A surgical robot arm force control method, device, equipment and storage medium

Abstract

The present invention discloses a method, device, equipment and storage medium for force control of a surgical robot arm. The present invention relates to the field of mechanical control technology. The method comprises: obtaining the original data of the robot arm corresponding to the normal operation of the surgical robot arm. According to the original data of the robot arm and the target dynamics model corresponding to the surgical robot arm, determining the actual torque vector corresponding to the surgical robot arm. According to the original data of the robot arm and the target torque compensation model corresponding to the surgical robot arm, determining the compensation torque vector corresponding to the surgical robot arm. According to the actual torque vector and the compensation torque vector, determining the target torque vector, and compensating the actual torque vector of the surgical robot arm according to the target torque vector, so that each joint of the surgical arm is accurately positioned, thereby reducing the interference of non-fixed wiring harnesses, and effectively improving the robustness of the surgical arm force control.

Description

Technical Field

[0001] The present invention relates to the field of mechanical control technology, and in particular to a surgical robot arm force control method, device, equipment and storage medium. Background Art

[0002] With the rapid development of medical technology, surgical robots have become an indispensable part of the modern medical system due to their high stability and high safety. The control operation of the surgical arm is a manifestation of its intelligence.

[0003] The key to surgical arm force control is that the doctor drags its rotating joints, parallelogram joints and slides to make the surgical instruments reach the target position and posture.

[0004] However, during the actual operation process, the wiring harness on the surgical arm is loaded on the surgical arm in a non-fixed state. The non-fixed wiring harness will change with the movement of the surgical arm, which will interfere with the doctor's control of the surgical arm, thereby affecting the precise positioning of the joints of the surgical arm, causing the expected trajectory and positioning of the surgical arm to shift, thereby affecting the surgical treatment and failing to meet actual needs. Summary of the invention

[0005] The present invention provides a surgical robot arm force control method, device, equipment and storage medium, which compensate the actual torque vector of the surgical robot arm so that each joint of the surgical arm can be accurately positioned, thereby reducing the interference of non-fixed wiring harnesses and effectively improving the robustness of surgical arm force control.

[0006] According to one aspect of the present invention, a method for controlling the force of a surgical robot arm is provided. The method comprises:

[0007] Obtaining the original data of the surgical robot arm when the surgical robot arm is operating normally;

[0008] Determine the actual torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target dynamics model corresponding to the surgical robot arm, wherein the target dynamics model includes a surgical arm dynamics equation and dynamics parameters, and the dynamics parameters are determined when the harness of the surgical robot arm is not fixed;

[0009] Determine a compensation torque vector corresponding to the surgical robot arm according to the original data of the robot arm and a target torque compensation model corresponding to the surgical robot arm;

[0010] A target torque vector is determined according to the actual torque vector and the compensation torque vector, and the surgical robot arm is controlled according to the target torque vector.

[0011] According to another aspect of the present invention, a surgical robot arm force control device is provided. The device comprises:

[0012] A robot arm data acquisition module is used to obtain the original robot arm data corresponding to the normal operation of the surgical robot arm;

[0013] an actual torque vector determination module, used to determine the actual torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target dynamics model corresponding to the surgical robot arm, wherein the target dynamics model includes a surgical arm dynamics equation and dynamics parameters, and the dynamics parameters are determined when the harness of the surgical robot arm is not fixed;

[0014] A compensation torque vector determination module, used to determine the compensation torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target torque compensation model corresponding to the surgical robot arm;

[0015] The target torque vector determination module is used to determine the target torque vector according to the actual torque vector and the compensation torque vector, and control the surgical robot arm according to the target torque vector.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed 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 surgical robot arm force control method described in any embodiment of the present invention.

[0020] According to another aspect 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 surgical robot arm force control method described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention is to obtain the original data of the robotic arm corresponding to the normal operation of the surgical robotic arm. According to the original data of the robotic arm and the target dynamics model corresponding to the surgical robotic arm, the actual torque vector corresponding to the surgical robotic arm is determined. According to the original data of the robotic arm and the target torque compensation model corresponding to the surgical robotic arm, the compensation torque vector corresponding to the surgical robotic arm is determined. According to the actual torque vector and the compensation torque vector, the target torque vector is determined, and the surgical robotic arm is controlled according to the target torque vector, which solves the problem of interference of the non-fixed wiring harness on the running trajectory of the robotic arm. By determining the compensation torque vector to compensate for the actual torque vector of the surgical robotic arm, each joint of the surgical arm can be accurately positioned, reducing the interference of the non-fixed wiring harness, and effectively improving the robustness of the surgical arm force control.

