Method, device and equipment for determining motion data of a robot arm and storage medium

Abstract

The present disclosure relates to a method and device for determining motion data of a mechanical arm, an apparatus and a storage medium. The method comprises: implanting a three-dimensional prosthesis model corresponding to a prosthesis into a three-dimensional joint model corresponding to a joint according to a plurality of implant data to obtain a plurality of candidate implant models; wherein the implant data and the candidate implant model are one-to-one corresponding; determining a plurality of joint function data corresponding to the plurality of candidate implant models, and determining a target implant model in the plurality of candidate implant models according to the plurality of joint function data; determining a grinding area corresponding to the joint according to the position of the target prosthesis model in the target implant model; and performing motion planning processing on the mechanical arm according to the grinding area to obtain motion data. Thus, the full-process automation in the joint implantation process is realized, the random error caused by human operation is avoided, and the surgical efficiency is improved.

Description

Technical Field

[0001] This disclosure relates to the field of motion control technology, and in particular to a method, apparatus, device and storage medium for determining motion data of a robotic arm. Background Technology

[0002] With the development of robot-assisted surgery technology, the use of orthopedic robots is becoming increasingly common. However, most existing orthopedic surgical robots are semi-automatic systems, which are prone to introducing random errors from human operation and are heavily reliant on the operator's skill level. Therefore, improving the efficiency of robot-assisted surgery has become an urgent problem to be solved. Summary of the Invention

[0003] To address the aforementioned technical problems, this disclosure provides a method, apparatus, device, and storage medium for determining motion data of a robotic arm.

[0004] In a first aspect, this disclosure provides a method for determining motion data of a robotic arm, the method comprising: Based on multiple implantation data, the three-dimensional prosthesis model corresponding to the prosthesis is implanted into the three-dimensional joint model corresponding to the joint to obtain multiple candidate implantation models; wherein, the implantation data and the candidate implantation models correspond one-to-one. Determine multiple joint function data corresponding to the multiple candidate implantation models, and determine the target implantation model among the multiple candidate implantation models based on the multiple joint function data; The grinding area corresponding to the joint is determined based on the position of the target prosthesis model in the target implantation model; Motion planning is performed on the robotic arm based on the grinding area to obtain motion data.

[0005] Secondly, this disclosure provides a motion data determination device for a robotic arm, the device comprising: An implantation module is used to implant the three-dimensional prosthesis model corresponding to the prosthesis into the three-dimensional joint model corresponding to the joint based on multiple implantation data, thereby obtaining multiple candidate implantation models; wherein, the implantation data and the candidate implantation models correspond one-to-one. The first determining module is used to determine multiple joint function data corresponding to the multiple candidate implantation models, and to determine the target implantation model among the multiple candidate implantation models based on the multiple joint function data. The second determining module is used to determine the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model; The planning module is used to perform motion planning processing on the robotic arm based on the grinding area to obtain motion data.

[0006] Thirdly, embodiments of this disclosure also provide an electronic device, the device comprising: One or more processors; Storage device for storing one or more programs. When one or more programs are executed by one or more processors, the one or more processors implement the methods provided in the first aspect.

[0007] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method provided in the first aspect.

[0008] The technical solution provided in this disclosure has the following advantages compared with the prior art: This disclosure discloses a method, apparatus, device, and storage medium for determining motion data of a robotic arm. The method includes: implanting a three-dimensional prosthesis model corresponding to a prosthesis into a three-dimensional joint model corresponding to a joint based on multiple implantation data, thereby obtaining multiple candidate implantation models; wherein the implantation data and the candidate implantation models correspond one-to-one; determining multiple joint function data corresponding to the multiple candidate implantation models, and determining a target implantation model among the multiple candidate implantation models based on the multiple joint function data; determining a grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model; and performing motion planning processing on the robotic arm based on the grinding area to obtain motion data.

[0009] In the above scheme, the implantation of the prosthesis into the joint is simulated in a three-dimensional virtual space to obtain multiple candidate implantation models. Based on the joint function data corresponding to the multiple candidate implantation models, the target implantation model is determined. Then, based on the position of the target prosthesis model in the target implantation model, the grinding area of ​​the joint is determined. The motion planning of the robotic arm is performed based on the grinding area, realizing the automated determination of a reasonable grinding area. Furthermore, the motion control of the robotic arm is performed based on the grinding area, realizing the fully automated processing of the joint implantation process, avoiding the introduction of random errors caused by human operation, and improving surgical efficiency. Attached Figure Description

[0010] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0011] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1A flowchart illustrating a method for determining motion data of a robotic arm according to an embodiment of this disclosure; Figure 2 Another method for determining motion data of a robotic arm provided in this disclosure embodiment; Figure 3 This is a schematic diagram of the structure of an image segmentation network provided in an embodiment of the present disclosure; Figure 4 A flowchart illustrating another method for determining motion data of a robotic arm provided in this embodiment of the present disclosure; Figure 5 A block diagram of a control system for determining position increments provided in an embodiment of this disclosure; Figure 6 A flowchart illustrating another method for determining motion data of a robotic arm provided in an embodiment of this disclosure; Figure 7 This is a schematic diagram of the structure of the robotic arm system provided in the embodiments of this disclosure; Figure 8 A schematic diagram of a method for determining motion data of a robotic arm provided for the implementation of this disclosure; Figure 9 A schematic diagram of an architecture provided for an embodiment of this disclosure; Figure 10 This is a schematic diagram of the structure of a motion data determination device for a robotic arm provided in an embodiment of the present disclosure; Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0013] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0014] In knee and hip replacement surgeries, the precision and efficiency of osteotomy play a crucial role in the accuracy of prosthesis placement and postoperative recovery. However, traditional osteotomy techniques rely heavily on the surgeon's personal experience and hand-eye coordination, making it difficult to ensure consistency. Due to the irregularities of the joint surface and individual patient differences, achieving high precision in manual osteotomy is challenging. Furthermore, learning the technique is time-consuming, requiring extensive training to reach a proficient level.

[0015] With the development of robot-assisted surgery technology, the use of robotic devices in surgery is becoming increasingly common. Most existing surgical robots are semi-automatic systems. Whether it's traditional manual knee replacement or a semi-automatic orthopedic surgical robot system, both are prone to introducing random errors from human operation, thus heavily relying on the operator's skill level. The operator's familiarity with the surgical procedure directly affects efficiency; unfamiliar operators need to frequently pause the operation to adjust the patient's position and confirm accuracy, increasing surgical time.

[0016] Therefore, there is an urgent need for an autonomous surgical robot system to achieve high-precision and intelligent surgery, thereby improving the accuracy of robot-assisted joint replacement surgery, saving osteotomy time, and reducing the difficulty of surgery.

[0017] To address at least one of the aforementioned technical problems, the method for determining motion data of a robotic arm provided in this disclosure is described below. In this disclosure, the method for determining motion data of the robotic arm can be executed by an electronic device. This electronic device may also include devices with communication capabilities such as tablet computers, desktop computers, and laptop computers.

