Surgical robot gravity compensation method, device and equipment and storage medium

Abstract

The invention discloses a surgical robot gravity compensation method, device and equipment and a storage medium. The method comprises the steps that joint data information corresponding to all mechanical joints of the surgical robot is obtained, and the joint data information at least comprises joint angle information and gravity torque information corresponding to the joint angle information. According to the joint data information and a target compensation network model, gravity compensation information corresponding to the mechanical joints is determined, and the target compensation network model is obtained by training a pre-established neural network model according to joint sample data. And according to the gravity compensation information, performing gravity compensation on each mechanical joint of the surgical robot so as to realize accurate measurement and effective compensation on the gravitational torque of each mechanical joint of the surgical robot and provide more accurate and stable operation performance for the surgical robot.

Description

Technical Field

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

[0002] Surgical robots play an increasingly important role in the field of modern medicine. Their high precision, high flexibility and low invasiveness make the surgical process safer and more effective. However, when performing complex surgical operations, surgical robots may produce motion errors due to the influence of dynamic characteristics, affecting the accuracy and safety of the surgery. Therefore, how to compensate for the dynamics of surgical robots has become a hot topic and difficulty in current research.

[0003] As an important component of robot dynamics, gravity torque is a factor that cannot be ignored in the design and operation of surgical robots. It not only affects the robot's motion accuracy and dynamic performance, but may also have a negative impact on the surgical effect. Summary of the invention

[0004] The present invention provides a surgical robot gravity compensation method, device, equipment and storage medium to achieve accurate measurement and effective compensation of the gravity torque of each mechanical joint of the surgical robot, providing the surgical robot with more accurate and stable operating performance.

[0005] According to one aspect of the present invention, a method for gravity compensation of a surgical robot is provided. The method comprises:

[0006] Acquire joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes joint angle information and gravity torque information corresponding to the joint angle information;

[0007] Determine the gravity compensation information corresponding to each of the mechanical joints according to the joint data information and the target compensation network model, wherein the target compensation network model is obtained by training a pre-established neural network model according to the joint sample data;

[0008] Gravity compensation is performed on each mechanical joint of the surgical robot according to the gravity compensation information.

[0009] According to another aspect of the present invention, a surgical robot gravity compensation device is provided. The device comprises:

[0010] A gravity torque acquisition module, used to acquire joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes joint angle information and gravity torque information corresponding to the joint angle information;

[0011] A compensation information determination module, used to determine the gravity compensation information corresponding to each of the mechanical joints according to the joint data information and a target compensation network model, wherein the target compensation network model is obtained by training a pre-established neural network model according to the joint sample data;

[0012] The gravity torque compensation module is used to perform gravity compensation on each mechanical joint of the surgical robot according to the gravity compensation information.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] 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 gravity compensation method described in any embodiment of the present invention.

[0017] 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 gravity compensation method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention is to obtain the joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes the joint angle information and the gravity torque information corresponding to the joint angle information. According to the joint data information and the target compensation network model, the gravity compensation information corresponding to each mechanical joint is determined, wherein the target compensation network model is obtained by training a pre-established neural network model based on joint sample data. According to the gravity compensation information, gravity compensation is performed on each mechanical joint of the surgical robot, which can significantly improve the positioning accuracy and dynamic response capability of the surgical robot, and improve the adaptability and robustness of the surgical robot system.

[0019] 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

[0020] 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.

[0021] Figure 1 is a flow chart of a surgical robot gravity compensation method provided according to Embodiment 1 of the present invention;

[0022] Figure 2 is a schematic diagram of the structure of a target compensation network model provided according to the first embodiment of the present invention;

[0023] Figure 3 is a flow chart of a surgical robot gravity compensation method provided according to Embodiment 2 of the present invention;

[0024] Figure 4 is a structural diagram of a surgical robot gravity compensation device provided according to Embodiment 3 of the present invention;

[0025] Figure 5 It is a structural schematic diagram of an electronic device for implementing the surgical robot gravity compensation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] 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.