[0022] 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

[0023] 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.

[0024] Figure 1 is a flow chart of a surgical robot arm force control method provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of a surgical robot arm force control method provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a structural diagram of a surgical robot arm force control device provided according to Embodiment 3 of the present invention;

[0027] Figure 4 It is a structural schematic diagram of an electronic device for implementing the surgical robot arm force control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] 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.

[0029] It should be noted that the terms "first", "second", 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 A flowchart of a surgical robot arm force control method is provided for the first embodiment of the present invention. This embodiment is applicable to the case of surgical robot arm torque compensation. The method can be executed by a surgical robot arm force control device. The surgical robot arm force control device can be implemented in the form of hardware and / or software. The surgical robot arm force control device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S101, obtaining original data of the surgical robot arm corresponding to the normal operation of the surgical robot arm.

[0033] The original data of the robot arm may refer to the operation data when the harness of the surgical robot arm is in a non-fixed state. It should be noted that under normal conditions, the harness state of the surgical robot arm is in a non-fixed state, and the shape of the harness changes with the movement of the robot arm. The change of the harness shape affects the precise positioning of the surgical robot arm.

[0034] For example, the raw data of the robot arm may include joint encoder values, motor output torque values, and movement speed. The joint encoder values ​​of the robot arm are mainly used to accurately measure and control the position, speed, and acceleration of the robot arm. The motor output torque value is of great significance for motor-driven applications, especially in the field of precision control. The motor output torque refers to the torsional force that can be applied to the motor shaft, which directly affects the working capacity and efficiency of the equipment.

[0035] S102: Determine an actual torque vector corresponding to the surgical robot arm according to the original data of the robot arm and a target dynamics model corresponding to the surgical robot arm.

[0036] The actual torque vector may refer to the torque vector of the surgical robot arm under the influence of the non-fixed wiring harness. The target dynamics model includes a surgical arm dynamics equation and dynamics parameters.

[0037] Exemplarily, the dynamic parameters are determined when the surgical robot arm harness is not fixed. The surgical arm dynamic equation calculates the surgical arm kinematics positive solution based on the kinematic parameters and is constructed using methods such as the Newton-Euler method.

[0038] Specifically, conventional mechanical operation data is input into a pre-obtained target dynamics model to perform torque calculation, thereby obtaining an actual torque vector of the surgical robot arm under the influence of the non-fixed wiring harness.

[0039] Exemplarily, the process of constructing the dynamic equation of the surgical arm includes: determining the local joint coordinate system corresponding to each joint in the surgical robot arm; determining the end posture information of the end joint of the surgical robot arm in three-dimensional space based on the local joint coordinate system; and determining the dynamic equation of the surgical arm based on the end posture information based on the Newton-Euler method.

[0040] Among them, the local coordinate system of the joint may refer to the coordinate system established by the joint of the surgical robot arm itself. The end posture information may refer to the posture of the end of the surgical robot arm in the global coordinate system established by the robot arm. The Newton-Euler method is a recursive algorithm used to calculate the dynamic equations of a multi-rigid body system. This method is based on Newton's second law (force equals mass times acceleration) and Euler's law (describing the relationship between the torque and angular acceleration of a rigid body when it rotates around its center of mass). It starts from the end of the system and recursively calculates forward step by step (toward the base) until the entire system is analyzed.