[0018] Figure 1 A flowchart illustrating a method for determining motion data of a robotic arm according to an embodiment of this disclosure is shown. Figure 1 As shown, the method for determining the motion data of the robotic arm may include the following steps.

[0019] Step 101: Based on multiple implantation data, the three-dimensional prosthesis model corresponding to the prosthesis is implanted into the three-dimensional joint model corresponding to the joint to obtain multiple candidate implantation models; wherein, the implantation data and the candidate implantation models correspond one-to-one.

[0020] The implantation data can be used to characterize the pose of the 3D prosthesis model implanted into the 3D joint model, which can be understood as recording the relative position between the 3D prosthesis model and the 3D joint model. This implantation data can include the implantation position and implantation angle. The implantation angle can include installation angles such as varus angle and eversion angle. The 3D prosthesis model can be a digital 3D virtual model simulating the joint prosthesis. The 3D joint model can be a digital 3D virtual model simulating the joint. The candidate implantation model can be a 3D virtual model simulating the joint after prosthesis implantation.

[0021] In this embodiment, the user can determine the prosthesis to be implanted and input the prosthesis identifier corresponding to the selected prosthesis into the motion data determination device of the robotic arm. The motion data determination device of the robotic arm can determine the corresponding three-dimensional prosthesis model according to the prosthesis identifier, and simulate the three-dimensional prosthesis model into the three-dimensional joint model corresponding to the joint according to multiple implantation data, so as to obtain candidate implantation models that correspond one-to-one with the implantation data. These multiple candidate implantation models realize the simulation of multiple implantation methods.

[0022] Step 102: Determine multiple joint function data corresponding to multiple candidate implantation models, and determine the target implantation model among multiple candidate implantation models based on the multiple joint function data.

[0023] Among them, joint function data can characterize the properties of candidate implantation models in the joint function dimension, and can be used to characterize the impact of the implanted prosthesis on joint function. The target implantation model can be the candidate implantation model that is optimal in the joint function dimension among multiple candidate implantation models, and can be used to characterize the relative pose between the finally determined prosthesis and joint.

[0024] In this embodiment, the motion data determination device for the robotic arm can perform force analysis on the joints and prosthesis interface, as well as joint motion analysis, on multiple candidate models to obtain multiple joint function data corresponding to the candidate models. Based on these multiple joint function data, the multiple candidate implantation models are comprehensively evaluated to obtain the target implantation model that is optimal in the joint function dimension.

[0025] In some embodiments of this disclosure, joint function data includes biomechanical data and joint motion data. The biomechanical data can be used to describe the mechanical properties in a biological dimension after implantation of the prosthesis. The joint motion data can be used to describe the characteristics in a motion dimension after implantation of the prosthesis.

[0026] In some embodiments of this disclosure, multiple joint function data corresponding to multiple candidate implantation models are determined, including: Step a1 involves performing stress analysis on multiple candidate implantation models to obtain multiple biomechanical data; among which, the biomechanical data includes at least one of contact stress distribution, shear force, reaction force, force line angle, and soft tissue tension.

[0027] Contact stress distribution characterizes the stress distribution at the contact interface between the prosthesis and the joint, reflecting the uniformity of load bearing at this interface. Shear force characterizes the shear force acting on the contact interface during joint movement after prosthesis implantation. Reaction force characterizes the opposing force exerted on the prosthesis during joint movement after prosthesis implantation. Force line angle represents the angle between the force lines of the two bones connected to the joint; for example, in the knee joint, this angle is the angle between the force lines corresponding to the femur and the tibia. Soft tissue tension characterizes the tension of ligaments, tendons, and other soft tissues around the joint after prosthesis implantation. This tension indicates the tightness and balance of the collateral ligaments, and consequently, whether the joint can maintain dynamic balance during flexion and extension after prosthesis implantation, whether postoperative joint instability or stiffness will occur, and whether force line alignment can be ensured while maintaining balanced force distribution.

[0028] In this embodiment, for each candidate implantation model, the motion data determination device of the robotic arm can perform joint force analysis based on the candidate implantation model to obtain one or more of the following: contact stress distribution, shear force, reaction force, and force line angle. This data can characterize whether the prosthesis can maintain stability under static and dynamic loads, and determine whether stress concentration and wear occur. Furthermore, the motion data determination device of the robotic arm can also obtain soft tissue tension through soft tissue balance simulation. Thus, the degree to which the joint's natural movement is restored after implantation is characterized using the aforementioned biomechanical data.

[0029] Step a2 involves performing multibody dynamics simulations on multiple candidate implantation models to obtain multiple joint motion data; wherein, the joint motion data includes at least one of the following: joint range of motion, joint motion trajectory, and joint center range of motion.

[0030] Among these, the range of motion of the joint can characterize the range of motion of the joint after implantation of the prosthesis, which can include flexion-extension range, rotation range, etc. The joint motion trajectory can characterize the positional path of the joint after implantation of the prosthesis. The range of motion of the joint center can characterize the range of motion of the joint center point during movement after implantation of the prosthesis, which can include translation and rotation of the joint center.

[0031] In this embodiment, for each candidate implantation model, the robotic arm motion data determination device can simulate the motion of the candidate implantation model through multibody dynamics simulation or large-scale model simulation to obtain the joint motion data corresponding to that candidate implantation model. This joint motion data can characterize whether the natural motion pattern of the joint can be effectively restored after prosthesis implantation.

[0032] The above approach provides a reliable basis for preoperative planning through a high-precision model, which helps to reduce surgical errors and improve the matching degree of prosthesis implantation.

[0033] For example, the motion data determination device for the robotic arm can acquire a three-dimensional joint model, match the corresponding three-dimensional prosthesis model from a prosthesis model library based on the size of the three-dimensional joint model, and virtually install the three-dimensional prosthesis model in the corresponding position of the three-dimensional joint model according to the implantation data, resulting in multiple candidate implantation models. Then, biomechanical modeling and analysis, as well as joint kinematic modeling and analysis, are performed on each candidate implantation model to obtain biomechanical data and joint motion data. This biomechanical data and joint motion data can be used to determine whether the prosthesis conforms to normal physiological movement patterns after installation. During the simulated movement, kinematic and mechanical monitoring can be performed in real time, monitoring the contact pressure distribution and shear force of the contact surface at different flexion and extension angles to ensure the stability of the prosthesis under stress. Furthermore, biomechanical assessment of the joint is performed, evaluating soft tissue tension to determine whether to adjust the installation angle of the prosthesis, optimizing postoperative functional recovery, and ensuring the prosthesis has mechanical stability in the patient's daily activities such as walking and weight-bearing, reducing postoperative complications. Subsequently, surgery is performed based on the determined target implantation model, and postoperative rehabilitation training is guided according to recommendations based on the postoperative joint range of motion, force distribution, and rehabilitation progress.

