Friction compensation methods, devices, equipment, media and products for surgical robots

Abstract

The application discloses a kind of surgical robot friction compensation method, device, equipment, medium and product, the method includes: obtaining the current angular velocity and the angle to be measured of joint to be measured in surgical robot;Obtain the target friction prediction model corresponding to the joint to be measured and the current angular velocity and pre-constructed;The angle to be measured is input into the target friction prediction model, and the output target friction torque size is obtained;According to the current angular velocity and the target friction torque size, the joint to be measured is compensated for friction torque, and the embodiment of the application solves the problem that the adaptation of conventional friction compensation method and surgical robot is poor, improves the friction compensation effect of surgical robot, and guarantees the stability of surgical robot under different angular velocity conditions.

Description

Technical Field

[0001] This invention relates to the field of surgical robot technology, and in particular to a friction compensation method, device, equipment, medium, and product for a surgical robot. Background Technology

[0002] Surgical robots, as a significant advancement in medical technology, play a crucial role in the success of surgeries due to their precision and stability. Joint friction is a significant factor in the design and operation of surgical robots, affecting not only their motion accuracy and dynamic performance but also potentially impacting surgical outcomes. Therefore, compensating for joint friction in surgical robots is a key technology for improving their motion accuracy and stability.

[0003] Current friction compensation methods are mainly designed for industrial robots. However, there are differences in the actual operation of industrial robots and surgical robots. Therefore, traditional friction compensation methods are poorly adapted to surgical robots, resulting in unsatisfactory friction compensation effects. Summary of the Invention

[0004] This invention provides a friction compensation method, device, equipment, medium, and product for surgical robots to solve the problem of poor compatibility between traditional friction compensation methods and surgical robots, thereby improving the friction compensation effect of surgical robots.

[0005] According to an embodiment of the present invention, a friction compensation method for a surgical robot is provided, the method comprising:

[0006] Obtain the current angular velocity and the angle to be measured of the joint under test in the surgical robot;

[0007] Obtain a pre-constructed target friction prediction model corresponding to the joint to be tested and the current angular velocity;

[0008] The measured angle is input into the target friction prediction model to obtain the output target friction torque.

[0009] Friction torque compensation is performed on the joint under test based on the current angular velocity and the target friction torque magnitude.

[0010] According to another embodiment of the present invention, a friction compensation device for a surgical robot is provided, the device comprising:

[0011] The module for acquiring the angle to be measured is used to acquire the current angular velocity and the angle to be measured of the joint to be measured in the surgical robot.

[0012] The target friction prediction model acquisition module is used to acquire a pre-constructed target friction prediction model corresponding to the joint to be measured and the current angular velocity.

[0013] The target friction torque output module is used to input the angle to be measured into the target friction prediction model to obtain the output target friction torque.

[0014] The friction torque compensation module is used to compensate the friction torque of the joint under test based on the current angular velocity and the target friction torque magnitude.

[0015] According to another embodiment of the present invention, a surgical robot is provided, the surgical robot comprising: a control device and at least one joint;

[0016] The control device includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the friction compensation method for the surgical robot according to any embodiment of the present invention.

[0017] According to another embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the friction compensation method of the surgical robot according to any embodiment of the present invention.

[0018] According to another embodiment of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the friction compensation method for a surgical robot according to any embodiment of the present invention.

[0019] In practical applications, surgical robots often move at a constant angular velocity. However, traditional friction compensation methods mostly construct friction compensation models with angular velocity as the independent variable, resulting in a single prediction result for friction torque in surgical robot scenarios and poor prediction accuracy.