[0041] Specifically, for each joint of the surgical robot arm, a local coordinate system is constructed with each joint itself, and a global coordinate system is constructed with the surgical robot arm. The position and posture changes of each joint relative to the previous joint are determined, and each joint is transformed in turn using a homogeneous transformation matrix, so as to cumulatively calculate the terminal posture information of the terminal joint of the surgical robot arm relative to the base in three-dimensional space. Using the Newton-Euler method, based on the terminal posture information, starting from the terminal joint of the surgical robot arm, all joints are traversed, and the motion equation of each connecting rod is calculated in turn until the base is reached. For each connecting rod, its motion equation is calculated, including inertial force, Coriolis force, centrifugal force, gravity and friction. The velocity, acceleration and torque of the previous connecting rod are used to calculate the dynamic equation of the current connecting rod, and then the dynamic equation of the surgical arm is determined.

[0042] Exemplarily, the surgical arm dynamics equation is:

[0043]

[0044] in: is the torque vector when the harness is fixed, i.e., the actual torque vector; is the joint position, Joint speed, is the joint acceleration; is the mass matrix; It is the centrifugal force and the Coriolis force; is the gravity term; is the friction term.

[0045] Exemplarily, the process of determining the dynamic parameters includes: acquiring the robot arm operation data of the surgical robot arm when the surgical robot arm harness is not fixed and the surgical robot arm operates based on a preset trajectory curve; and determining the dynamic parameters based on the robot arm operation data based on least squares fitting.

[0046] Among them, the preset trajectory curve may refer to a preset surgical robot arm motion trajectory curve, and the preset trajectory curve includes the complete motion range of each joint. It should be noted that during the experiment or simulation process, the motion trajectory of the surgical arm must first be defined. This usually means planning a series of predetermined joint angles and positions so that the surgical arm can move along a certain path. This trajectory should cover the maximum motion range of all joints of the surgical arm to ensure a comprehensive understanding of the dynamic characteristics of the surgical arm in the entire workspace.

[0047] Specifically, when the harness of the surgical robot arm is not fixed and the surgical robot arm is running based on a preset trajectory curve, the robot arm operation data of the surgical robot arm is obtained, and the robot arm operation data is used to estimate the unknown parameters in the surgical arm dynamics model. One of the commonly used parameter identification methods is "least squares fitting", which is a statistical method that finds the optimal parameter value, i.e., the dynamic parameter, by minimizing the residual sum of squares between the observed data and the model prediction value. Then, based on the dynamic parameters and the surgical arm dynamics equation, a target dynamics model is constructed. The target dynamics model can reflect the behavioral characteristics of the surgical robot arm under different motion states, which plays a vital role in designing the controller of the surgical arm, achieving accurate force feedback, and improving the operation accuracy during surgery.

[0048] S103 . Determine a compensation torque vector corresponding to the surgical robot arm according to the original data of the robot arm and a target torque compensation model corresponding to the surgical robot arm.

[0049] Among them, the target torque compensation model is a neural network model pre-trained according to the preset torque compensation model, which can be used to determine the compensation torque vector. In addition, the compensation torque vector can refer to the torque required for the surgical robot arm to reach the expected position point at the actual position point. In other words, the surgical robot arm can be controlled by the actual torque vector and the compensation torque vector so that the surgical robot arm can run to the expected position point.

[0050] Specifically, the original data of the robotic arm is input into the pre-trained target torque compensation model for torque compensation prediction. According to the output of the target torque compensation model, the compensation torque vector can be obtained. The target torque compensation model can improve the accuracy of determining the compensation torque vector, thereby achieving precise control of the surgical robotic arm.

[0051] S104. Determine a target torque vector according to the actual torque vector and the compensation torque vector, and control the surgical robot arm according to the target torque vector.

[0052] The target torque vector may refer to the torque vector required for the surgical robot to reach the expected position. Specifically, the target torque vector is determined by the actual torque vector and the compensation torque vector, and the determination method may be addition and summation, subtraction and difference, or weighted summation, etc. It should be noted that the technical solution of the embodiment of the present invention does not limit the determination method, and it can be selected according to actual needs or designs.

[0053] After determining the target torque vector, the controller of the surgical robot arm performs torque control on the robot arm according to the target torque vector so that the surgical robot arm reaches the expected position point.

[0054] Exemplarily, the dynamic equation of the surgical robot arm to resist wire harness interference is:

[0055]

[0056] in: is the torque vector of the harness when it is in a non-fixed state, i.e., the target torque vector; is the compensation torque vector related to position, velocity and acceleration; It is the torque vector when the harness is fixed, that is, the actual torque vector.