[0034] In some embodiments of this disclosure, a target implantation model is determined from a plurality of candidate implantation models based on multiple joint function data, including: Step b1: Among multiple candidate implantation models, the candidate implantation model whose biomechanical data meets the first screening condition and whose joint motion data meets the second screening condition is determined as the intermediate implantation model.

[0035] The first screening criterion can be a screening criterion set for biomechanical data. The second screening criterion can be a screening criterion set for joint motion values. This embodiment does not limit the first and second screening criterions; for example, the above screening criterions can limit the range of the corresponding data. The intermediate implantation model can be the implantation model determined during the screening of candidate implantation models.

[0036] In this embodiment, the device for determining the motion data of the robotic arm can identify, from multiple candidate implantation models, a candidate implantation model whose biomechanical data meets the first screening condition and whose joint motion data meets the second screening condition, and then determine the candidate implantation model as an intermediate implantation model.

[0037] Step b2: If there are multiple intermediate implantation models, determine multiple comprehensive values ​​corresponding to the multiple intermediate implantation models based on biomechanical data and joint motion data, and determine the target implantation model among the multiple intermediate implantation models based on the multiple comprehensive values.

[0038] The comprehensive value can be a comprehensive evaluation value determined based on biomechanical data and joint motion data.

[0039] In this embodiment, the motion data determination device of the robotic arm can determine whether there are multiple intermediate implantation models. If so, the biomechanical data and joint motion data corresponding to each intermediate implantation model are input into the comprehensive evaluation model. The comprehensive evaluation model determines the comprehensive value corresponding to each intermediate implantation model, and the intermediate model with the largest comprehensive value is determined as the target implantation model. The comprehensive evaluation model can be a calculation formula or a neural network model, and this embodiment does not impose any restrictions.

[0040] In the above scheme, intermediate implantation models that meet the screening criteria in both biomechanical and key motion dimensions are first identified. Then, the target implantation model is obtained by comprehensively scoring the intermediate implantation models. Under the condition that the data in each dimension meets the corresponding conditions, the target implantation model with the best overall performance is determined.

[0041] Step 103: Determine the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model.

[0042] The target prosthesis model can be a candidate prosthesis model implanted in the target implantation model. The grinding region can be the area of ​​the joint that needs to be ground away in physical space.

[0043] In this embodiment of the disclosure, the motion data determination device of the robotic arm can determine the position of the target prosthesis model in the target implantation model, and determine the grinding area corresponding to the joint in the physical space based on the position.

[0044] Figure 2 Another method for determining motion data of a robotic arm provided in this disclosure embodiment, such as Figure 2 As shown, in some embodiments of this disclosure, determining the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model includes: Step 201: Obtain the first prosthesis position of the target prosthesis model, the coordinate system transformation relationship between the model coordinate system and the physical coordinate system of the target implanted model, and the preset positional relationship between the target prosthesis and the target boundary wall.

[0045] The model coordinate system can be the coordinate system corresponding to the target implanted model in a three-dimensional virtual space. The first prosthesis position can be the position of the target prosthesis model in the model coordinate system. The physical coordinate system can be the coordinate system in physical space, or the coordinate system based on which the robotic arm path planning is performed. The coordinate system transformation relationship can be the transformation relationship from the model coordinate system to the physical coordinate system, and this coordinate system transformation relationship can be pre-calibrated. The target prosthesis can be the prosthesis corresponding to the target prosthesis model in real space. The target boundary wall can be the boundary wall corresponding to the target prosthesis in real space. The boundary wall can be a virtual safety boundary in physical space during grinding operations. Through this virtual safety boundary, the maximum range of cutting operations can be defined, thereby preventing over-cutting. Through this boundary wall, the range of motion of the robotic arm can be controlled, improving the safety and stability of the surgery. The positional relationship can characterize the relative position between the target prosthesis and the target boundary wall in physical space. Since the prosthesis and the boundary wall are matched, this positional relationship can be pre-calibrated.

[0046] In this embodiment, the motion data determination device of the robotic arm can read the first prosthesis position of the target prosthesis model in the 3D software and obtain the pre-calibrated coordinate system transformation relationship and position relationship.

[0047] Step 202: Transform the position of the first prosthesis according to the coordinate system transformation relationship to obtain the position of the second prosthesis of the target prosthesis in the physical coordinate system.

[0048] The second prosthesis position can be the location of the target prosthesis in physical space.

[0049] In this embodiment, the motion data determination device of the robotic arm can transform the coordinates within the first prosthesis position in the model coordinate system according to the coordinate transformation relationship to obtain the second prosthesis position in the physical coordinate system.

[0050] Step 203: Determine the position of the target boundary wall in the physical coordinate system based on the positional relationship and the position of the second spur.

[0051] The location of the boundary wall can be the location of a virtual boundary wall within the physical space. The area inside the boundary wall is the area where grinding operations can be performed, and the area outside the boundary wall is the area where grinding operations are prohibited.

[0052] In this embodiment, the motion data determination device of the robotic arm can adjust the position based on the position of the second dummy according to the positional relationship to obtain the position of the boundary wall in the physical coordinate system.

[0053] Step 204: Determine the grinding area based on the location of the second prosthesis and the location of the boundary wall.

[0054] In this embodiment, the motion data determination device of the robotic arm can determine the initial grinding area to be ground off in the joint based on the part where the position of the second prosthesis coincides with the joint, and remove the area outside the boundary wall position in the initial grinding area to obtain the grinding area.

[0055] In the above scheme, the location of the second spur in the physical space and the location of the boundary wall where the target wall is located were determined, and a reasonable grinding area was determined based on the location of the second spur and the location of the boundary wall.

[0056] Step 104: Perform motion planning on the robotic arm based on the grinding area to obtain motion data.

[0057] Among them, motion data can be data for motion control of the robotic arm during the operation process, which can include motion trajectory, cutting parameters of the end effector, etc.

[0058] In this embodiment, the motion data determination device for the robotic arm can obtain a motion path based on the grinding area using an adaptive trajectory generation method. This adaptive trajectory generation method can be determined using a multi-objective optimization algorithm and a path prediction method based on a mechanical model. This method comprehensively considers path length, cutting error, and trajectory smoothness to obtain motion data through path sliding. Furthermore, the motion data can be further optimized to obtain an optimized motion path. Optionally, further optimization can be performed using B-spline interpolation and an optimal cutting sequence strategy to improve the path smoothness and surgical efficiency. Optionally, machine learning techniques can also be combined to improve the motion path through analysis and training on a large amount of surgical data. After determining the motion path, the motion data determination device for the robotic arm can calculate the joint angle trajectories of each joint of the robotic arm based on the motion path to obtain motion data.

[0059] The motion data may also include cutting parameters of the end-effector, which may be determined in conjunction with bone mineral density, which can be determined from grayscale values ​​of computed tomography (CT) images. These cutting parameters may include tool feed rate and cutting speed.

