Friction compensation method, device and equipment for surgical robot, medium and product

Abstract

The invention discloses a friction compensation method, device and equipment for a surgical robot, a medium and a product. The method comprises the steps that the current angular velocity and the to-be-measured angle of a to-be-measured joint in the surgical robot are obtained; acquiring a pre-constructed target friction prediction model corresponding to the joint to be measured and the current angular velocity; inputting the angle to be measured into the target friction prediction model to obtain an output target friction torque; according to the current angular velocity and the target friction torque, friction torque compensation is conducted on the to-be-measured joint, the problem that a traditional friction compensation method is poor in adaptation degree with a surgical robot is solved, the friction compensation effect of the surgical robot is improved, and the accuracy of the friction compensation method is improved. And the stability of the surgical robot under different angular velocity working conditions is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of surgical robots, and in particular to a friction compensation method, device, equipment, medium and product of a surgical robot. Background Art

[0002] As an important advancement in medical technology, the accuracy and stability of surgical robots are crucial to the success of surgery. In the design and operation of surgical robots, joint friction is a factor that cannot be ignored. It not only affects the robot's motion accuracy and dynamic performance, but may also have a negative impact on the surgical effect. Therefore, compensating for the joint friction of surgical robots is one of the key technologies to improve the motion accuracy and stability of surgical robots.

[0003] The current friction compensation methods are mainly aimed at industrial robots, but there are differences in the actual operation of industrial robots and surgical robots. Therefore, the traditional friction compensation methods are poorly compatible with surgical robots and the friction compensation effect is not good. Summary of the invention

[0004] Embodiments of the present invention provide a friction compensation method, device, equipment, medium and product for a surgical robot to solve the problem of poor compatibility between traditional friction compensation methods and surgical robots and improve the friction compensation effect of the surgical robot.

[0005] According to one 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 angle of the joint to be measured in the surgical robot;

[0007] Acquire a pre-built target friction prediction model corresponding to the joint to be measured and the current angular velocity;

[0008] Inputting the angle to be measured into the target friction prediction model to obtain the output target friction torque;

[0009] Friction torque compensation is performed on the joint to be measured according to the current angular velocity and the target friction torque.

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

[0011] The angle acquisition module to be measured is used to obtain the current angular velocity and angle to be measured of the joint to be measured in the surgical robot;

[0012] A target friction prediction model acquisition module is used to acquire a pre-built target friction prediction model corresponding to the joint to be tested and the current angular velocity;

[0013] A target friction torque magnitude output module, used for inputting the angle to be measured into the target friction prediction model to obtain an output target friction torque magnitude;

[0014] The friction torque compensation module is used to perform friction torque compensation on the joint to be tested according to the current angular velocity and the target friction torque.

[0015] According to another embodiment of the present invention, there is provided a surgical robot, 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, and the computer program is executed by the at least one processor so that the at least one processor can execute the friction compensation method of the surgical robot described in any embodiment of the present invention.

[0017] According to another embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the friction compensation method for a surgical robot described in any embodiment of the present invention when executed.

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

[0019] In actual use, surgical robots often move at a constant angular velocity. Traditional friction compensation methods mostly use angular velocity as the independent variable to construct friction compensation models, which results in a single prediction result of friction torque in surgical robot scenarios and poor prediction accuracy.

[0020] The technical solution of the embodiment of the present invention is to build a friction prediction model for each joint in the surgical robot for different angular velocity conditions in advance, use the angle as the independent variable, predict the friction torque of the joint at different angles under the same angular velocity condition, and compensate the joint for friction torque based on the current angular velocity of the joint and the predicted friction torque. 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 contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flowchart of a friction compensation method for a surgical robot provided by one embodiment of the present invention;

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

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

[0026] Figure 4 A schematic structural diagram of a friction compensation device for a surgical robot provided by one embodiment of the present invention;

[0027] Figure 5 A schematic diagram of the structure of a surgical robot provided by one embodiment of the present invention;