[0057] The technical solution of the embodiment of the present invention is to obtain the original data of the robotic arm corresponding to the normal operation of the surgical robotic arm. According to the original data of the robotic arm and the target dynamics model corresponding to the surgical robotic arm, the actual torque vector corresponding to the surgical robotic arm is determined. According to the original data of the robotic arm and the target torque compensation model corresponding to the surgical robotic arm, the compensation torque vector corresponding to the surgical robotic arm is determined. According to the actual torque vector and the compensation torque vector, the target torque vector is determined, and the surgical robotic arm is controlled according to the target torque vector, which solves the problem of interference of the non-fixed wiring harness on the running trajectory of the robotic arm. By determining the compensation torque vector to compensate for the actual torque vector of the surgical robotic arm, each joint of the surgical arm can be accurately positioned, reducing the interference of the non-fixed wiring harness, and effectively improving the robustness of the surgical arm force control.

[0058] Embodiment 2

[0059] Figure 2 This is a flow chart of a surgical robot arm force control method provided in the second embodiment of the present invention. Based on the above embodiments, this embodiment further refines the training of the target torque compensation model. Figure 2 As shown, the method includes:

[0060] S201. Acquire sample robotic arm data and sample compensation torque corresponding to the sample robotic arm data.

[0061] The sample compensation torque is the torque difference between the harness of the surgical robot arm in the non-fixed state and the fixed state. It should be noted that when the harness of the surgical robot arm is in the fixed state, the harness will not affect the positioning of the surgical robot arm, that is, when the harness is in the fixed state, it can accurately reach the expected position point. In other words, the sample compensation torque is the torque required for the surgical robot arm to reach the expected position point at the sample position point.

[0062] Specifically, sample robotic arm data is collected. For example, historical robotic arm data may be subjected to noise reduction processing using a Kalman filter or other method to obtain sample robotic arm data.

[0063] Exemplarily, determining the sample compensation torque includes: determining a first sample torque vector corresponding to the surgical robot arm when the surgical robot arm harness is not fixed; determining a second sample torque vector corresponding to the surgical robot arm when the surgical robot arm harness is fixed; and determining the sample compensation torque based on the first sample torque vector and the second sample torque vector.

[0064] The first sample torque vector may refer to a sample torque vector when the harness of the surgical robot is in a non-fixed state. The second sample torque vector may refer to a sample torque vector when the harness of the surgical robot is in a fixed state. In practice, the difference between the first sample torque vector and the second sample torque vector is determined as the sample compensation torque.

[0065] Exemplarily, determining the second sample torque vector corresponding to the surgical robot arm includes: acquiring sample robot arm data corresponding to the surgical robot arm when the surgical robot arm harness is fixed, and determining the second sample torque vector according to the sample robot arm data and a sample dynamics model corresponding to the surgical robot arm.

[0066] The sample robot arm data may be operation data obtained by the operation of the surgical robot arm based on a preset trajectory curve when the harness is fixed. The sample robot arm data also includes a surgical arm dynamics equation and sample model parameters.

[0067] It should be noted that the determination process of the surgical arm dynamics equation is the same as the determination process in the above-mentioned embodiments, and the embodiments of the present invention will not be repeated. The sample model parameters are determined using the least squares fitting method and the operating parameters when the surgical robot harness is fixed. The process of determining the sample model parameters is similar to the process of determining the dynamic parameters. The process of determining the sample model parameters can be that when the surgical robot harness is fixed and the surgical robot operates based on a preset trajectory curve, the operating data of the surgical robot is obtained, and the sample model parameters are determined based on the least squares fitting.

[0068] Specifically, the acquired sample robotic arm data is input into the sample dynamics model. Based on the output of the sample dynamics model, a second sample torque vector can be obtained. Based on the second sample torque vector, a sample compensation torque can be determined, and then a target torque compensation model is trained according to the sample compensation torque.

[0069] S202: Input the sample robot arm data into a preset torque compensation model to perform torque compensation prediction, and obtain an output prediction result based on the output of the preset torque compensation model.

[0070] The preset torque compensation model may be a feedforward neural network, a recurrent neural network or a generative adversarial network. The output prediction result may refer to the output result of the preset torque compensation model during training.