[0060] For example, the motion data determination device for the robotic arm can determine the coordinate system of the grinding tool and perform path planning for the robotic arm to obtain the osteotomy path in the flange coordinate system (i.e., the physical coordinate system). Based on kinematic constraints, it generates the joint angular trajectories of each joint according to the osteotomy path in the flange coordinate system and performs interpolation calculations on each joint angular trajectory to obtain motion data. In the subsequent osteotomy process, the motion data determination device for the robotic arm can output the angular trajectories of each joint based on the motion data and the adaptive impedance control algorithm. Specifically, the force sensor collects the torque data of the end effector and the bone contact, and updates the angular trajectories of the joints based on the tool positioning data and torque data, ultimately realizing the closed-loop control strategy of the robotic arm to achieve more precise osteotomy operations and improve the system's adaptability to bone density and individual anatomical characteristics.

[0061] The method for determining motion data of a robotic arm provided in this disclosure includes: implanting a three-dimensional prosthesis model corresponding to a prosthesis into a three-dimensional joint model corresponding to a joint based on multiple implantation data, thereby obtaining multiple candidate implantation models; wherein, the implantation data and the candidate implantation models correspond one-to-one; determining multiple joint function data corresponding to the multiple candidate implantation models, and determining a target implantation model among the multiple candidate implantation models based on the multiple joint function data; determining the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model; and performing motion planning processing on the robotic arm based on the grinding area to obtain motion data.

[0062] In the above scheme, the implantation of the prosthesis into the joint is simulated in a three-dimensional virtual space to obtain multiple candidate implantation models. Based on the joint function data corresponding to the multiple candidate implantation models, the target implantation model is determined. Then, based on the position of the target prosthesis model in the target implantation model, the grinding area of ​​the joint is determined. The motion planning of the robotic arm is performed based on the grinding area, realizing the automated determination of a reasonable grinding area. Furthermore, the motion control of the robotic arm is performed based on the grinding area, realizing the fully automated processing of the joint implantation process, avoiding the introduction of random errors caused by human operation, and improving surgical efficiency.

[0063] In some embodiments of this disclosure, the method for determining the motion data of the robotic arm further includes: acquiring multiple scan images obtained by performing continuous tomographic scanning of the joints; performing bone segmentation processing on the multiple scan images to obtain multiple joint images; and sequentially performing surface reconstruction processing, surface smoothing processing, and mesh simplification processing on the multiple joint images to obtain a three-dimensional joint model.

[0064] The scanned images can be obtained through computed tomography (CT) scans of the joint area. Joint images can be two-dimensional images of the joint obtained through segmentation. Surface reconstruction processing involves building a continuous three-dimensional surface model of the joint based on raw data such as tomographic images. Surface smoothing processing is an optimization process that corrects anomalies such as burrs, noise, and irregular protrusions on the surface of the three-dimensional model, reducing surface roughness and making the model more closely resemble the morphological characteristics of the real object. Mesh simplification processing is a lightweighting process that reduces the number of mesh patches in the model. By eliminating redundant vertices and patches, the data volume of the model is reduced, thereby improving the computational efficiency of subsequent simulation analysis and visualization.

[0065] In this embodiment, the motion data determination device for the robotic arm can acquire scanned images of the joints, perform image preprocessing on the scanned images, and input the preprocessed scanned images into an image segmentation network. Figure 3 This is a schematic diagram of the structure of an image segmentation network provided in an embodiment of this disclosure. Figure 3 As shown, this image segmentation network can include convolutional layer 1 (Conv1), pooling layer 1 (Pool1), convolutional layer 2 (Conv1), pooling layer 2 (Pool), and an input layer. This network can perform convolution, downsampling, upsampling, and output processing. Multiple joint images can be stacked as two-dimensional slices. Then, the moving cube algorithm is used to reconstruct the surface of the bones in the joint images, and surface smoothing and simplification are performed using Laplacian smoothing and bilateral filtering to obtain a visualized three-dimensional joint model.

[0066] Specifically, in this embodiment, a high-resolution computed tomography scan of the knee or hip joint is performed preoperatively to obtain scanned images of the joint bones. After denoising, contrast enhancement, and normalization processing to improve the contrast between bone and soft tissue, Gaussian filtering or wavelet denoising techniques are used to remove noise generated during the scanning process. Subsequently, an image segmentation network is used to extract joint images from the scanned images. Furthermore, graph theory methods combined with anatomical prior information can be used to further optimize the image segmentation results.

[0067] After bone segmentation, a moving cube algorithm is used to reconstruct the 3D surface of the bones, and techniques such as Laplacian smoothing and bilateral filtering are employed to improve the smoothness and visual quality of the model. Furthermore, a mesh simplification algorithm is used to reduce model complexity and computational overhead while preserving the geometric features of the bones. The 3D distribution of bone density information can aid in assessing bone quality and developing personalized surgical plans. The density distribution of bones can be reconstructed using grayscale values ​​from computed tomography (CT) images, helping to evaluate bone quality and strength. In addition, finite element analysis can simulate bone deformation under stress, providing a basis for intraoperative bone resection.

[0068] Figure 4 A flowchart illustrating another method for determining motion data of a robotic arm provided in this disclosure is shown below. Figure 4 As shown in some embodiments of this disclosure, the method further includes: Step 401: Determine the target force data and target position of the robotic arm in the current control cycle based on the motion data.

[0069] The control cycle refers to the cycle in which the robotic arm is controlled for motion. The current control cycle refers to the current cycle in which the robotic arm is controlled for motion. The previous control cycle refers to the control cycle preceding the current control cycle. Target force data can be used to record the force expected to be reached in the current control cycle. Target position can be used to record the position expected to be reached by the robotic arm in the current control cycle.

[0070] In this embodiment, the motion data determination device of the robotic arm can analyze the motion data to determine the target force data to be applied by the robotic arm in the current control cycle and the target position to be reached.

[0071] Step 402: Obtain the position increment and feedback force data of the robotic arm in the previous control cycle.

[0072] The position increment represents the relative position change of the current control cycle compared to the previous control cycle. The feedback force data can be force data collected by sensors on the robotic arm, specifically real-time data collected by a six-dimensional force sensor or torque sensor at the end effector of the robotic arm.

[0073] In this embodiment, during the grinding process, the motion data determination device of the robotic arm can detect the positions of the joints and the end effector of the robotic arm in real time through the navigation subsystem, thereby achieving the position positioning of the robotic arm at the end of the previous control cycle. Furthermore, it determines the position increment of the previous control cycle based on the position of the robotic arm at the end of the previous control cycle and the position of the robotic arm in the cycle before that. It also acquires feedback force data collected by the sensors at the end effector of the robotic arm.

[0074] Step 403: Calculate the vector difference between the target force data and the feedback force data to obtain the error force data. Input the error force data into the impedance controller to obtain the corrected position.