[0020] The technical solution of this invention pre-builds friction prediction models for each joint in a surgical robot under different angular velocity conditions, using angle as the independent variable to predict the magnitude of friction torque at different angular postures of the joint under the same angular velocity condition. Based on the current angular velocity of the joint and the predicted magnitude of friction torque, friction torque compensation is performed on the joint. This solves the problem of poor compatibility between traditional friction compensation methods and surgical robots, improves the friction compensation effect of the surgical robot, and ensures the stability of the surgical robot under different angular velocity conditions.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart illustrating a friction compensation method for a surgical robot according to an embodiment of the present invention;

[0024] Figure 2 A flowchart illustrating another friction compensation method for a surgical robot provided in one embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the model architecture of a target friction prediction model provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of a friction compensation device for a surgical robot according to an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of a surgical robot provided in one embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of a control device provided in one embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," "target," "preset," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Figure 1 This is a flowchart illustrating a friction compensation method for a surgical robot according to an embodiment of the present invention. This embodiment is applicable to situations requiring compensation for frictional forces at joints in a surgical robot. The method can be executed by a friction compensation device of the surgical robot, which can be implemented in hardware and / or software and can be configured in a control device. Figure 1 As shown, the method includes:

[0032] S110. Obtain the current angular velocity and the angle to be measured of the joint to be tested in the surgical robot.

[0033] Specifically, the surgical robot has at least one joint, and the joint to be tested can be any joint in the surgical robot. For example, the joint to be tested can be a joint used to connect the base and the robotic arm, a joint used to connect two robotic arms, or a joint used to connect the robotic arm and surgical instruments. There is no limitation on the joint to be tested here, and it can be customized according to the actual friction compensation requirements.

[0034] Specifically, the current angular velocity can characterize the running speed of the joint under test, and the measured angle can characterize the running position of the joint under test.

[0035] For example, the triggering conditions for the friction compensation process of the surgical robot include, but are not limited to, a preset trigger cycle, detection of a change in the angular velocity of the joint under test, and detection of a compensation trigger operation. For example, the preset trigger cycle can be 1 minute, and the compensation trigger operation can be implemented by the user through hardware components or software controls provided by the control device. The triggering conditions for the friction compensation process of the surgical robot are not limited here; they can be customized according to actual needs.

[0036] S120. Obtain the pre-built target friction prediction model corresponding to the joint to be measured and the current angular velocity.

[0037] Specifically, pre-built friction prediction models for different joints under different angular velocities are constructed. Based on the joint to be tested and the current angular velocity, the target friction prediction model can be found from a series of pre-built friction prediction models. The input of the pre-built friction prediction model is the angle of the joint, and the output is the magnitude of the friction torque.

[0038] In an optional embodiment, the method further includes: for each training joint in the surgical robot, during the uniform motion of the training joint at a training angular velocity, acquiring a training motor torque set for the training joint; wherein the training motor torque set includes the positive motor torque and negative motor torque corresponding to each training angle of the training joint; constructing a training friction torque set based on the training motor torque set; wherein the training friction torque set includes the magnitude of the training friction torque corresponding to each training angle of the training joint; and constructing a preset friction prediction model corresponding to the training joint and the training angular velocity based on the training friction torque set.

[0039] In one optional embodiment, the training angular velocity includes a positive angular velocity and a negative angular velocity. Correspondingly, during the uniform movement of the training joint at the training angular velocity, obtaining the training motor torque set of the training joint includes: during the uniform movement of the training joint at the positive angular velocity, adding the motor torque of the training joint at each training angle as a positive motor torque to the training motor torque set; during the uniform movement of the training joint at the negative angular velocity, adding the motor torque of the training joint at each training angle as a negative motor torque to the training motor torque set; wherein the positive angular velocity and the negative angular velocity have the same magnitude but opposite directions.

[0040] In one optional embodiment, a series of training angles are obtained by dividing the space at preset angle intervals. For example, the preset angle interval can be 5° or 10°. The preset angle interval is not limited here and can be customized according to actual needs.

[0041] Specifically, the training motor torque set includes a positive motor torque set and a negative motor torque set. The positive motor torque set includes the positive motor torque corresponding to the training joint and each training angle, while the negative motor torque set includes the negative motor torque corresponding to the training joint and each training angle.