[0071] Specifically, the sample robot arm data is input into a preset torque compensation model to perform torque compensation prediction, and the output of the preset torque compensation model is determined as the output prediction result.

[0072] S203, determining a training error based on the output prediction result and the sample compensation torque, and back-propagating the training error to the preset torque compensation model to adjust network parameters in the preset torque compensation model.

[0073] Specifically, based on the training function, the training error can be determined according to the output prediction result and the sample compensation torque, and the training error can be back-propagated to the preset torque compensation model to adjust the network parameters in the preset torque compensation model.

[0074] S204: When a preset convergence condition is met, determine that the training of the preset torque compensation model is completed, and obtain a target torque compensation model.

[0075] Exemplarily, the preset convergence condition may be that the number of iterations reaches a preset number or the training error converges.

[0076] Specifically, when the preset convergence condition is met, it is determined that the training of the preset torque compensation model is completed, and at this time, the preset torque compensation model that has completed the training can be used as the target torque compensation model.

[0077] S205: Acquire original data of the surgical robot arm corresponding to the normal operation of the surgical robot arm.

[0078] S206: Determine an actual torque vector corresponding to the surgical robotic arm according to the original data of the robotic arm and the target dynamics model corresponding to the surgical robotic arm.

[0079] S207: Determine a compensation torque vector corresponding to the surgical robot arm according to the original data of the robot arm and a target torque compensation model corresponding to the surgical robot arm.

[0080] S208. Determine a target torque vector according to the actual torque vector and the compensation torque vector, and control the surgical robot arm according to the target torque vector.

[0081] The technical solution of the embodiment of the present invention can ensure the accuracy of the target torque compensation model in predicting the compensation torque vector by utilizing sample robotic arm data and sample compensation torque for model training, and adjust the network parameters in the preset torque compensation model according to the training error, so as to improve the accuracy of determining the target torque vector, and further ensure the accuracy of controlling the surgical robotic arm.

[0082] Embodiment 3

[0083] Figure 3 This is a schematic diagram of the structure of a surgical robot arm force control device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0084] The robot data acquisition module 301 is used to acquire the original robot data corresponding to the normal operation of the surgical robot;

[0085] An actual torque vector determination module 302 is used to determine the actual torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target dynamics model corresponding to the surgical robot arm, wherein the target dynamics model includes a surgical arm dynamics equation and dynamics parameters, and the dynamics parameters are determined when the harness of the surgical robot arm is not fixed;

[0086] A compensation torque vector determination module 303, used to determine the compensation torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target torque compensation model corresponding to the surgical robot arm;

[0087] The target torque vector determination module 304 is used to determine the target torque vector according to the actual torque vector and the compensation torque vector, and control the surgical robot arm according to the target torque vector.

[0088] The technical solution of the embodiment of the present invention is to obtain the original data of the robotic arm corresponding to the normal operation of the surgical robotic arm. According to the original data of the robotic arm and the target dynamics model corresponding to the surgical robotic arm, the actual torque vector corresponding to the surgical robotic arm is determined. According to the original data of the robotic arm and the target torque compensation model corresponding to the surgical robotic arm, the compensation torque vector corresponding to the surgical robotic arm is determined. According to the actual torque vector and the compensation torque vector, the target torque vector is determined, and the surgical robotic arm is controlled according to the target torque vector, which solves the problem of interference of the non-fixed wiring harness on the running trajectory of the robotic arm. By determining the compensation torque vector to compensate for the actual torque vector of the surgical robotic arm, each joint of the surgical arm can be accurately positioned, reducing the interference of the non-fixed wiring harness, and effectively improving the robustness of the surgical arm force control.

[0089] Optionally, the device further comprises a kinetic equation building module, wherein:

[0090] Kinetic equation building blocks for:

[0091] Determine a joint local coordinate system corresponding to each joint in the surgical robot arm;

[0092] Determining the terminal posture information of the terminal joint of the surgical robot arm in three-dimensional space according to the local coordinate system of the joint;

[0093] Based on the Newton-Euler method, the dynamic equation of the surgical arm is determined according to the end posture information.