[0028] Figure 6 A schematic diagram of the structure of a control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", "target", "preset", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Figure 1 This is a flow chart of a friction compensation method for a surgical robot provided by an embodiment of the present invention. This embodiment is applicable to the case of compensating the friction force of the joints in the surgical robot. The method can be performed by a friction compensation device of the surgical robot. The friction compensation device of the surgical robot can be implemented in the form of hardware and / or software. The friction compensation device of the surgical robot can be configured in a control device. Figure 1 As shown, the method includes:

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

[0033] Specifically, the surgical robot is provided with at least one joint, and the joint to be tested may be any joint in the surgical robot. Exemplarily, the joint to be tested may be a joint for connecting a base and a robotic arm, a joint for connecting two robotic arms, or a joint for connecting a robotic arm and surgical equipment. The joint to be tested is not limited here, and may be customized according to actual friction compensation requirements.

[0034] Specifically, the current angular velocity can represent the operating speed of the joint to be measured, and the angle to be measured can represent the operating position of the joint to be measured.

[0035] Exemplarily, the triggering conditions of the friction compensation process of the surgical robot include, but are not limited to, a preset trigger period, detection of a change in the angular velocity of the joint to be tested, and detection of a compensation trigger operation, etc. Among them, for example, the preset trigger period can be 1 minute, and the compensation trigger operation can be implemented by the user through a hardware component or software control provided by the control device. The triggering conditions of the friction compensation process of the surgical robot are not limited here, and can be customized according to actual needs.

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

[0037] Specifically, preset friction prediction models for different joints under different angular velocity conditions are pre-built, and according to the joint to be tested and the current angular velocity, the target friction prediction model can be found from a series of pre-built preset friction prediction models. The input of the preset 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 also includes: for each training joint in the surgical robot, while the training joint moves at a uniform speed at a training angular velocity, obtaining a training motor torque set of the training joint; wherein the training motor torque set includes the positive motor torque and negative motor torque corresponding to the training joint and each training angle; based on the training motor torque set, constructing a training friction torque set; wherein the training friction torque set includes the magnitude of the training friction torque corresponding to the training joint and each training angle; based on the training friction torque set, constructing a preset friction prediction model corresponding to the training joint and the training angular velocity.

[0039] In an optional embodiment, the training angular velocity includes a positive angular velocity and a negative angular velocity. Accordingly, when the training joint moves at a uniform speed at the training angular velocity, the training motor torque set of the training joint is obtained, including: when the training joint moves at a uniform speed at a positive angular velocity, the motor torque of the training joint at each training angle is added to the training motor torque set as a positive motor torque; when the training joint moves at a uniform speed at a negative angular velocity, the motor torque of the training joint at each training angle is added to the training motor torque set as a negative motor torque; wherein the positive angular velocity and the negative angular velocity are the same in magnitude and opposite in direction.

[0040] In an optional embodiment, a series of training angles are obtained by dividing the angles at preset angle intervals. For example, the preset angle intervals may be 5° or 10°, and the preset angle intervals are not limited here, and may 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, wherein the positive motor torque set includes the positive motor torque corresponding to the training joint and each training angle, and 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 in the training motor torque set corresponding to the training angle; 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 training friction torque size corresponding to the training angle to the training friction torque set.

[0043] According to robotics, the dynamic equation of the robot joint satisfies the following formula:

[0044]

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

[0046] Since the operating environment of the surgical robot is low-speed motion, gravity torque and friction torque play a dominant role. Therefore, in the surgical robot scenario, the inertia torque and centripetal torque can be ignored.

