friction between the clamping component and the target object based on the weight of the clamped part of the target object and the angle between the extension direction of the clamping component and the horizontal direction.

[0117] In some embodiments, Figure 9 or Figure 11 Before the method shown is executed, it can also detect in real time whether the clamping component is performing a clamping action; when a clamping action is detected, the clamping state of the clamping component on the target object is determined; if the predetermined clamping state is reached, the method is executed. Figure 9 or Figure 11 The method shown involves presenting a prompt message to the operator if the target object is not reached. This prompt message serves to remind the operator to control the clamping component's movement to adjust the clamping state of the clamping component on the target object.

[0118] The detection of whether the clamping component is performing clamping can be performed by detecting the image acquired by the image acquisition component; or by collecting and detecting whether the clamping component is performing clamping action by pressure sensors set on the clamping surface of the clamping component. When the pressure sensors on the clamping surface are deployed in an array, the clamping state of the clamping component on the target object can also be determined based on the collected values ​​of the pressure sensors in the array.

[0119] The clamping state of a clamping component relative to a target object can refer to the coverage of the target object on the clamping surface of the clamping component. That is, the ratio of the contact area between the target object and the clamping surface to the total area of ​​the clamping surface. Of course, the clamping state can also be obtained by further classifying the coverage rate; for example, a coverage rate greater than 90% indicates complete clamping, while a coverage rate less than 50% indicates incomplete clamping.

[0120] This specification provides a control device for a clamping assembly, which can be used to achieve... Figure 9 or Figure 11 The method shown. (As illustrated) Figure 15 As shown, the device includes an acquisition unit 10, a first determination unit 20, a processing unit 30, and an adjustment unit 40.

[0121] The acquisition unit 10 is used to acquire the current value of a predetermined variable of the clamping component when the clamping component clamps the target object. The predetermined variable is a variable associated with the clamping force output by the clamping component.

[0122] The first determining unit 20 is used to determine the target parameters based on the attributes of the current target object.

[0123] The processing unit 30 is used to process the value of the predetermined variable using the target parameter to obtain the processing result.

[0124] The adjustment unit 40 is used to adjust the input control amount of the clamping assembly according to the processing result; wherein the predetermined variable changes with the change of the input control amount.

[0125] In some embodiments, the first determining unit includes: an acquisition subunit, configured to acquire a current image of the clamping component clamping the current target object; an identification subunit, configured to identify the attributes of the current target object from the current image; and a first processing subunit, configured to input the attributes of the current target object into a pre-trained network model to obtain target parameters.

[0126] In some embodiments, the network model is trained by: acquiring a training sample set, the training sample set including multiple training samples, each training sample including a sample image of a sample object held by a clamping component and sample parameters corresponding to the sample image; training the network model by using the sample images of each training sample in the training sample set as input to the network model and the sample parameters of the training samples as output to the network model; wherein the network model includes a first sub-network and a second sub-network, wherein the first sub-network is used to identify the attribute information of the sample object from the sample image, and the second sub-network is used to determine multiple values ​​of the target parameter and the probability corresponding to each value based on the attribute information of the sample object.

[0127] In some embodiments, the acquisition unit includes: a first prediction subunit, configured to predict the current value of a predetermined variable of the clamping component when the clamping component clamps the target object using a target state observer; wherein the target state observer is constructed using the input control quantity and output quantity of the clamping component as the input of the state observer and the predetermined variable of the clamping component as the output of the state observer; the predetermined variable includes a mechanical quantity; correspondingly, the processing unit includes: a second processing subunit, configured to substitute the predicted value of the predetermined variable into a pre-constructed objective function to determine the target input control quantity when the number of objects is minimized; the objective function is constructed using the predetermined variable of the clamping component and the input control quantity of the clamping component as variables.

[0128] In some embodiments, predetermined variables of the target clamping component include the clamping force of the target clamping component.

[0129] In some embodiments, the first prediction subunit includes: a second prediction subunit, configured to predict, using a first target state observer, a first output torque of a first driven wheel that drives the first clamping plate when the clamping assembly clamps the target object; wherein the clamping assembly includes a first clamping plate and a second clamping plate, the first clamping plate and the second clamping plate being connected by a rotating shaft; a third prediction subunit, configured to predict, using a second target state observer, a second output torque of a second driven wheel that drives the second clamping plate; and a determination subunit, configured to determine the clamping force of the clamping assembly based on the minimum value of the first output torque and the second output torque.