[0028] Embodiment 1

[0029] Figure 1 This is a flowchart of a surgical robot gravity compensation method provided in the first embodiment of the present invention. This embodiment is applicable to the case of performing gravity compensation on the mechanical arm of a surgical robot. The method can be performed by a surgical robot gravity compensation device. The surgical robot gravity compensation device can be implemented in the form of hardware and / or software. The surgical robot gravity compensation device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S101, obtaining joint data information corresponding to each mechanical joint of the surgical robot.

[0031] The joint data information may refer to parameter information of each joint of the surgical robot to be subjected to gravity compensation. Exemplarily, the joint data information at least includes joint angle information and gravity torque information corresponding to the joint angle information.

[0032] Specifically, the joint data information of each mechanical joint of the surgical robot can be collected through sensors arranged in the surgical robot.

[0033] Exemplarily, the method of obtaining joint data information corresponding to each mechanical joint of the surgical robot includes: obtaining joint angle information corresponding to each mechanical joint of the surgical robot and joint torque information corresponding to the joint angle information, and determining the joint torque information as the gravity torque information; fusing the joint angle information and the gravity torque information to obtain joint data information.

[0034] It needs to be explained that according to robotics, the dynamic equation of the robot joint is:

[0035]

[0036] Among them, τ m is the joint torque, q is the current angle of each joint, is the moment of inertia, is the centripetal torque, and G(q) is the gravity torque. Since the main hand of the surgical robot is manually controlled by the doctor, the common operating environment is low-speed motion, and the gravity torque plays a dominant role. The data collection process of the gravity torque is low-speed uniform motion. Based on this premise, it can be known that each joint is in uniform motion, so and then Each joint moves at a low speed. and then So, τ m ≈G(q), that is, the joint torque at this time is the gravity torque.

[0037] Specifically, when the surgical robot is powered, the surgical robot is controlled to cover the entire workspace according to a pre-designed low-speed uniform motion trajectory. Exemplarily, in the process of covering the entire surgical robot workspace, data is collected according to a preset sampling period (e.g., the sampling period is set to 0.2s). The joint torque information of each joint is recorded, and the joint torque information is determined as the gravity torque information G(q), and the corresponding angle value q of each joint is recorded at the same time. The joint angle value and the corresponding gravity torque data set are stored, so that the joint data information (X i , Y i ), where X i is the collected angle value of each joint, Y i It is the gravitational moment value corresponding to this angle value.

[0038] S102. Determine gravity compensation information corresponding to each of the mechanical joints according to the joint data information and the target compensation network model.

[0039] The target compensation network model is obtained by training a pre-established neural network model according to the joint sample data. Exemplarily, the target compensation network model can be a generalized regression network model. The gravity compensation information can be a torque compensation value of each mechanical joint or a current compensation value of each mechanical joint.

[0040] Specifically, the joint data information is input into the target compensation network model for gravity compensation calculation, and gravity compensation information is obtained according to the output of the target compensation network model. The target compensation network model can accurately obtain gravity compensation information, thereby improving the accuracy of gravity compensation for the surgical robot.

[0041] Exemplarily, the target compensation network model includes an input layer, a hidden layer, a summing layer and an output layer. Determining the gravity compensation information corresponding to each of the mechanical joints according to the joint data information and the target compensation network model includes:

[0042] The input layer receives the joint angle information corresponding to each of the mechanical joints in the joint data information; the hidden layer determines the Gaussian kernel function value between each joint angle information and all the joint angle information; the sum layer determines the sum of the angle Gaussian kernel functions according to all the Gaussian kernel function values, and determines the sum of the weighted Gaussian kernel functions according to all the Gaussian kernel function values ​​and the gravity torque information corresponding to each of the mechanical joints; the output layer determines the gravity compensation information corresponding to each of the mechanical joints according to the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions.