[0094] Optionally, the device further comprises an identification model parameter determination module.

[0095] The identification model parameter determination module is specifically used for:

[0096] When the surgical robot arm harness is not fixed and the surgical robot arm operates based on a preset trajectory curve, acquiring robot arm operation data of the surgical robot arm;

[0097] Based on the least squares fitting, the dynamic parameters are determined according to the robot operation data.

[0098] Optionally, the device further comprises a torque compensation model training module.

[0099] The torque compensation model training module is specifically used for:

[0100] Acquire sample robotic arm data and a sample compensation torque corresponding to the sample robotic arm data, wherein the sample compensation torque is a torque difference between a harness of the surgical robotic arm in a non-fixed state and a fixed state;

[0101] Inputting the sample manipulator data into a preset torque compensation model to perform torque compensation prediction, and obtaining an output prediction result based on the output of the preset torque compensation model;

[0102] Determine a training error based on the output prediction result and the sample compensation torque, and back-propagate the training error to the preset torque compensation model to adjust network parameters in the preset torque compensation model;

[0103] When the preset convergence condition is met, it is determined that the training of the preset torque compensation model is completed, and the target torque compensation model is obtained.

[0104] Optionally, the identification model parameter determination module includes a sample compensation torque determination unit.

[0105] The sample compensation torque determination unit comprises:

[0106] A first determining subunit, configured to determine a first sample torque vector corresponding to the surgical robot arm when the harness of the surgical robot arm is not fixed;

[0107] A second determining subunit, configured to determine a second sample torque vector corresponding to the surgical robot arm when the harness of the surgical robot arm is fixed;

[0108] The sample compensation torque determination subunit is used to determine the sample compensation torque according to the first sample torque vector and the second sample torque vector.

[0109] Optionally, the second determining subunit is specifically configured to:

[0110] When the surgical robot arm harness is fixed, obtaining sample robot arm data corresponding to the surgical robot arm;

[0111] The second sample torque vector is determined according to the sample robotic arm data and a sample dynamics model corresponding to the surgical robotic arm.

[0112] Optionally, the sample dynamics model includes the surgical arm dynamics equation and sample model parameters, and the sample model parameters are determined using a least squares fitting method and operating parameters when the surgical robot arm harness is fixed.

[0113] The surgical robot arm force control device provided in the embodiment of the present invention can execute the surgical robot arm force control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0114] Embodiment 4

[0115] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, 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.

[0116] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11 in communication, 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, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the random access memory (RAM) 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the read-only memory (ROM) 12, and the random access memory (RAM) 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0117] A number of components in the electronic device 10 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 electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0118] The processor 11 may be a variety of general and / or dedicated 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, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for surgical robot arm force control.

[0119] In some embodiments, the method surgical robot arm force control can 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 can be loaded and / or installed on the electronic device 10 via a read-only memory (ROM) 12 and / or a communication unit 19. When the computer program is loaded into a random access memory (RAM) 13 and executed by the processor 11, one or more steps of the method surgical robot arm force control described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the method surgical robot arm force control in any other appropriate manner (e.g., by means of firmware).

[0120] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can 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 can 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.

[0121] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may 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 may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0122] In the context of the present invention, 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 signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] 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 client and server relationship 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 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 VPS services.

[0124] 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 surgical robot arm force control method, characterized in that: include: Acquire original data of the surgical robot arm corresponding to the normal operation of the surgical robot arm, wherein, during the normal operation, the harness state of the surgical robot arm is a non-fixed state; Determine the actual torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target dynamics model corresponding to the surgical robot arm, wherein the target dynamics model includes a surgical arm dynamics equation and dynamics parameters, and the dynamics parameters are determined when the harness of the surgical robot arm is not fixed; Determine a compensation torque vector corresponding to the surgical robot arm according to the original data of the robot arm and a target torque compensation model corresponding to the surgical robot arm; Determining a target torque vector according to the actual torque vector and the compensation torque vector, and controlling the surgical robot arm according to the target torque vector; The training process of the target torque compensation model includes: Acquire sample robotic arm data and a sample compensation torque corresponding to the sample robotic arm data, wherein the sample compensation torque is a torque difference between a harness of the surgical robotic arm in a non-fixed state and a fixed state; Inputting the sample manipulator data into a preset torque compensation model for torque compensation prediction, and obtaining an output prediction result based on the output of the preset torque compensation model, wherein the preset torque compensation model includes a feedforward neural network, a recurrent neural network, and a generative adversarial network; Determine a training error based on the output prediction result and the sample compensation torque, and back-propagate the training error to the preset torque compensation model to adjust network parameters in the preset torque compensation model; When the preset convergence condition is met, it is determined that the training of the preset torque compensation model is completed, and the target torque compensation model is obtained.