[0130] In some embodiments, predetermined variables of the target clamping assembly include: tension in the thread connecting the driving wheel and the driven wheel; wherein, when the driven wheel rotates, it drives the clamping plates of the clamping assembly to move.

[0131] In some embodiments, the tension on the wire is obtained by measuring the voltage between two surfaces of a piezoelectric material layer disposed in the first wire and the cross-sectional area of ​​the piezoelectric material layer; calculating the charge on one surface of the piezoelectric material layer based on the voltage and the cross-sectional area; and calculating the tension on the first wire based on the charge on the one surface and the piezoelectric effect coefficient.

[0132] In some embodiments, predetermined variables of the clamping component include: the static friction force when the clamping component clamps the target object.

[0133] In some embodiments, the static friction force is obtained by: determining the angle between the extension direction of the clamping component and the horizontal direction from an image of the clamping component clamping the target object; the horizontal direction being a direction perpendicular to the direction of gravity; determining the weight of the clamped portion of the target object; determining the static friction force between the clamping component and the target object based on the weight of the clamped portion of the target object and the angle between the extension direction of the clamping component and the horizontal direction, and using the static friction force as a predetermined variable of the clamping component.

[0134] In some embodiments, the method further includes: a detection unit, configured to detect in real time whether the clamping component is performing a clamping action; a second determination unit, configured to determine the clamping state of the clamping component on the target object when a clamping action is detected; the clamping state is determined based on the coverage of the target object on the clamping surface of the clamping component; and, in the case of reaching a predetermined clamping state, to obtain the current value of a predetermined variable of the clamping component, the predetermined variable being a variable associated with the clamping force output by the clamping component; and a prompting unit, configured to present a prompting message to the operator if the predetermined clamping state is not reached, the prompting message being used to remind the operator to control the action of the clamping component to adjust the clamping state of the clamping component on the target object.

[0135] For details regarding the control device of the aforementioned clamping assembly, please refer to [link / reference needed]. Figure 9 , Figure 11 The relevant descriptions and effects in the corresponding embodiments are for reference only and will not be repeated here.

[0136] This specification provides a robot, including a base, a first robotic arm, a gripping assembly, a manipulator, an image acquisition assembly, an adjustment assembly, and a controller.

[0137] The first and second robotic arms are mounted on the base. In some embodiments, there may be multiple first robotic arms and multiple second robotic arms.

[0138] The gripping assembly is located at the end of the first robotic arm.

[0139] An adjustment component is provided on the clamping assembly for adjusting the clamping force of the clamping assembly. For example, the adjustment component may include motors provided on each shaft of the clamping assembly, i.e., motors for realizing movement in each degree of freedom (especially the opening and closing degree of freedom of the first and second clamping plates at the ends of the clamping assembly).

[0140] The controller is used to obtain the current value of a predetermined variable of the clamping component when the clamping component clamps the target object, the predetermined variable being a variable associated with the clamping force output by the clamping component; determine target parameters based on the current attributes of the target object; process the value of the predetermined variable using the target parameters to obtain a processing result; and adjust the input control quantity of the clamping component based on the processing result; wherein the predetermined variable changes with the input control quantity.

[0141] For example, in Figure 1 The controller is provided in the execution device 200 shown. The controller can generate control commands for each shaft motor in the clamping assembly according to the control commands sent by the control device 100, so that the first clamping plate and the second clamping plate of the clamping assembly can move in the opening and closing degrees of freedom, thereby realizing the adjustment of the clamping force.

[0142] In some embodiments, the robot may also include a second robotic arm, an image acquisition component, and a manipulator.

[0143] An image acquisition component is located at the end of the second robotic arm and is used to acquire real-time images of the target object held by the gripping component. For example, the image acquisition component can be an endoscope, an ultrasound detector, etc.

[0144] The manipulator is used by the operator to control the clamping assembly to hold the target object. The manipulator can be detached from the base, for example, Figure 2 The main operator is shown on the doctor's console; the operator can also be mounted on the base.

[0145] This invention also provides a controller, such as... Figure 16 As shown, the controller may include a processor 1601 and a memory 1602, wherein the processor 1601 and the memory 1602 can be connected via a bus or other means. Figure 16 Taking the example of a connection between China and Israel via a bus.