[0043] Figure 2 Schematic diagram of the structure of the target compensation network model provided by the embodiment of the present invention. Figure 2 As shown, x M It may refer to the joint angle information corresponding to the Mth mechanical joint in the input layer. It can refer to the Gaussian kernel function value corresponding to the Nth group of joint angle information in the hidden layer. N It can refer to the gravity torque matrix corresponding to the Nth group of joint angle information in the summation layer, and the gravity torque matrix includes the gravity torque matrix corresponding to each joint angle information. Mul refers to the sum of weighted Gaussian kernel functions in the summation layer. Div refers to the sum of angle Gaussian kernel functions in the summation layer. g M It may refer to the gravity compensation information corresponding to the Mth mechanical joint in the output layer.

[0044] It should be noted that if Figure 2 As shown in , the number of neurons in the input layer is equal to the dimension of the input vector. Here, the input is the angle value X of each joint specified. The hidden layer is composed of nodes directly connected to the input node. One hidden node corresponds to one sampling point. Therefore, its number is equal to the number of sampling points. The summation layer is to perform linear summation on the output of the hidden layer. The output layer is to compare the two outputs of the summation layer to obtain the final output G. Here, the output is the gravity torque of each joint when each joint angle is specified. The target compensation network model has a great influence on the model performance by adjusting the appropriate smoothing factor to ensure the width of the Gaussian kernel function. The appropriate smoothing factor can ensure the accuracy of the target compensation network model and the generalization ability of the network. The smoothing factor is crucial to the performance of the target compensation network model. If the smoothing factor is too small, the model may be overfitted; if the smoothing factor is too large, the model may be underfitted. Usually, the selection of the smoothing factor needs to be determined by methods such as cross-validation to find the best model performance.

[0045] Exemplarily, determining the gravity compensation information corresponding to each of the mechanical joints according to the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions through the output layer includes:

[0046] The output layer determines the sum ratio between the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions, and determines the gravity compensation information corresponding to each of the mechanical joints according to the sum ratio.

[0047] Specifically, in the target compensation network model, the summation layer is responsible for converting the output of the hidden layer into the final prediction output. The work of the summation layer can be divided into two parts: the numerator and the denominator. That is, the sum of the weighted Gaussian kernel function is determined as the numerator, the sum of the angle Gaussian kernel function is determined as the denominator, and the sum ratio is determined, and the gravity compensation information corresponding to each of the mechanical joints is included in the sum ratio.

[0048] S103. Perform gravity compensation on each mechanical joint of the surgical robot according to the gravity compensation information.

[0049] Specifically, the gravity compensation information is input into the surgical robot controller, thereby achieving gravity compensation for each mechanical joint of the surgical robot.

[0050] The technical solution of the embodiment of the present invention is to obtain the joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes the joint angle information and the gravity torque information corresponding to the joint angle information. According to the joint data information and the target compensation network model, the gravity compensation information corresponding to each mechanical joint is determined, wherein the target compensation network model is obtained by training a pre-established neural network model based on joint sample data. According to the gravity compensation information, gravity compensation is performed on each mechanical joint of the surgical robot, which can significantly improve the positioning accuracy and dynamic response capability of the surgical robot, and improve the adaptability and robustness of the surgical robot system.

[0051] Embodiment 2

[0052] Figure 3 This is a flowchart of a surgical robot gravity compensation method provided by the second embodiment of the present invention. Based on the above embodiments, this embodiment concretizes the training process of the target compensation network model. Figure 3 As shown, the method includes:

[0053] S201, obtaining joint sample data.

[0054] It should be noted that the joint sample data at least includes sample angle information and sample gravity torque corresponding to the sample angle information. The method for acquiring joint sample data is similar to the method for acquiring joint data information, which will not be described in detail in the present invention.

[0055] S202: Determine the output gravity compensation output by the neural network model according to the joint sample data and a pre-established neural network model.

[0056] It is worth noting that the pre-established neural network model may be a generalized regression neural network model. By inputting the joint sample data into the pre-established neural network model for gravity compensation prediction, the output gravity compensation output by the neural network model may be obtained.

[0057] S203. Adjust the smoothing factor in the neural network model based on a preset loss function and the output gravity compensation.