[0075] Among them, the error force data can characterize the error between the expected applied force and the actual applied force. The impedance controller can be a dynamic relationship model between the end effector position and the contact force. Through this impedance controller, the system characteristics of the spring-damped-mass system can be simulated to achieve flexible interaction between the robotic arm and the environment. The corrected position can be a position compensation amount determined based on the force, which can characterize the position offset required to achieve the desired contact force.

[0076] In this embodiment, the motion data determination device of the robotic arm can calculate the vector difference between the target force data and the feedback force data to obtain error force data, and input the error force data to the impedance controller to obtain the corresponding correction position.

[0077] Step 404: Determine the position increment for the current control cycle based on the target position, the corrected position, and the position increment of the previous control cycle.

[0078] In this embodiment, the motion data determination device of the robotic arm can superimpose the target position and the corrected position and then subtract the position increment of the previous control cycle to obtain the calculated position. The calculated position is then subjected to proportional-integral-derivative control and robotic arm transfer function processing to obtain the position increment.

[0079] Figure 5 A block diagram of a control system for determining position increments provided in this disclosure embodiment is shown below. Figure 5 As shown, Represents target force data. Represents feedback force data. Indicates error force data, The correlation coefficient of quality is obtained by... Force can be converted into acceleration. This represents a first-order integral. This is the speed feedback coefficient. This is the position feedback coefficient. The corrected position is obtained through integration. The target position. PID stands for Proportional-Integral-Derivative (PID) control. Used to describe the dynamic characteristics of a robotic arm. It can characterize the acquisition of feedback force data after controlling the movement of the robotic arm based on position increments. X It can characterize the position increment.

[0080] like Figure 5As shown, in this implementation, the target force data and feedback force data are subtracted to obtain error force data. This error force data is then superimposed with the velocity feedback force data and position feedback force data to obtain comprehensive force data. This comprehensive force data is converted using the mass correlation coefficient to obtain comprehensive acceleration. The comprehensive acceleration is adjusted using the velocity feedback force data to obtain the adjustment acceleration. A first integral is performed on this adjustment acceleration to obtain the comprehensive velocity. The comprehensive velocity is then adjusted using the position feedback force data to obtain the adjustment velocity. A first integral is performed on this adjustment velocity to obtain the corrected position. The error position and target position are added together and the position increment from the previous control cycle is subtracted to obtain the calculated position. Proportional-integral-derivative control and dynamic characteristic processing of the robotic arm are applied to this calculated position to obtain the position increment for the current control cycle. After moving according to the position increment of the current control cycle, the feedback force data for the current control cycle is collected, and the position increment for the next control cycle is determined. Furthermore, the position feedback coefficient is adjusted based on the position increment using an adaptive control law, and the velocity feedback coefficient is adjusted based on the feedback force data.

[0081] In the above scheme, the robotic arm control adopts a dual-loop control. The inner loop position control uses a feedforward PID control strategy. The output of the robot control system is position information, which is converted into a force signal through interaction with the external environment. To improve the control performance of position tracking, a force error signal or torque error signal is used as the driving force of the target impedance. A new impedance controller is established to adapt to changes in the osteotomy environment. Based on the changes in osteotomy force error, an adaptive control law is designed to adjust the impedance parameters in real time, compensating for the uncertainty of the dynamic environment online. This reduces the force tracking error of the system, allowing the robot to maintain good control performance even when the bone state changes or the controlled object model changes. This enables real-time feedback control during surgery, achieving dynamic adjustment and closed-loop control of the cutting path to avoid over-cutting or soft tissue damage.

[0082] This surgical path planning method, based on precise modeling, real-time feedback, and path optimization, enables orthopedic surgical robot systems to demonstrate significant advantages in personalized and minimally invasive knee replacement surgery. It can significantly improve the accuracy of prosthesis implantation, the postoperative force line recovery effect, and the level of soft tissue protection, providing strong guarantees for postoperative rehabilitation quality and prosthesis lifespan.

[0083] Furthermore, to meet the individual needs of different operators, the robotic arm system offers two control methods: autonomous mode and assisted mode. In autonomous mode, the robotic arm autonomously completes the approach and osteotomy / bone-grinding processes according to the planned osteotomy path, while the user acts as a supervisor to monitor the entire process and ensure its safety.

[0084] In some embodiments of this disclosure, the motion data includes approach motion data and task motion data. The approach motion data can be used to control the robotic arm to move closer to the joint to be worked on. The task motion data can be used to control the robotic arm to perform grinding operations on the joint.

[0085] Figure 6 A flowchart illustrating another method for determining motion data of a robotic arm provided in this disclosure is shown below. Figure 6 As shown, the method also includes: Step 601: Before the robotic arm reaches the work preparation position, in response to the user's pressing operation on the first control of the robotic arm, the robotic arm is controlled to move towards the work preparation position according to the approach motion data. In response to the user's popping operation on the first control, a first stop command is sent to the robotic arm to stop the robotic arm from moving.

[0086] The preparation position can be a preset position that the robotic arm needs to reach before performing the grinding operation. This preparation position can be a position near the joint. The first control can be a control used to control the movement of the robotic arm to the preparation position. This embodiment does not limit the type of the first control. For example, the first control can be a physical foot pedal control. The press operation can be the operation to activate the control. The release operation can be the operation to terminate the activation of the control. The first stop command can be a command to instruct the robotic arm to stop moving.

[0087] Step 602: After the robotic arm reaches the work preparation position, in response to the user's pressing operation on the second control of the end effector carried by the robotic arm, the robotic arm is controlled to move according to the work motion data and the end effector is controlled to perform grinding operations. In response to the user's popping operation on the second control, a second stop command is sent to the robotic arm to stop the robotic arm and the end effector to stop grinding operations.

[0088] The second control can be a control used to control the robotic arm to carry the end effector tool to perform grinding operations. This embodiment does not limit the type of the second control. For example, the second control can be a trigger on the end effector tool. The second stop command can be a command instructing the robotic arm to stop moving and the end effector tool to stop working.

[0089] During the approach process in assisted mode, the robotic arm moves towards the work preparation position based on the planned path information in the approach motion data. The user can control the robotic arm's approach to the work preparation position by controlling the switch of the first control on the robotic arm as a trigger signal. If the first control is pressed, the robotic arm moves towards the work preparation position; if the first control is released, the robotic arm stops moving.

[0090] After the robotic arm reaches the work preparation position, the end effector performs the grinding operation. During this process, the user needs to press the second control of the end effector as a trigger signal to start the cutting operation. Pressing the second control causes the robotic arm to carry the end effector to perform the grinding operation, and releasing the second control stops the robotic arm's movement and the end effector's grinding operation.

[0091] In both osteotomy and bone grinding processes described above, the robotic arm can automatically adjust the rotation speed of the power system based on the bone density value determined by the grayscale value of the CT image, dynamically controlling the applied force of the osteotomy tool. This increases the power output in high-density bone areas and decreases the power in low-density bone areas, improving the smoothness and safety of the osteotomy, while reducing the damage to the robotic arm and the patient caused by vibration during the grinding process.