[0042] In an optional embodiment, a training friction torque set is constructed based on the training motor torque set, including: for each training angle, obtaining the positive motor torque and negative motor torque corresponding to the training angle in the training motor torque set; determining the difference motor torque between the positive motor torque and the negative motor torque; and adding the absolute value of half of the difference motor torque as the magnitude of the training friction torque corresponding to the training angle to the training friction torque set.

[0043] According to robotics, the dynamic equations of a robot's joints satisfy the following formula:

[0044]

[0045] Where q represents the angle of the joint. Indicates the angular velocity of the joint. τ represents the angular acceleration of the joint. m Indicates motor torque. Represents the moment of inertia. G(q) represents the centripetal torque, and τ represents the gravitational torque. f This represents the frictional torque.

[0046] Since surgical robots operate in a low-speed environment, gravitational torque and frictional torque play a dominant role. Therefore, inertial torque and centripetal torque can be ignored in surgical robot scenarios.

[0047] When the joint moves at a constant positive angular velocity, the above dynamic equations can be simplified to:

[0048]

[0049] in, G represents the positive motor torque at training angle q. + (q) represents the gravitational torque at the positive angular velocity and training angle q, τ f (q) represents the magnitude of the frictional torque at the training angle q.

[0050] When the joint moves at a constant negative angular velocity, the above dynamic equations can be simplified to:

[0051]

[0052] in, G represents the negative motor torque at training angle q. - (q) represents the negative angular velocity and the gravitational torque at the training angle q.

[0053] Since gravitational torque is only related to the angle of the joints and not to the angular velocity, therefore G + (q)=G - (q). From this, the magnitude of the frictional torque τ can be derived. f (q) satisfies the following formula:

[0054]

[0055] In one optional embodiment, constructing a preset friction prediction model corresponding to the training joint and training angular velocity based on the training friction torque set includes: training an untrained initial friction prediction model based on the training friction torque set to obtain a pre-trained preset friction prediction model corresponding to the training joint and training angular velocity.

[0056] For example, the preset friction prediction model can be a ResNet, Transformer, CNN (Convolutional Neural Networks), FCN (Fully Convolutional Networks), DNN (Deep Neural Networks), or RNN (Recurrent Neural Network), etc. The model architecture of the preset friction prediction model is not limited here; it can be customized according to actual needs.

[0057] The model architecture of each preset friction prediction model for different joints under different angular velocities can be the same or different. For example, the model architecture of the preset friction prediction model for joint A at angular velocity A can be a residual network, the model architecture of the preset friction prediction model for joint B at angular velocity A can be a CNN network, and the model architecture of the preset friction prediction model for joint A at angular velocity B can be a DNN network.

[0058] Of course, it is also possible to set the model architecture of each preset friction prediction model for the same joint under different angular velocity conditions to be the same, or to set the model architecture of each preset friction prediction model for different joints under the same angular velocity conditions to be the same.

[0059] Specifically, each training angle from the training friction torque set is input into the untrained initial friction prediction model to obtain the output predicted friction torque set. The loss function value is determined based on the predicted friction torque set and the training friction torque set. The model parameters of the initial friction prediction model are adjusted based on the loss function value until the training termination condition is met. Then, the initial friction prediction model in the current iteration is taken as the preset friction prediction model that has been trained.

[0060] For example, the loss functions corresponding to the loss function values ​​include, but are not limited to, the squared loss function, the logarithmic loss function, the exponential loss function, the mean squared error loss function, the logistic regression loss function, the Huber loss function, the cross-entropy loss function, or the Kullback-Leibler divergence loss function, etc.

[0061] S130. Input the angle to be measured into the target friction prediction model to obtain the output target friction torque.

[0062] For example, the magnitude of the target frictional torque can be expressed as ||f||.

[0063] S140. Based on the current angular velocity and the target friction torque, perform friction torque compensation on the joint under test.