[0058] Specifically, the error result of the output gravity compensation is determined by a predetermined loss function, and the smoothing factor in the neural network model is adjusted according to the error result.

[0059] S204: When the training end condition is met, the trained neural network model is determined as a target compensation network model.

[0060] Specifically, when the training end conditions are met, such as when the number of iterations reaches a preset number or the training error converges, the training of the neural network model is determined to be finished, and the neural network model can be used as a target compensation network model.

[0061] S205. Obtain joint data information corresponding to each mechanical joint of the surgical robot.

[0062] S206. Determine gravity compensation information corresponding to each of the mechanical joints according to the joint data information and the target compensation network model.

[0063] S207. Perform gravity compensation on each mechanical joint of the surgical robot according to the gravity compensation information.

[0064] The technical solution of the embodiment of the present invention can ensure the accuracy of gravity compensation determined by the target compensation network model by using joint sample data to train the neural network model, thereby ensuring the accuracy of the control of the surgical robot.

[0065] Embodiment 3

[0066] Figure 4 This is a schematic diagram of the structure of a surgical robot gravity compensation device provided by the third embodiment of the present invention. Figure 4 As shown, the device comprises:

[0067] A gravity torque acquisition module 301 is used to acquire joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes joint angle information and gravity torque information corresponding to the joint angle information;

[0068] A compensation information determination module 302 is used to determine the gravity compensation information corresponding to each of the mechanical joints according to the joint data information and a target compensation network model, wherein the target compensation network model is obtained by training a pre-established neural network model according to the joint sample data;

[0069] The gravity torque compensation module 303 is used to perform gravity compensation on each mechanical joint of the surgical robot according to the gravity compensation information.

[0070] The technical solution of the embodiment of the present invention is to obtain the joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes the joint angle information and the gravity torque information corresponding to the joint angle information. According to the joint data information and the target compensation network model, the gravity compensation information corresponding to each mechanical joint is determined, wherein the target compensation network model is obtained by training a pre-established neural network model based on joint sample data. According to the gravity compensation information, gravity compensation is performed on each mechanical joint of the surgical robot, which can significantly improve the positioning accuracy and dynamic response capability of the surgical robot, and improve the adaptability and robustness of the surgical robot system.

[0071] Optionally, the gravity torque acquisition module 301 is specifically used for:

[0072] Acquire joint angle information corresponding to each mechanical joint of the surgical robot and joint torque information corresponding to the joint angle information, and determine the joint torque information as the gravity torque information;

[0073] The joint angle information and the gravity torque information are fused to obtain joint data information.

[0074] Exemplarily, the target compensation network model includes an input layer, a hidden layer, a summation layer and an output layer.

[0075] Optionally, the compensation information determination module 302 is specifically configured to:

[0076] Accepting joint angle information corresponding to each of the mechanical joints in the joint data information through the input layer;

[0077] Determine the Gaussian kernel function value between each joint angle information and all joint angle information through the hidden layer;

[0078] Determining the sum of angle Gaussian kernel functions according to all the Gaussian kernel function values ​​through the summing layer, and determining the sum of weighted Gaussian kernel functions according to all the Gaussian kernel function values ​​and the gravity torque information corresponding to each of the mechanical joints;

[0079] The gravity compensation information corresponding to each of the mechanical joints is determined through the output layer according to the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions.

[0080] Optionally, the compensation information determination module 302 is further configured to:

[0081] The output layer determines the sum ratio between the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions, and determines the gravity compensation information corresponding to each of the mechanical joints according to the sum ratio.

[0082] Optionally, the device further comprises a compensation network model.

[0083] The compensation network model is used to:

[0084] Acquire joint sample data, wherein the joint sample data includes sample angle information and sample gravity torque corresponding to the sample angle information;

[0085] Determining an output gravity compensation output by the neural network model according to the joint sample data and a pre-established neural network model;

[0086] Adjusting a smoothing factor in the neural network model based on a preset loss function and the output gravity compensation;

[0087] When the training end condition is reached, the trained neural network model is determined as the target compensation network model.