[0092] Figure 7 This is a schematic diagram of the structure of the robotic arm system provided in the embodiments of this disclosure, such as... Figure 7 As shown, this robotic arm system integrates a main control subsystem, a robotic arm subsystem, and a navigation subsystem, covering a complete process including preoperative intelligent planning, intraoperative real-time navigation, robotic arm feedback control, and postoperative recovery assessment. Through the coordinated work of multiple subsystems, a high-precision and intelligent joint replacement surgery process is achieved, realizing intelligent segmentation and reconstruction, joint biomechanical and kinematic analysis, robotic arm trajectory planning and feedback control, autonomous osteotomy, and intraoperative and postoperative surgical effect evaluation and optimization. It solves the problems of insufficient osteotomy precision and low surgical efficiency, enabling precise planning and execution of osteotomy paths, reducing random errors caused by human operation, and achieving efficient and stable automatic osteotomy function.

[0093] Specifically, the main control subsystem coordinates and manages the overall process and is the core decision-making unit of the system, comprising a control module, a functional module, and an interaction module. It imports CT or MRI image data and uses intelligent segmentation and reconstruction algorithms to generate a 3D joint model. Combined with artificial intelligence algorithms, it intelligently identifies bone density, marks different density areas, and provides accurate bone quality information. It generates a preliminary osteotomy plan and uses a multi-objective optimization algorithm to automatically plan the prosthesis, determine the optimal prosthesis implantation position and angle, and implants the 3D prosthesis model into the 3D joint model through a bone registration module. Through kinematic dynamics analysis, it receives pose feedback from the navigation system and force feedback signals from the robotic arm, adjusting the robotic arm's trajectory and osteotomy power in real time. Motion planning and control provide closed-loop control signals to ensure accuracy and stability during the osteotomy process. The interaction module provides a preoperative planning confirmation interface and an intraoperative real-time monitoring interface, allowing users to manually intervene or adjust as needed. It supports two operating modes: user as supervisor or assistant under different indications. This interaction module may include a monitor, mouse, and keyboard. Furthermore, the control modules in this main control subsystem include a power supply and a main control unit.

[0094] The robotic arm subsystem is the unit that directly performs surgical operations. It employs a multi-degree-of-freedom robotic arm with high-precision motion control and force feedback capabilities, and mainly includes a control module, a sensing module, and a power supply module. The control module includes a hollow plate, outrigger motors, and foot switches. The power supply module includes a switching power supply, an isolation transformer, and relays. The sensing module includes a six-dimensional force sensor and a position sensor. The control module enables trajectory planning and dynamic adjustment of the robotic arm, supporting various osteotomy path planning algorithms, including parallel layer cutting, helical cutting, and adaptive path methods. Furthermore, by combining bone density information identified through artificial intelligence, it adaptively adjusts the power parameters of the osteotomy tool to ensure cutting effects in different bone regions. The six-dimensional force sensor or torque sensor can monitor the force on the robotic arm's end effector in real time and perform closed-loop control based on feedback signals from the main control system. This ensures uniform force and precise path during osteotomy, avoiding miscuts or damage to the bone surface.

[0095] The navigation subsystem provides precise pose information and real-time feedback, ensuring accurate surgical execution. It includes a tracking module and a display module. The tracking module comprises a power supply and a binocular camera. This module can be an optical tracking device, which monitors real-time pose changes of the patient's bones and the robotic arm's end effector, ensuring precise alignment of the surgical path with the actual anatomical location. It provides intraoperative pose calibration to correct deviations caused by minor patient movements or robotic arm errors. It also monitors the distance between the robotic arm and soft tissues in real-time, ensuring the robotic arm's range of motion remains within safe boundaries to prevent soft tissue injury.

[0096] This robotic arm system, through its highly integrated, systematic, and modular design, can significantly improve osteotomy accuracy, the fit between bone surface structure and prosthesis, and surgical efficiency, providing a safer and more efficient automated osteotomy solution for orthopedic surgery.

[0097] Figure 8 A schematic diagram illustrating a method for determining motion data of a robotic arm provided for embodiments of this disclosure, as shown below. Figure 8 As shown, in the preoperative stage, the robotic arm system acquires image data and then performs intelligent segmentation and reconstruction based on artificial intelligence algorithms. Besides obtaining a 3D joint model, it also assesses bone quality and strength, performing bone density analysis and modeling. The rotation speed and torque of the power tool are adjusted based on the bone density value; higher density corresponds to higher rotation speed and torque, and lower density to lower rotation speed and torque, avoiding bone damage caused by high torque in cases of osteoporosis. After obtaining the 3D joint model, an AI-driven automatic segmentation algorithm combined with an expert knowledge graph enables intelligent prosthesis planning for knee replacement surgery. A multi-objective optimization algorithm automatically optimizes the prosthesis implantation position, angle, and osteotomy plan. The osteotomy plan can record prosthesis type, osteotomy plan, etc. The 3D joint model before osteotomy is segmented using the automatic segmentation algorithm. The knowledge graph stores force line analysis, ligament tension of the joint, force data of the left and right legs, and the correlation between the 3D joint model and the prosthesis implantation position, angle, and osteotomy plan. The 3D joint model is input into this knowledge graph to match the corresponding prosthesis implantation position, angle, and osteotomy plan. Based on the prosthesis planning results, bone registration is performed using the nearest point iterative algorithm. The functional modules in the main control system perform calculations based on the prosthesis implantation position, angle, osteotomy plan, registration results, and bone density values ​​to obtain the osteotomy data for the robotic arm. The robotic arm acquires the osteotomy data, which includes data such as power rotation speed, lesion location, tool feed rate, and boundary wall.

[0098] During the intraoperative phase, after obtaining the osteotomy data from the robotic arm, surgical path planning is executed. Depending on the stage of the surgical procedure, surgical path planning includes an approach process and a grinding process. Based on the generated osteotomy path, the power system is energized to perform bone grinding operations. The osteotomy process is divided into two modes: autonomous mode and assisted mode. In autonomous mode, the user acts only as a supervisor to improve the level of surgical intelligence. In assisted mode, the user controls the robotic arm's approach process via a foot switch and manually operates the grinding tools. Regardless of whether it is autonomous or assisted mode, the robotic arm automatically performs osteotomy operations within the planned path and safety boundaries. At the same time, the robotic arm dynamically adjusts the cutting parameters based on feedback information from the robotic arm force sensor data and navigation posture data to enhance the accuracy and safety of the operation. During the powered osteotomy grinding process, the kinematics and dynamics calculation module of the main control system performs intraoperative joint balance and checks the fit between the prosthesis and bone and the force line of the lower limb in real time.

[0099] In the postoperative stage, after the osteotomy is completed, a probe is slid across the bone surface to perform a CT view to verify the surgical effect. Finally, the entire knee replacement surgery process is completed. After the surgery, the data is saved for subsequent case follow-up.