[0064] In one optional embodiment, friction torque compensation is performed on the joint under test based on the current angular velocity and the target friction torque magnitude, including: determining the compensation torque based on the angular velocity direction corresponding to the current angular velocity and the target friction torque magnitude; and performing friction torque compensation on the joint under test based on the compensation torque.

[0065] In this embodiment, the direction of the compensating torque is the same as the direction of the angular velocity, and the magnitude of the compensating torque is the same as the magnitude of the target friction torque.

[0066] For example, the compensation torque F can be expressed as F=||f||×sgn(ω), where ω represents the current angular velocity and sgn represents the sign function.

[0067] Specifically, the compensation torque and the motor torque of the joint under test are summed to obtain the compensated motor torque.

[0068] In another optional embodiment, friction torque compensation is performed on the joint under test based on the current angular velocity and the target friction torque magnitude, including: obtaining a compensation coefficient corresponding to the current angular velocity; determining a compensation torque based on the angular velocity direction corresponding to the current angular velocity, the compensation coefficient, and the target friction torque magnitude; and performing friction torque compensation on the joint under test based on the compensation torque.

[0069] Specifically, compensation coefficients corresponding to different angular velocity ranges are pre-set, and the compensation coefficients are determined based on the angular velocity range satisfied by the current angular velocity. For example, the compensation torque F can be expressed as F=k×||f||×sgn(ω), where k represents the compensation coefficient.

[0070] The technical solution of this embodiment pre-builds friction prediction models for each joint in the surgical robot under different angular velocity conditions. Using the angle as the independent variable, it predicts the magnitude of the friction torque of the joint at different angular postures under the same angular velocity condition. Based on the current angular velocity of the joint and the predicted friction torque, it compensates for the friction torque of the joint. This solves the problem of poor compatibility between traditional friction compensation methods and surgical robots, improves the friction compensation effect of the surgical robot, and ensures the stability of the surgical robot under different angular velocity conditions.

[0071] Figure 2This is a flowchart illustrating another friction compensation method for a surgical robot according to an embodiment of the present invention. This embodiment further refines the "target friction prediction model" in the above embodiment. Figure 2 As shown, the method includes:

[0072] S210. Obtain the current angular velocity and the angle to be measured of the joint to be tested in the surgical robot.

[0073] S220. Obtain the pre-built target friction prediction model corresponding to the joint to be measured and the current angular velocity.

[0074] In this embodiment, S210-S220 are the same as those in the above embodiments. Figure 1 The S110-S120 shown are the same or similar, and will not be described again in this embodiment.

[0075] In this embodiment, the target friction prediction model includes an input layer, a hidden layer, a summing layer, and an output layer; wherein, the number of hidden modules in the hidden layer is the same as the number of training angles for the training friction torque, the output of the input layer is connected to each hidden module, and the output of each hidden module is connected to the summing layer.

[0076] In this embodiment, the summation layer includes a first summation module and a second summation module.

[0077] S230. Through the input layer, the input angle to be measured is output to each hidden module in the hidden layer.

[0078] For example, the input layer may consist of a single neuron. The layer architecture of the input layer is not limited here; it can be customized according to actual needs.

[0079] Figure 3 This is a schematic diagram of the model architecture for a target friction prediction model provided in one embodiment of the present invention. Specifically, Figure 3 In this context, "θ" represents the angle to be measured.

[0080] S240. Using the hidden module, determine the angle distance feature based on the angle to be tested and the training angle corresponding to the hidden module.

[0081] Specifically, the angular distance feature characterizes the difference between the angle to be tested and the training angle corresponding to the hidden module. For example, the angular distance feature p output by the i-th hidden module... i It is expressed by the following formula:

[0082]

[0083] Where x0 represents the angle to be measured, x i Let represent the training angle corresponding to the i-th hidden module, σ represent the smoothing factor, and d represent the distance function.

[0084] For example, distance functions include, but are not limited to, Euclidean distance functions, Manhattan distance functions, Chebyshev distance functions, or cosine distance functions, etc.