[0047] When the joint moves at a uniform speed with a positive angular velocity, the above dynamic equation can be simplified to:

[0048]

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

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

[0051]

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

[0053] Since the gravitational torque is only related to the angle of the joint and has nothing to do with the angular velocity, G + (q) = G - (q). From this, we can get the friction torque τ f (q) satisfies the following formula:

[0054]

[0055] In an optional embodiment, a preset friction prediction model corresponding to the training joints and training angular velocities is constructed based on the training friction torque set, including: based on the training friction torque set, an untrained initial friction prediction model is trained to obtain a pre-trained preset friction prediction model corresponding to the training joints and training angular velocities.

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

[0057] Among them, the model architecture of each preset friction prediction model of different joints under different angular velocity conditions can be the same or different. Exemplarily, the model architecture of the preset friction prediction model of joint A at angular velocity A can be a residual network, the model architecture of the preset friction prediction model of joint B at angular velocity A can be a CNN network, and the model architecture of the preset friction prediction model of joint A at angular velocity B can be a DNN network.

[0058] Of course, the model architecture of each preset friction prediction model of the same joint under different angular velocity conditions may be set to be the same, or the model architecture of each preset friction prediction model of different joints under the same angular velocity condition may be set to be the same.

[0059] Specifically, each training angle in the training friction torque set is input into the untrained initial friction prediction model to obtain an output predicted friction torque set, and the loss function value is determined according to the predicted friction torque set and the training friction torque set. The model parameters of the initial friction prediction model are adjusted according to the loss function value until the training end condition is met, and the initial friction prediction model in the current iteration process is used as the preset friction prediction model that has completed the training.

[0060] Exemplarily, the loss function corresponding to the loss function value includes but is not limited to a square loss function, a logarithmic loss function, an exponential loss function, a mean square error loss function, a logistic regression loss function, a Huber loss function, a cross entropy loss function, or a Kullback-Leibler divergence loss function, etc.

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

[0062] Exemplarily, the target friction torque magnitude may be expressed as ||f||.

[0063] S140: Perform friction torque compensation on the joint to be measured according to the current angular velocity and the target friction torque.

[0064] In an optional embodiment, friction torque compensation is performed on the joint to be measured according to the current angular velocity and the target friction torque magnitude, including: determining the compensation torque according to the angular velocity direction corresponding to the current angular velocity and the target friction torque magnitude; and performing friction torque compensation on the joint to be measured according to the compensation torque.

[0065] In this embodiment, 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.

[0066] Exemplarily, the compensation torque F may 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 to be measured are summed to obtain the compensated motor torque.

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

[0069] Specifically, compensation coefficients corresponding to different angular velocity ranges are preset, and the compensation coefficient is determined according to the angular velocity range satisfied by the current angular velocity. Exemplarily, 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 is to build a friction prediction model for each joint in the surgical robot for different angular velocity conditions in advance, use the angle as the independent variable, predict the friction torque of the joint at different angles under the same angular velocity condition, and compensate the joint for friction torque based on the current angular velocity of the joint and the predicted friction torque. This solves the problem of poor compatibility between the traditional friction compensation method and the surgical robot, 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 flow chart of another friction compensation method for a surgical robot provided by 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, obtaining the current angular velocity and angle to be measured of the joint to be measured in the surgical robot.

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

[0074] S210-S220 in this embodiment are similar to those in the above embodiment. Figure 1 The S110 - S120 shown correspond to the same or similar ones, and are not described in detail in this embodiment.

[0075] In this embodiment, the target friction prediction model includes an input layer, a hidden layer, a summation 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 summation layer.

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

[0077] S230, outputting the input angle to be measured to each hidden module in the hidden layer through the input layer.

[0078] Exemplarily, the input layer may be composed of one neuron. The layer architecture of the input layer is not limited here, and can be customized according to actual needs.

[0079] Figure 3 A schematic diagram of a model architecture of a target friction prediction model provided by an embodiment of the present invention. Specifically, Figure 3 The "θ" in represents the angle to be measured.

[0080] S240: Determine the angle distance feature through the implicit module according to the angle to be measured and the training angle corresponding to the implicit module.