2. The surgical robot arm force control method according to claim 1, characterized in that: The construction process of the surgical arm dynamics equation includes: Determine a joint local coordinate system corresponding to each joint in the surgical robot arm; Determining the terminal posture information of the terminal joint of the surgical robot arm in three-dimensional space according to the local coordinate system of the joint; Based on the Newton-Euler method, the dynamic equation of the surgical arm is determined according to the end posture information.

3. The surgical robot arm force control method according to claim 1, characterized in that: The process of determining the kinetic parameters includes: When the surgical robot arm harness is not fixed and the surgical robot arm operates based on a preset trajectory curve, acquiring robot arm operation data of the surgical robot arm; Based on the least squares fitting, the dynamic parameters are determined according to the robot operation data.

4. The surgical robot arm force control method according to claim 1, characterized in that: Determining the sample compensation torque includes: In the case where the harness of the surgical robot arm is not fixed, determining a first sample torque vector corresponding to the surgical robot arm; When the harness of the surgical robot arm is fixed, determining a second sample torque vector corresponding to the surgical robot arm; The sample compensation torque is determined according to the first sample torque vector and the second sample torque vector.

5. The surgical robot arm force control method according to claim 4, characterized in that: The determining of a second sample torque vector corresponding to the surgical robot arm comprises: When the surgical robot arm harness is fixed, obtaining sample robot arm data corresponding to the surgical robot arm; The second sample torque vector is determined according to the sample robotic arm data and a sample dynamics model corresponding to the surgical robotic arm.

6. The surgical robot arm force control method according to claim 5, characterized in that: The sample dynamics model includes the surgical arm dynamics equation and sample model parameters, and the sample model parameters are determined by using a least squares fitting method and operating parameters when the surgical robot arm harness is fixed.

7. A surgical robot arm force control device, characterized in that: include: A robot arm data acquisition module, used to acquire original robot arm data corresponding to the normal operation of the surgical robot arm, wherein, during the normal operation, the harness state of the surgical robot arm is a non-fixed state; an actual torque vector determination module, used to determine the actual torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target dynamics model corresponding to the surgical robot arm, wherein the target dynamics model includes a surgical arm dynamics equation and dynamics parameters, and the dynamics parameters are determined when the harness of the surgical robot arm is not fixed; A compensation torque vector determination module, used to determine the compensation torque vector corresponding to the surgical robot arm according to the original data of the robot arm and the target torque compensation model corresponding to the surgical robot arm; a target torque vector determination module, used to determine a target torque vector according to the actual torque vector and the compensation torque vector, and control the surgical robot arm according to the target torque vector; Torque compensation model training module, used for: Acquire sample robotic arm data and a sample compensation torque corresponding to the sample robotic arm data, wherein the sample compensation torque is a torque difference between a harness of the surgical robotic arm in a non-fixed state and a fixed state; Inputting the sample manipulator data into a preset torque compensation model for torque compensation prediction, and obtaining an output prediction result based on the output of the preset torque compensation model, wherein the preset torque compensation model includes a feedforward neural network, a recurrent neural network, and a generative adversarial network; Determine a training error based on the output prediction result and the sample compensation torque, and back-propagate the training error to the preset torque compensation model to adjust network parameters in the preset torque compensation model; When the preset convergence condition is met, it is determined that the training of the preset torque compensation model is completed, and the target torque compensation model is obtained.

8. An electronic device, characterized in that: The electronic 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 surgical robot arm force control method according to any one of claims 1 to 6.

9. 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 surgical robot arm force control method according to any one of claims 1 to 6 when executed.

Images