[0085] See Figure 3 , Figure 3 Taking a hidden layer containing three hidden modules as an example, each hidden module outputs its determined angle and distance features to the first and second summing modules in the summing layer, respectively.

[0086] S250. Through the first summing module, the first friction feature is obtained by weighted summing of the angle distance features output by each hidden module according to the magnitude of the training friction torque corresponding to each training angle.

[0087] For example, the first friction feature S1 is represented by the following formula:

[0088]

[0089] Where n represents the number of hidden modules, y i This represents the magnitude of the training friction torque corresponding to the i-th training angle.

[0090] S260. The second friction feature is obtained by arithmetic summation of the angle and distance features output by each hidden module through the second summation module.

[0091] In the second summing module, each angular distance feature has a weight of 1. For example, the second friction feature S2 is represented by the following formula:

[0092]

[0093] Where n represents the number of hidden modules, y i This represents the magnitude of the training friction torque corresponding to the i-th training angle.

[0094] S270. Through the output layer, the ratio between the first friction feature and the second friction feature is used as the target friction torque magnitude.

[0095] For example, the target frictional torque ||f|| is expressed by the following formula:

[0096]

[0097] In this embodiment, during the construction of the target friction prediction model, the target friction prediction model is obtained by adjusting and testing the smoothing factor of the initial friction prediction model, or by selecting and testing initial friction prediction models with different smoothing factors.

[0098] S280. Based on the current angular velocity and the target friction torque, perform friction torque compensation on the joint under test.

[0099] S280 in this embodiment is the same as that in the above embodiment. Figure 1 The S140 shown is the same or similar, and will not be described again in this embodiment.

[0100] The technical solution of this embodiment sets up a target friction prediction model including an input layer, a hidden layer, a summing layer, and an output layer. The number of hidden modules in the hidden layer is the same as the number of angles trained for the friction torque. The output of the input layer is connected to each hidden module, and the output of each hidden module is connected to the summing layer. This avoids the problem of local optima that may occur during the training of traditional neural network models. It also avoids the overfitting and underfitting of traditional neural network models, ensuring the generalization ability of the target friction prediction model, thereby further improving the friction compensation effect of the surgical robot.

[0101] The following are embodiments of the friction compensation device for a surgical robot provided in this invention. This device and the friction compensation method for a surgical robot in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the friction compensation device for a surgical robot, please refer to the content of the friction compensation method for a surgical robot in the above embodiments.

[0102] Figure 4 This is a schematic diagram of the structure of a friction compensation device for a surgical robot according to an embodiment of the present invention. Figure 4 As shown, the device includes: a module for acquiring the angle to be measured 310, a module for acquiring the target friction prediction model 320, a module for outputting the magnitude of the target friction torque 330, and a module for compensating for the friction torque 340.

[0103] Among them, the angle acquisition module 310 is used to acquire the current angular velocity and the angle to be measured of the joint to be measured in the surgical robot;

[0104] The target friction prediction model acquisition module 320 is used to acquire a pre-built target friction prediction model corresponding to the joint to be measured and the current angular velocity.

[0105] The target friction torque output module 330 is used to input the angle to be measured into the target friction prediction model to obtain the output target friction torque.

[0106] The friction torque compensation module 340 is used to compensate for the friction torque of the joint under test based on the current angular velocity and the magnitude of the target friction torque.

[0107] The technical solution of this embodiment pre-builds friction prediction models for each joint in the surgical robot for different angular velocity conditions. Using the angle as the independent variable, it predicts the magnitude of the friction torque of the joint at different angular postures under the same angular velocity condition. Based on the current angular velocity of each joint and the predicted friction torque, it compensates for the friction torque of each joint. This solves the problem of poor adaptability between traditional friction compensation methods and surgical robots, improves the friction compensation effect of the surgical robot, and ensures the stability of the surgical robot under different angular velocity conditions.