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

[0082]

[0083] Among them, x 0 Indicates the angle to be measured, x irepresents the training angle corresponding to the i-th hidden module, σ represents the smoothing factor, and d represents the distance function.

[0084] Exemplarily, the distance function includes but is not limited to the Euclidean distance function, the Manhattan distance function, the Chebyshev distance function, the cosine distance function, and the like.

[0085] See also Figure 3 , Figure 3 Taking the hidden layer including three hidden modules as an example for exemplary description, each hidden module outputs the angle distance features determined by itself to the first summing module and the second summing module in the summing layer respectively.

[0086] S250. Using a first summing module, according to the training friction torque corresponding to each training angle, weighted sum is performed on the angle distance features output by each implicit module to obtain a first friction feature.

[0087] Exemplarily, the first friction feature S 1 It is expressed by the following formula:

[0088]

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

[0090] S260, performing arithmetic summation on the angle distance features output by each implicit module through a second summing module to obtain a second friction feature.

[0091] In the second summing module, the weight of each angle distance feature is 1. For example, the second friction feature S 2 It is expressed by the following formula:

[0092]

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

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

[0095] Exemplarily, the target friction torque ||f|| is expressed by the following formula:

[0096]

[0097] In this embodiment, in the process of constructing 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 the initial friction prediction models with different smoothing factors.

[0098] S280: Perform friction torque compensation on the joint to be measured according to the current angular velocity and the target friction torque.

[0099] S280 in this embodiment is different from that in the above embodiment. Figure 1 The S140 shown corresponds to the same or similar steps, and will not be described in detail in this embodiment.

[0100] The technical solution of this embodiment is to set the target friction prediction model to include 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 concentrated training angles for 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 sum layer, thereby avoiding the problem of local optimal solution that may occur in the training process of traditional neural network models, and also avoiding the overfitting and underfitting of traditional neural network models, thereby ensuring the generalization ability of the target friction prediction model, thereby further improving the friction compensation effect of the surgical robot.

[0101] The following is an embodiment of the friction compensation device of the surgical robot provided in an embodiment of the present invention. The device and the friction compensation method of the surgical robot in the above-mentioned embodiment belong to the same inventive concept. For details not fully described in the embodiment of the friction compensation device of the surgical robot, reference can be made to the contents of the friction compensation method of the surgical robot in the above-mentioned embodiment.

[0102] Figure 4 The structural diagram of a friction compensation device of a surgical robot provided by one embodiment of the present invention is shown in FIG. Figure 4 As shown, the device includes: a module for obtaining an angle to be measured 310 , a module for obtaining a target friction prediction model 320 , a module for outputting a target friction torque magnitude 330 , and a module for compensating a friction torque 340 .

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

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

[0105] The target friction torque magnitude 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 magnitude;

[0106] The friction torque compensation module 340 is used to perform friction torque compensation on the joint to be measured according to the current angular velocity and the target friction torque.

[0107] The technical solution of this embodiment is to build a friction prediction model for each joint in the surgical robot for different angular velocity conditions in advance, use the angle as the independent variable, predict the friction torque of the joint at different angles under the same angular velocity condition, and perform friction torque compensation for each joint based on the current angular velocity of each joint and the predicted friction torque. 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.

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

[0109] A training motor torque set acquisition module is used to acquire the training motor torque set of each training joint in the surgical robot while the training joint is moving at a uniform speed at a training angular velocity; wherein the training motor torque set includes the positive motor torque and negative motor torque corresponding to the training joint and each training angle;

[0110] A training friction torque set construction module is used to construct a training friction torque set according to the training motor torque set; wherein the training friction torque set includes the training friction torque magnitude corresponding to the training joint and each training angle;

[0111] The preset friction prediction model building module is used to build a preset friction prediction model corresponding to the training joint and the training angular velocity according to the training friction torque set.