[0088] Optionally, the target compensation network model includes a generalized regression network model.

[0089] The surgical robot gravity compensation device provided in the embodiment of the present invention can execute the surgical robot gravity compensation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0090] Embodiment 4

[0091] Figure 5 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.

[0092] like Figure 5As shown, the electronic device 10 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, 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 RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] 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.

[0094] 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 special 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 a surgical robot gravity compensation method.

[0095] In some embodiments, the surgical robot gravity compensation method 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 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 of the surgical robot gravity compensation method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the surgical robot gravity compensation method in any other appropriate manner (for example, by means of firmware).

[0096] 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.

[0097] 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.

[0098] 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 combination 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.

[0099] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to 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).

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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 method for gravity compensation of a surgical robot, characterized in that: include: Acquire joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes joint angle information and gravity torque information corresponding to the joint angle information; Determine the gravity compensation information corresponding to each of the mechanical joints according to the joint data information and the target compensation network model, wherein the target compensation network model is obtained by training a pre-established neural network model according to the joint sample data; Gravity compensation is performed on each mechanical joint of the surgical robot according to the gravity compensation information.

2. The method according to claim 1, characterized in that The obtaining of joint data information corresponding to each mechanical joint of the surgical robot includes: Acquire joint angle information corresponding to each mechanical joint of the surgical robot and joint torque information corresponding to the joint angle information, and determine the joint torque information as the gravity torque information; The joint angle information and the gravity torque information are fused to obtain joint data information.

3. The method according to claim 1, characterized in that The target compensation network model includes an input layer, a hidden layer, a summation layer and an output layer.

4. The method according to claim 3, characterized in that Determining gravity compensation information corresponding to each of the mechanical joints according to the joint data information and the target compensation network model includes: Accepting joint angle information corresponding to each of the mechanical joints in the joint data information through the input layer; Determine the Gaussian kernel function value between each joint angle information and all joint angle information through the hidden layer; Determining the sum of angle Gaussian kernel functions according to all the Gaussian kernel function values ​​through the summing layer, and determining the sum of weighted Gaussian kernel functions according to all the Gaussian kernel function values ​​and the gravity torque information corresponding to each of the mechanical joints; The gravity compensation information corresponding to each of the mechanical joints is determined through the output layer according to the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions.

5. The method according to claim 4, characterized in that The step of determining the gravity compensation information corresponding to each of the mechanical joints according to the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions through the output layer includes: The output layer determines the sum ratio between the sum of the angle Gaussian kernel functions and the sum of the weighted Gaussian kernel functions, and determines the gravity compensation information corresponding to each of the mechanical joints according to the sum ratio.

6. The method according to claim 1, characterized in that The target compensation network model is obtained by training in the following manner: Acquire joint sample data, wherein the joint sample data includes sample angle information and sample gravity torque corresponding to the sample angle information; Determining an output gravity compensation output by the neural network model according to the joint sample data and a pre-established neural network model; Adjusting a smoothing factor in the neural network model based on a preset loss function and the output gravity compensation; When the training end condition is reached, the trained neural network model is determined as the target compensation network model.

7. The method according to claim 1, characterized in that The target compensation network model includes a generalized regression network model.

8. A surgical robot gravity compensation device, characterized in that: include: A gravity torque acquisition module, used to acquire joint data information corresponding to each mechanical joint of the surgical robot, wherein the joint data information at least includes joint angle information and gravity torque information corresponding to the joint angle information; A compensation information determination module, used to determine the gravity compensation information corresponding to each of the mechanical joints according to the joint data information and a target compensation network model, wherein the target compensation network model is obtained by training a pre-established neural network model according to the joint sample data; The gravity torque compensation module is used to perform gravity compensation on each mechanical joint of the surgical robot according to the gravity compensation information.

9. 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 perform the surgical robot gravity compensation method according to any one of claims 1 to 7.

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 surgical robot gravity compensation method according to any one of claims 1 to 7 when executed.

Images