[0108] In an optional embodiment, the device further includes:

[0109] The training motor torque set acquisition module is used to acquire the training motor torque set of each training joint in the surgical robot during the uniform motion of the training joint at the training angular velocity; wherein, the training motor torque set includes the positive motor torque and negative motor torque corresponding to each training angle of the training joint;

[0110] The training friction torque set construction module is used to construct a training friction torque set based on the training motor torque set; wherein, the training friction torque set contains the magnitude of the training friction torque corresponding to the training joint and each training angle;

[0111] The preset friction prediction model construction module is used to construct a preset friction prediction model corresponding to the training joint and the training angular velocity based on the training friction torque set.

[0112] In one optional embodiment, the training angular velocity includes positive angular velocity and negative angular velocity; correspondingly, the training motor torque set acquisition module is specifically used for:

[0113] During the uniform movement of the training joint at a positive angular velocity, the motor torque of the training joint at each training angle is added as a positive motor torque to the training motor torque set.

[0114] During the uniform movement of the training joint at a negative angular velocity, the motor torque of the training joint at each training angle is added as a negative motor torque to the training motor torque set.

[0115] Among them, the positive angular velocity and the negative angular velocity have the same magnitude but opposite directions.

[0116] In one optional embodiment, the friction torque set construction module is specifically used for:

[0117] For each training angle, obtain the positive and negative motor torques corresponding to the training motor torque concentration and the training angle;

[0118] Determine the difference between the positive and negative motor torque;

[0119] The absolute value of half of the differential motor torque is added to the training friction torque set as the training friction torque magnitude corresponding to the training angle.

[0120] In one optional embodiment, the target friction prediction model includes an input layer, a hidden layer, a summing layer, and an output layer;

[0121] The number of hidden modules in the hidden layer is the same as the number of angles trained for the friction torque. The output of the input layer is connected to each hidden module, and the output of each hidden module is connected to the summation layer.

[0122] In an optional embodiment, the summing layer includes a first summing module and a second summing module. Correspondingly, the target friction torque magnitude output module 330 is specifically used for:

[0123] The input layer outputs the measured angle to each hidden module in the hidden layer.

[0124] By using the hidden module, the angular distance feature is determined based on the angle to be tested and the training angle corresponding to the hidden module;

[0125] The first friction feature is obtained by weighting and summing the angle distance features output by each hidden module according to the magnitude of the training friction torque corresponding to each training angle through the first summing module.

[0126] The second summation module performs an arithmetic summation on the angular distance features output by each hidden module to obtain the second friction feature.

[0127] The ratio between the first friction feature and the second friction feature is used as the target friction torque magnitude through the output layer.

[0128] In an optional embodiment, the friction torque compensation module 340 is specifically used for:

[0129] The compensation torque is determined based on the direction of the angular velocity corresponding to the current angular velocity and the magnitude of the target friction torque; wherein, the direction of the compensation torque is the same as the direction of the angular velocity, and the magnitude of the compensation torque is the same as the magnitude of the target friction torque;

[0130] Based on the compensation torque, friction torque compensation is performed on the joint under test.

[0131] The friction compensation device for the surgical robot provided in this embodiment of the invention can execute the friction compensation method for the surgical robot provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0132] Figure 5This is a schematic diagram of the structure of a surgical robot provided in one embodiment of the present invention. The surgical robot in this embodiment provides services for the friction compensation method of the surgical robot in the above embodiments.

[0133] In this embodiment, the surgical robot includes a control device 410 and at least one joint 420. See also Figure 5 , Figure 5 An example is given using a surgical robot that has three joints.

[0134] In an optional embodiment, the control device 410 is specifically used to: take the angular velocity of the joint to be tested set during operation as the current angular velocity of the joint to be tested, and take the product of the running time of the joint to be tested and the current angular velocity as the angle to be tested of the joint to be tested.

[0135] In another alternative embodiment, each joint is provided with a data acquisition device, and the control device 410 is communicatively connected to the data acquisition device.