[0146] Processor 1601 can be a Central Processing Unit (CPU). Processor 1601 can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0147] Memory 1602, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the control method of the clamping component in the embodiments of the present invention (e.g., Figure 15 The processor 1601 comprises an acquisition unit 10, a first determination unit 20, a processing unit 30, and an adjustment unit 40. The processor 1601 executes various functional applications and data classification by running non-transitory software programs, instructions, and modules stored in the memory 1602, thereby implementing the control method for the clamping component in the above method embodiments.

[0148] The memory 1602 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor 1601, etc. Furthermore, the memory 1602 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1602 may optionally include memory remotely located relative to the processor 1601, and these remote memories may be connected to the processor 1601 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0149] The one or more modules are stored in the memory 1602, and when executed by the processor 1601, they perform the following: Figure 9 or Figure 11 The control method of the clamping component in the illustrated embodiment.

[0150] For specific details about the aforementioned controller, please refer to [link / reference]. Figure 9 or Figure 11 The relevant descriptions and effects in the corresponding embodiments are for reference only and will not be repeated here.

[0151] This specification also provides a computer storage medium storing computer program instructions, which, when executed, implement... Figure 9 or Figure 11 The steps corresponding to the embodiments.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0153] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0154] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0155] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0156] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A control method for a clamping component, characterized in that, The method is used to rapidly converge the clamping force of the clamping assembly to the target clamping force value after determining the target clamping force control value; the method includes: When the clamping component clamps the target object, a pre-built target state observer is used to predict the current value of a predetermined variable of the clamping component. The predetermined variable is a variable related to the clamping force output by the clamping component. The target state observer takes the input control quantity and the measurable output quantity of the clamping component as inputs, and the observed estimated value of the predetermined variable as the observed output. The input control quantity refers to the control quantity used to control the action of the clamping component. Determine the target parameters based on the attributes of the current target object; The values ​​of the predetermined variables are processed using the target parameters to obtain the processing results; Based on the processing result, the input control quantity of the clamping component is adjusted so that the clamping force of the clamping component quickly converges to the clamping force control target value; wherein, the predetermined variable changes with the input control quantity; The values ​​of the predetermined variables are processed using target parameters to obtain processing results, including: substituting the predicted values ​​of the predetermined variables into a pre-constructed target function to determine the target input control quantity when the value of the target function is minimized; the target function is constructed using the predetermined variables of the clamping component and the input control quantity of the clamping component as variables.

2. The method according to claim 1, characterized in that, The target parameters are determined based on the attributes of the current target object, including: Get the current image of the clamping component holding the current target object; Identify the attributes of the current target object from the current image; Input the attributes of the current target object into the pre-trained network model to obtain the target parameters.

3. The method according to claim 2, characterized in that, The network model was trained in the following way: Obtain a training sample set, which includes multiple training samples. Each training sample includes a sample image of a sample object held by a clamping component and sample parameters corresponding to the sample image. The network model is trained by using sample images from each training sample in the training sample set as input and sample parameters from the training samples as output. The network model includes a first sub-network and a second sub-network. The first sub-network is used to identify the attribute information of the sample object from the sample image, and the second sub-network is used to determine multiple values ​​of the target parameter and the probability corresponding to each value based on the attribute information of the sample object.

4. The method according to claim 1, characterized in that, The predetermined variables of the clamping component include: the clamping force of the clamping component.

5. The method according to claim 4, characterized in that, When the clamping component clamps the target object, a pre-built target state observer is used to predict the current values ​​of predetermined variables of the clamping component, including: When the clamping assembly clamps the target object, a first target state observer is used to predict the first output torque of the first driven wheel that drives the first clamping plate to move; wherein, the clamping assembly includes a first clamping plate and a second clamping plate, and the first clamping plate and the second clamping plate are connected by a rotating shaft; The second target state observer is used to predict the second output torque of the second driven wheel that drives the second clamping plate. The clamping force of the clamping assembly is determined based on the minimum value between the first output torque and the second output torque.

6. The method according to claim 1, characterized in that, The predetermined variables of the clamping assembly include: the tension in the thread connecting the driving wheel and the driven wheel; wherein, when the driven wheel rotates, it drives the clamping plates of the clamping assembly to move.