[0112] In an optional embodiment, the training angular velocity includes a positive angular velocity and a negative angular velocity. Accordingly, the training motor torque set acquisition module is specifically used for:

[0113] When the training joint moves at a uniform speed with a positive angular velocity, the motor torque of the training joint at each training angle is added to the training motor torque set as a positive motor torque;

[0114] When the training joint moves at a negative angular velocity at a uniform speed, the motor torque of the training joint at each training angle is added to the training motor torque set as a negative motor torque;

[0115] Among them, the positive angular velocity and the negative angular velocity are the same in magnitude but opposite in direction.

[0116] In an optional embodiment, the training friction torque set building module is specifically used to:

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

[0118] determining a differential motor torque between a positive motor torque and a negative motor torque;

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

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

[0121] 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 summing layer.

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

[0123] Through the input layer, the input angle to be measured is output to each hidden module in the hidden layer;

[0124] By using the implicit module, the angle distance feature is determined according to the angle to be measured and the training angle corresponding to the implicit module;

[0125] Through the first summing module, according to the training friction torque corresponding to each training angle, the angle distance feature output by each implicit module is weightedly summed to obtain the first friction feature;

[0126] Through the second summing module, the angle distance features output by each implicit module are arithmetically summed to obtain the second friction feature;

[0127] Through the output layer, the ratio between the first friction feature and the second friction feature is used as the target friction torque.

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

[0129] Determine the compensation torque according to the angular velocity direction corresponding to the current angular velocity and the target friction torque magnitude; wherein the torque direction of the compensation torque is the same as the angular velocity direction, and the magnitude of the compensation torque is the same as the target friction torque magnitude;

[0130] According to the compensation torque, the friction torque compensation is performed on the joint to be measured.

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

[0132] Figure 5 This is a schematic diagram of the structure of a surgical robot provided by 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-mentioned embodiment.

[0133] In this embodiment, the surgical robot includes: a control device 410 and at least one joint 420. Figure 5 , Figure 5 The following is an example of a surgical robot that contains three joints.

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

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

[0136] In an optional 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 a specific embodiment, when the data acquisition device only includes an angular velocity sensor, the control device 410 is specifically used to: use the angular velocity collected by the angular velocity sensor as the current angular velocity of the joint to be measured, and use the product of the running time of the joint to be measured and the current angular velocity as the measured angle 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: use the angular velocity of the joint to be measured set during operation as the current angular velocity of the joint to be measured, and use the angle collected by the angle sensor as the angle to be measured of the joint to be measured.

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

[0141] It is understandable that the current angular velocity can be obtained by performing statistical value calculation based on the angular velocity collected by the data acquisition device, the calculated angular velocity, and at least two of the angular velocities pre-set during operation, and the angle to be measured can be obtained by performing statistical value calculation based on the angle collected by the data acquisition device and the calculated angle. Exemplarily, the statistical value calculation includes but is not limited to the mean value calculation, the maximum value calculation, or the 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] On the basis of the above-mentioned embodiments, illustratively, the surgical robot may further include a robotic arm system, a chassis system, a power system, a circuit system, etc. The specific hardware structure of the surgical robot is not limited here.

[0144] Figure 6 A schematic diagram of the structure of a control device provided for 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, workstations, servers, blade servers, mainframe computers, and other suitable computers. The control device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, 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 examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0145] like Figure 6As shown, the control device 410 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor 11, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the ROM 12 or the computer program loaded from the storage unit 18 to the RAM 13. Various programs and data required for the operation of the control device 410 can also be stored in the RAM 13. The processor 11, the ROM 12, and the RAM 13 are connected to each other through the bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

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

[0147] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as the friction compensation method of the surgical robot provided in the above embodiments.

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

[0149] Various embodiments of the systems and techniques described above herein may 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: being implemented 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 special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] The computer program 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, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone 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 the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable storage medium. Examples of machine readable storage media may include electrical connections based on at least one line, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM), flash memories, optical fibers, portable compact disc read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

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

[0153] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a Local Area Network (LAN), a Wide Area Network (WAN), a blockchain network, and the Internet.