[0100] Figure 9 A schematic diagram of an architecture provided for an embodiment of this disclosure, such as Figure 9 As shown, the entire process starts with the grid voltage, providing power to the system. Through the coordinated work of various subsystems and modules, the system's operation is safe and controllable, enabling autonomous osteotomy.

[0101] The main control subsystem receives operator commands, processes information, and coordinates the work of various subsystems. Specifically, the operator inputs operation commands through the main control system's interaction module, and the results are displayed on a screen. The interaction module converts the operator's commands into system-recognizable signals and transmits them to the host computer control module. The host computer control module, as the core control unit, receives commands from the lower-level control module, the power switch module, and the robotic arm sensing module. It then feeds back status information to the operator through the interaction module and issues specific trigger control signals to the functional modules. The lower-level control module controls the robotic arm according to the host computer commands, achieving motion control. The functional modules receive command information and execute corresponding advanced functions, such as intelligent segmentation and reconstruction, automatic prosthesis planning, skeletal registration, and motion planning and control. They also feed back status information to the host computer to monitor the overall control status and ensure stable system operation.

[0102] The navigation subsystem is responsible for acquiring image data, tracking the lesion location in real time, and assisting the robotic arm in precise positioning. After intelligent segmentation and reconstruction by the main control subsystem's functional modules, the image data yields a 3D visualization model, providing anatomical information of the surgical site as a basis for path planning and execution. Real-time position feedback ensures precise navigation and adjustment of the robotic arm during surgery. The tracking module monitors the lesion location information in real time, achieving accurate positioning of the target site during surgery. Status information is displayed through the display module, providing the navigation device's operating status and feeding it back to the operator, allowing the operator to monitor the navigation subsystem's operation at any time.

[0103] The system improves the efficiency, safety, and precision of the surgical procedure through multiple feedback mechanisms. Force feedback information monitors the force on the robotic arm in real time to prevent overload or tissue damage; end-effector pose information feedback ensures that the robotic arm's motion trajectory conforms to the planned requirements; control information feedback improves the stability of the host computer control system; and lesion location feedback improves the accurate identification and manipulation of the target area.

[0104] The robotic arm system, through the coordinated operation of the main control subsystem, navigation subsystem, and robotic arm subsystem, realizes a complete process from power supply, command input, information processing, robotic arm execution, navigation assistance to the final surgical procedure. Each module ensures precise control, safe execution, and efficient collaboration during the surgical process through efficient information exchange and real-time feedback, providing intelligent support for modern orthopedic surgery.

[0105] Figure 10 A schematic diagram of the structure of a motion data determination device for a robotic arm provided in an embodiment of this disclosure is shown.

[0106] like Figure 10 As shown, the motion data determination device 1000 for the robotic arm may include: The implantation module 1001 is used to implant the three-dimensional prosthesis model corresponding to the prosthesis into the three-dimensional joint model corresponding to the joint according to multiple implantation data, thereby obtaining multiple candidate implantation models; wherein, the implantation data and the candidate implantation models correspond one-to-one. The first determining module 1002 is used to determine multiple joint function data corresponding to the multiple candidate implantation models, and to determine the target implantation model among the multiple candidate implantation models based on the multiple joint function data. The second determining module 1003 is used to determine the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model; The planning module 1004 is used to perform motion planning processing on the robotic arm based on the grinding area to obtain motion data.

[0107] Optionally, the joint function data includes biomechanical data and joint motion data; The determination of multiple joint function data corresponding to the multiple candidate implantation models includes: The multiple candidate implantation models were subjected to stress analysis to obtain multiple biomechanical data; wherein, the biomechanical data includes at least one of contact stress distribution, shear force, reaction force, force line angle, and soft tissue tension; Multibody dynamics simulations are performed on the multiple candidate implantation models to obtain multiple joint motion data; wherein, the joint motion data includes at least one of joint range of motion, joint motion trajectory, and joint center range of motion.

[0108] Optionally, determining the target implantation model among the multiple candidate implantation models based on the multiple joint function data includes: Among the multiple candidate implantation models, the candidate implantation model whose biomechanical data meets the first screening condition and whose joint motion data meets the second screening condition is determined as the intermediate implantation model; If there are multiple intermediate implantation models, multiple comprehensive values ​​corresponding to the multiple intermediate implantation models are determined based on the biomechanical data and the joint motion data, and the target implantation model among the multiple intermediate implantation models is determined based on the multiple comprehensive values.

[0109] Optionally, determining the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model includes: The first prosthesis position of the target prosthesis model, the coordinate system transformation relationship between the model coordinate system and the physical coordinate system of the target implantation model, and the preset positional relationship between the target prosthesis and the target boundary wall are obtained. The position of the first prosthesis is transformed according to the coordinate system transformation relationship to obtain the second prosthesis position of the target prosthesis in the physical coordinate system; Based on the positional relationship and the position of the second spur, the position of the target boundary wall in the physical coordinate system is determined; The grinding area is determined based on the position of the second prosthesis and the position of the boundary wall.

[0110] Optionally, the device further includes: The first acquisition module is used to acquire multiple scan images obtained by performing continuous tomographic scanning of the joint; The segmentation module is used to perform bone segmentation processing on the multiple scanned images to obtain multiple joint images; The processing module is used to sequentially perform surface reconstruction processing, surface smoothing processing, and mesh simplification processing on the multiple joint images to obtain the three-dimensional joint model.

[0111] Optionally, the device further includes: The third determining module is used to determine the target force data and target position of the robotic arm in the current control cycle based on the motion data; The second acquisition module is used to acquire the position increment and feedback force data of the robotic arm in the previous control cycle; The correction module is used to perform vector difference calculation on the target force data and the feedback force data to obtain error force data, and input the error force data into the impedance controller to obtain the correction position; The fourth determining module is used to determine the position increment of the current control cycle based on the target position, the corrected position, and the position increment of the previous control cycle.

[0112] Optionally, the motion data includes approach motion data and operational motion data, and the device further includes: A first control operation is configured to, before the robotic arm reaches the work preparation position, respond to a user's pressing operation on a first control of the robotic arm, control the robotic arm to move toward the work preparation position according to the approach motion data, and respond to a user's releasing operation on the first control, send a first stop command to the robotic arm to stop the robotic arm from moving. The second control operation is used to, after the robotic arm reaches the work preparation position, in response to a user pressing a second control of the end effector carried by the robotic arm, control the movement of the robotic arm according to the work motion data and control the end effector to perform grinding operations; and in response to a user releasing the second control, send a second stop command to the robotic arm to stop the movement of the robotic arm and stop the grinding operations of the end effector.

[0113] It should be noted that, Figure 10 The motion data determination device 1000 of the robotic arm shown can execute each step in the above-described embodiment of the motion data determination method for the robotic arm, and realize each process and effect in the above-described embodiment of the motion data determination method for the robotic arm, which will not be elaborated here.