7. The method according to claim 6, characterized in that, The tension in the thread is obtained in the following way: Measure the voltage between the two surfaces of the piezoelectric material layer disposed in the wire, and the cross-sectional area of ​​the piezoelectric material layer; The charge on one surface of the piezoelectric material layer is calculated based on the voltage and the cross-sectional area. The tension on the wire is calculated based on the charge and piezoelectric coefficient of one of the surfaces.

8. The method according to claim 1, characterized in that, The predetermined variables of the clamping component include: the static friction force when the clamping component clamps the target object.

9. The method according to claim 8, characterized in that, The static friction force is obtained in the following way: Determine the angle between the extension direction of the clamping component and the horizontal direction from an image of the clamping component holding the target object; the horizontal direction is the direction perpendicular to the direction of gravity. Determine the weight of the portion of the target object that is being clamped; Based on the weight of the clamped portion of the target object and the angle between the extension direction of the clamping component and the horizontal direction, the static friction force between the clamping component and the target object is determined, and the static friction force is used as a predetermined variable of the clamping component.

10. The method according to claim 1, characterized in that, Before substituting the values ​​of predetermined variables of the clamping component into the objective function to determine the target input control quantity when the objective function is minimized, the method further includes: Real-time detection of whether the clamping components are performing clamping actions; When a clamping action is detected, the clamping state of the clamping component on the target object is determined; the clamping state is determined based on the coverage of the target object on the clamping surface of the clamping component. If the predetermined clamping state is reached, the predetermined variable of the clamping component is predicted to be at its current value. The predetermined variable is a variable related to the clamping force output by the clamping component. Otherwise, a prompt message is presented to the operator to remind the operator to control the action of the clamping component to adjust the clamping state of the clamping component on the target object.

11. A control device for a clamping assembly, characterized in that, The device is used to rapidly converge the clamping force of the clamping assembly to the target clamping force value after the target clamping force value has been determined; the device includes: The acquisition unit is used to predict the current value of a predetermined variable of the clamping component when the clamping component clamps the target object, using a pre-built target state observer. The predetermined variable is a variable related to the clamping force output by the clamping component. The target state observer takes the input control quantity and the measurable output quantity of the clamping component as inputs, and the observed estimated value of the predetermined variable as the observed output. The input control quantity refers to the control quantity used to control the action of the clamping component. The first determining unit is used to determine the target parameters based on the attributes of the current target object; The processing unit is used to process the values ​​of the predetermined variables using the target parameters to obtain the processing result; An adjustment unit is configured to adjust the input control quantity of the clamping component according to the processing result, so that the clamping force of the clamping component quickly converges to the clamping force control target value; wherein the predetermined variable changes with the input control quantity. The values ​​of the predetermined variables are processed using target parameters to obtain processing results, including: substituting the predicted values ​​of the predetermined variables into a pre-constructed target function to determine the target input control quantity when the value of the target function is minimized; the target function is constructed using the predetermined variables of the clamping component and the input control quantity of the clamping component as variables.

12. A robot, characterized in that, include: Base; The first robotic arm is mounted on the base; A gripping assembly is disposed at the end of the first robotic arm; An adjustment component, disposed on the clamping component, is used to adjust the clamping force of the clamping component; A controller is used to predict the current value of a predetermined variable of the clamping component when the clamping component is clamping a target object, using a pre-built target state observer. The predetermined variable is a variable associated with the clamping force output by the clamping component. The target state observer takes the input control quantity and the measurable output quantity of the clamping component as inputs, and the observed estimated value of the predetermined variable as the observed output. The input control quantity refers to the control quantity used to control the action of the clamping component. Target parameters are determined based on the current attributes of the target object. The values ​​of the predetermined variable are processed using the target parameters to obtain a processing result. Based on the processing result, the input control quantity of the clamping component is adjusted so that the clamping force of the clamping component quickly converges to the clamping force control target value after it is determined. The predetermined variable changes with the input control quantity. The values ​​of the predetermined variables are processed using target parameters to obtain processing results, including: substituting the predicted values ​​of the predetermined variables into a pre-constructed target function to determine the target input control quantity when the value of the target function is minimized; the target function is constructed using the predetermined variables of the clamping component and the input control quantity of the clamping component as variables.

13. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed, implement the steps of the method according to any one of claims 1 to 10.

Images