[0136] In one alternative embodiment, the data acquisition device includes an angular velocity sensor and / or an angle sensor, wherein the angular velocity sensor is used to acquire the angular velocity of the joint, and the angle sensor is used to acquire the angle of the joint.

[0137] In one specific embodiment, when the data acquisition device only includes an angular velocity sensor, the control device 410 is specifically used to: take the angular velocity acquired by the angular velocity sensor as the current angular velocity of the joint to be measured, and take the product of the running time of the joint to be measured and the current angular velocity as the angle to be measured of the joint to be measured.

[0138] In another specific embodiment, when the data acquisition device only includes an angle sensor, the control device 410 is specifically used to: take the angular velocity of the joint to be tested set during operation as the current angular velocity of the joint to be tested, and take the angle collected by the angle sensor as the angle to be tested of the joint to be tested.

[0139] In another specific embodiment, when the data acquisition device only includes an angle sensor, the control device 410 is specifically used to: take the angle acquired by the angle sensor as the angle to be measured of the joint to be measured, and take the ratio between the angle to be measured and the running time of the joint to be measured as the current angular velocity of the joint to be measured.

[0140] In another specific embodiment, when the data acquisition device includes an angular velocity sensor and an angle sensor, the control device 410 is specifically used to: use the angular velocity acquired by the angular velocity sensor as the current angular velocity of the joint to be measured, and use the angle acquired by the angle sensor as the angle to be measured of the joint to be measured.

[0141] Understandably, the current angular velocity can be obtained by statistically calculating at least two of the following: the angular velocity collected by the data acquisition device, the calculated angular velocity, and the angular velocity preset during operation. The angle to be measured can then be obtained by statistically calculating the angle collected by the data acquisition device and the calculated angle. For example, statistical value calculation includes, but is not limited to, mean calculation, maximum value calculation, or minimum value calculation.

[0142] The advantage of this setting is that it can improve the accuracy of the current angular velocity and the angle to be measured, thereby further improving the friction compensation effect of the surgical robot.

[0143] Based on the above embodiments, the surgical robot may also include a robotic arm system, a chassis system, a power system, and a circuit system, etc. The specific hardware structure of the surgical robot is not limited here.

[0144] Figure 6 This is a schematic diagram of a control device provided according to one embodiment of the present invention. The control device 410 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, servers, blade servers, mainframe computers, and other suitable computers. The control device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0145] like Figure 6 As shown, the control device 410 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor 11. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the control device 410. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0146] Multiple components in the control device 410 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the control device 410 to exchange information or data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0147] Processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the friction compensation method for a surgical robot provided in the above embodiments.

[0148] In some embodiments, the friction compensation method for a surgical robot provided in the above embodiments can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the control device 410 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the friction compensation method for a surgical robot described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the friction compensation method for a surgical robot by any other suitable means (e.g., by means of firmware).

[0149] Various embodiments of the systems and techniques described above herein can be implemented in the following systems or combinations thereof: digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] Computer programs for implementing the friction compensation method of the surgical robot of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0151] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable storage medium. Examples of machine-readable storage media include, based on an electrical connection of at least one wire, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0152] To provide interaction with the user, the systems and techniques described herein can be implemented on a control device having: a display device for displaying information to the user (e.g., a cathode-ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the control device. Other types of devices can also provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0153] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0154] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0155] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0156] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A friction compensation method for a surgical robot, characterized by, The method comprises: obtaining a current angular velocity and a to-be-measured angle of a to-be-measured joint in a surgical robot; obtaining a pre-constructed target friction prediction model corresponding to the to-be-measured joint and the current angular velocity; inputting the to-be-measured angle into the target friction prediction model to obtain an output target friction torque size; performing friction torque compensation on the to-be-measured joint according to the current angular velocity and the target friction torque size; wherein the method further comprises: for each training joint in the surgical robot, obtaining a training motor torque set of the training joint during uniform motion of the training joint at a training angular velocity; wherein the training motor torque set contains positive motor torque and negative motor torque corresponding to the training joint and each training angle; constructing a training friction torque set according to the training motor torque set; wherein the training friction torque set contains a training friction torque size corresponding to the training joint and each training angle; constructing a preset friction prediction model corresponding to the training joint and the training angular velocity according to the training friction torque set.