[0114] Figure 11 A schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure is shown.

[0115] like Figure 11 As shown, the electronic device may include a processor 1101 and a memory 1102 storing computer program instructions.

[0116] Specifically, the processor 1101 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0117] Memory 1102 may include a large-capacity storage device for information or instructions. For example, and not limitingly, memory 1102 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1102 may include removable or non-removable (or fixed) media. Where appropriate, memory 1102 may be internal or external to the integrated gateway device. In a particular embodiment, memory 1102 is a non-volatile solid-state memory. In a particular embodiment, memory 1102 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable programmable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0118] The processor 1101 reads and executes computer program instructions stored in the memory 1102 to perform the steps of the motion data determination method for the robotic arm provided in this embodiment of the present disclosure.

[0119] In one example, the electronic device may also include a transceiver 1103 and a bus 1104. Wherein, as... Figure 11 As shown, the processor 1101, memory 1102 and transceiver 1103 are connected via bus 1104 and communicate with each other.

[0120] Bus 1104 may include hardware, software, or both. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 1104 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0121] The following are embodiments of a computer-readable storage medium provided in this disclosure. This computer-readable storage medium and the motion data determination method for the robotic arm in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the computer-readable storage medium, please refer to the embodiments of the motion data determination method for the robotic arm described above.

[0122] This embodiment provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a method for determining motion data of a robotic arm.

[0123] Of course, the computer-executable instructions provided in the embodiments of this disclosure are not limited to the above-described method operations, but can also perform related operations in the motion data determination method for the robotic arm provided in any embodiment of this disclosure.

[0124] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this disclosure can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer cloud platform (which may be a personal computer, server, or network cloud platform, etc.) to execute the motion data determination method for the robotic arm provided in the various embodiments of this disclosure.

[0125] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0126] Note that the above description is merely a preferred embodiment and the technical principles employed in this disclosure. Those skilled in the art will understand that this disclosure is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this disclosure. Therefore, although this disclosure has been described in detail through the above embodiments, it is not limited to the above embodiments. Many other equivalent embodiments may be included without departing from the concept of this disclosure, and the scope of this disclosure is determined by the scope of the appended claims.

Claims

1. A method for determining motion data of a robotic arm, characterized in that, include: Based on multiple implantation data, the three-dimensional prosthesis model corresponding to the prosthesis is implanted into the three-dimensional joint model corresponding to the joint to obtain multiple candidate implantation models; wherein, the implantation data and the candidate implantation models correspond one-to-one. Determine multiple joint function data corresponding to the multiple candidate implantation models, and determine the target implantation model among the multiple candidate implantation models based on the multiple joint function data; The grinding area corresponding to the joint is determined based on the position of the target prosthesis model in the target implantation model; Motion planning is performed on the robotic arm based on the grinding area to obtain motion data.

2. The method according to claim 1, characterized in that, The joint function data includes biomechanical data and joint motion data; The determination of multiple joint function data corresponding to the multiple candidate implantation models includes: The multiple candidate implantation models were subjected to stress analysis to obtain multiple biomechanical data; wherein, the biomechanical data includes at least one of contact stress distribution, shear force, reaction force, force line angle, and soft tissue tension; Multibody dynamics simulations are performed on the multiple candidate implantation models to obtain multiple joint motion data; wherein, the joint motion data includes at least one of joint range of motion, joint motion trajectory, and joint center range of motion.

3. The method according to claim 2, characterized in that, The step of determining the target implantation model among the multiple candidate implantation models based on the multiple joint function data includes: Among the multiple candidate implantation models, the candidate implantation model whose biomechanical data meets the first screening condition and whose joint motion data meets the second screening condition is determined as the intermediate implantation model; If there are multiple intermediate implantation models, multiple comprehensive values ​​corresponding to the multiple intermediate implantation models are determined based on the biomechanical data and the joint motion data, and the target implantation model among the multiple intermediate implantation models is determined based on the multiple comprehensive values.

4. The method according to claim 1, characterized in that, Determining the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model includes: The first prosthesis position of the target prosthesis model, the coordinate system transformation relationship between the model coordinate system and the physical coordinate system of the target implantation model, and the preset positional relationship between the target prosthesis and the target boundary wall are obtained. The position of the first prosthesis is transformed according to the coordinate system transformation relationship to obtain the second prosthesis position of the target prosthesis in the physical coordinate system; Based on the positional relationship and the position of the second spur, the position of the target boundary wall in the physical coordinate system is determined; The grinding area is determined based on the position of the second prosthesis and the position of the boundary wall.

5. The method according to claim 1, characterized in that, The method further includes: Acquire multiple scan images obtained by continuous tomographic scanning of the joint; The multiple scanned images are subjected to bone segmentation processing to obtain multiple joint images; The surface reconstruction, surface smoothing, and mesh simplification processes are sequentially performed on the multiple joint images to obtain the three-dimensional joint model.

6. The method according to claim 1, characterized in that, The method further includes: The target force data and target position of the robotic arm in the current control cycle are determined based on the motion data. Acquire the position increment and feedback force data of the robotic arm in the previous control cycle; The target force data and the feedback force data are used to calculate the vector difference to obtain the error force data. The error force data is then input into the impedance controller to obtain the correction position. The position increment of the current control cycle is determined based on the target position, the corrected position, and the position increment of the previous control cycle.

7. The method according to claim 1, characterized in that, The motion data includes approach motion data and task motion data, and the method further includes: Before the robotic arm reaches the work preparation position, in response to the user's pressing operation on the first control of the robotic arm, the robotic arm is controlled to move towards the work preparation position according to the approach motion data. In response to the user's popping operation on the first control, a first stop command is sent to the robotic arm to stop the robotic arm from moving. After the robotic arm reaches the work preparation position, in response to the user pressing the second control of the end effector carried by the robotic arm, the robotic arm is controlled to move according to the work motion data and the end effector is controlled to perform grinding operations. In response to the user releasing the second control, a second stop command is sent to the robotic arm to stop the robotic arm and the end effector to stop grinding operations.

8. A motion data determination device for a robotic arm, characterized in that, include: An implantation module is used to implant the three-dimensional prosthesis model corresponding to the prosthesis into the three-dimensional joint model corresponding to the joint based on multiple implantation data, thereby obtaining multiple candidate implantation models; wherein, the implantation data and the candidate implantation models correspond one-to-one. The first determining module is used to determine multiple joint function data corresponding to the multiple candidate implantation models, and to determine the target implantation model among the multiple candidate implantation models based on the multiple joint function data. The second determining module is used to determine the grinding area corresponding to the joint based on the position of the target prosthesis model in the target implantation model; The planning module is used to perform motion planning processing on the robotic arm based on the grinding area to obtain motion data.

9. An electronic device, characterized in that, include: processor; Memory, used to store executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method of any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The storage medium stores a computer program that, when executed by a processor, causes the processor to implement the method described in any one of claims 1-7.

Images