[0154] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0155] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0156] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A friction compensation method for a surgical robot, characterized in that: include: Obtain the current angular velocity and angle of the joint to be measured in the surgical robot; Acquire a pre-built target friction prediction model corresponding to the joint to be measured and the current angular velocity; Inputting the angle to be measured into the target friction prediction model to obtain the output target friction torque; Friction torque compensation is performed on the joint to be measured according to the current angular velocity and the target friction torque.

2. The method according to claim 1, characterized in that The method further comprises: For each training joint in the surgical robot, a training motor torque set of the training joint is obtained during the uniform motion of the training joint at a training angular velocity; wherein the training motor torque set includes a positive motor torque and a negative motor torque corresponding to each training angle of the training joint; According to the training motor torque set, a training friction torque set is constructed; wherein the training friction torque set includes the magnitude of the training friction torque corresponding to the training joint and each training angle; According to the training friction torque set, a preset friction prediction model corresponding to the training joint and the training angular velocity is constructed.

3. The method according to claim 2, characterized in that The training angular velocity includes a positive angular velocity and a negative angular velocity. Accordingly, when the training joint moves at a uniform speed at the training angular velocity, obtaining a training motor torque set of the training joint includes: 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 as the positive motor torque to the training motor torque set; During the uniform motion of the training joint at the 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; The positive angular velocity and the negative angular velocity are of the same magnitude but opposite directions.

4. The method according to claim 2, characterized in that: The step of constructing a training friction torque set according to the training motor torque set includes: 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 differential motor torque between the positive motor torque and the negative motor torque; The absolute value of half of the difference motor torque is added to the training friction torque set as the training friction torque magnitude corresponding to the training angle.

5. The method according to claim 2, characterized in that: The target friction prediction model includes 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 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 summation layer.

6. The method according to claim 5, characterized in that The summing layer includes a first summing module and a second summing module. Accordingly, the angle to be measured is input into the target friction prediction model to obtain the output target friction torque, including: Outputting the input angle to be measured to each hidden module in the hidden layer through the input layer; Determining an angle distance feature through the implicit module according to the angle to be measured and the training angle corresponding to the implicit module; By using the first summing module, according to the training friction torque corresponding to each training angle, weighted summation is performed on the angle distance features output by each implicit module to obtain a first friction feature; The second adding module performs arithmetic summation on the angle distance features output by each implicit module to obtain a second friction feature; Through the output layer, the ratio between the first friction feature and the second friction feature is used as the target friction torque.

7. The method according to any one of claims 1 to 6, characterized in that: The compensating the friction torque of the joint to be tested according to the current angular velocity and the target friction torque comprises: Determine a compensation torque according to the angular velocity direction corresponding to the current angular velocity and the target friction torque magnitude; wherein the torque direction of the compensation torque is the same as the angular velocity direction, and the magnitude of the compensation torque is the same as the target friction torque magnitude; According to the compensation torque, friction torque compensation is performed on the joint to be tested.

8. A friction compensation device for a surgical robot, characterized in that: include: The angle acquisition module to be measured is used to obtain the current angular velocity and angle to be measured of the joint to be measured in the surgical robot; A target friction prediction model acquisition module, used to acquire a pre-built target friction prediction model corresponding to the joint to be tested and the current angular velocity; A target friction torque magnitude output module, used for inputting the angle to be measured into the target friction prediction model to obtain an output target friction torque magnitude; The friction torque compensation module is used to perform friction torque compensation on the joint to be tested according to the current angular velocity and the target friction torque.

9. A surgical robot, characterized in that: The surgical robot comprises: a control device and at least one joint; The control device comprises 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, and the computer program is executed by the at least one processor so that the at least one processor can execute the friction compensation method of the surgical robot described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the friction compensation method for a surgical robot according to any one of claims 1 to 7 when executed.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the friction compensation method for a surgical robot according to any one of claims 1 to 7 is implemented.

Images