2. The method of claim 1, wherein, The training angular velocity includes a positive angular velocity and a negative angular velocity, and correspondingly, the obtaining of the training motor torque set of the training joint during the uniform motion of the training joint at the training angular velocity comprises: during the uniform motion of the training joint at the positive angular velocity, adding the motor torque of the training joint at each training angle to the training motor torque set as positive motor torque; during the uniform motion of the training joint at the negative angular velocity, adding the motor torque of the training joint at each training angle to the training motor torque set as negative motor torque; wherein the positive angular velocity and the negative angular velocity have the same size and opposite directions.

3. The method of claim 1, wherein, The construction of the training friction torque set according to the training motor torque set comprises: for each training angle, obtaining the positive motor torque and the negative motor torque corresponding to the training angle in the training motor torque set; determining a difference motor torque between the positive motor torque and the negative motor torque; adding half of the absolute value of the difference motor torque to the training friction torque set as the training friction torque size corresponding to the training angle.

4. The method of claim 1, wherein, The target friction prediction model comprises an input layer, a hidden layer, a sum layer and an output layer; wherein the number of hidden modules in the hidden layer is the same as the number of training angles in the training friction torque set, the output of the input layer is connected to each hidden module, and the output of each hidden module is connected to the sum layer.

5. The method of claim 4, wherein, The sum layer comprises a first sum module and a second sum module, and correspondingly, the inputting of the to-be-measured angle into the target friction prediction model to obtain the output target friction torque size comprises: outputting the input to-be-measured angle to each hidden module in the hidden layer through the input layer; determining an angle distance feature according to the to-be-measured angle and the training angle corresponding to the hidden module through the hidden module; The first adding module is configured to: according to the training friction torque corresponding to each training angle, weight and sum the angle distance features output by each implicit module to obtain a first friction feature; The second adding module is configured to: arithmetically sum the angle distance features output by each implicit module to obtain a second friction feature; The output layer is configured to: take the ratio between the first friction feature and the second friction feature as a target friction torque.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: According to the target friction torque and the current angular velocity, determining a compensation torque; wherein the compensation torque has the same direction as the angular velocity, and the compensation torque has the same size as the target friction torque; According to the compensation torque, compensating the friction torque of the joint to be tested.

7. A friction compensation device of a surgical robot characterized by comprising: The method further includes: An angle to be tested acquisition module is configured to: acquire a current angular velocity and an angle to be tested of a joint to be tested in a surgical robot; A target friction prediction model acquisition module is configured to: acquire a target friction prediction model corresponding to the joint to be tested and the current angular velocity; A target friction torque output module is configured to: input the angle to be tested into the target friction prediction model to obtain an output target friction torque; A friction torque compensation module is configured to: according to the current angular velocity and the target friction torque, compensate the friction torque of the joint to be tested. The device further includes: A training motor torque set acquisition module is configured to: for each training joint in the surgical robot, acquire a training motor torque set of the training joint when the training joint moves at a training angular velocity; A training friction torque set construction module is configured to: according to the training motor torque set, construct a training friction torque set; wherein the training friction torque set includes a training friction torque corresponding to each training angle of the training joint; A preset friction prediction model construction module is configured to: according to the training friction torque set, construct a preset friction prediction model corresponding to the training joint and the training angular velocity.

8. A surgical robot, characterized by The surgical robot includes: a control device and at least one joint; The control device includes at least one processor and a memory connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the friction compensation method of the surgical robot in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the friction compensation method of the surgical robot in any one of claims 1-6.

10. A computer program product comprising a computer program which, when executed by a processor, implements the friction compensation method of a surgical robot according to any one of claims 1-6.

Images