A master-slave hybrid surgical robotic system and control method

Abstract

The present application provides a master-slave hybrid surgical robot system and a control method. The system includes: a preoperative planning module for generating a three-dimensional surgical plan; an intraoperative registration module for performing registration mapping; a passive robotic arm composed of at least one unpowered passive joint for联动 with the surgeon to indicate the positioning range for the surgeon to roughly position the end tool; and an active robotic arm for planning the movement path of the end tool to reach the target pose within the positioning range indicated by the passive robotic arm based on the registration mapping result of the intraoperative registration module, and controlling the end tool to reach the target pose along the movement path and perform surgical operations along the surgical path. By adopting a master-slave hybrid architecture, the rough positioning of the passive arm retains the surgical experience and intuitive judgment of the surgeon, and the precise execution of the active arm ensures the high precision of the surgical path, realizing the complementary advantages of human-machine cooperation.

Description

Technical Field

[0001] This application relates to the field of medical device technology, and more specifically, to a hybrid active and passive surgical robot system and method. Background Technology

[0002] Currently, the mainstream form of orthopedic surgical robots is the fully active robotic arm system, where all joints of the robotic arm are driven by servo motors, and the surgeon remotely controls it via a console or the system performs the surgery autonomously. While this fully active architecture has advantages in precision and automation, in fully active mode, there is a lack of direct physical interaction between the surgeon and the robotic arm. The surgeon finds it difficult to quickly intervene in the initial positioning of the robotic arm based on their own experience, resulting in longer surgical preparation time and insufficient flexibility. Summary of the Invention

[0003] To address the aforementioned problems, the first aspect of this application provides a hybrid active-passive surgical robot system, comprising: The preoperative planning module is used to generate a three-dimensional surgical plan based on the patient's preoperative imaging data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundaries. The intraoperative registration module is used to register and map the three-dimensional surgical plan generated by the preoperative planning module with the actual intraoperative anatomical space through a navigator and a tracer. A passive robotic arm, consisting of at least one unpowered passive joint, is used to interact with the operator and indicate the positioning range for the operator to perform coarse positioning of the end effector. An active robotic arm, mounted at the distal end of the passive robotic arm, consists of multiple servo-driven active joints. Within the positioning range indicated by the passive robotic arm, it plans the motion path of the end-effector to the target pose based on the registration mapping results of the intraoperative registration module, and controls the end-effector to reach the target pose along the motion path and perform surgical operations along the surgical path.

[0004] The second aspect of this application provides a hybrid active-passive control method for a surgical robot system, comprising: A three-dimensional surgical plan is generated based on the patient's preoperative imaging data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundaries. The three-dimensional surgical plan is registered and mapped with the actual intraoperative anatomical space using a navigator and a tracer; The operator pushes the passive robotic arm and locks the joint after reaching the target positioning range according to the coarse positioning navigation instructions; Within the target positioning range, the active robotic arm plans the motion path of the end effector based on the registration mapping results, and controls the end effector to reach the target pose along the motion path and perform surgical operations along the surgical path.

[0005] A third aspect of this application provides an electronic device comprising: a memory and a processor; The memory is used to store programs; The processor, coupled to the memory, is used to execute the program to implement the above-described active-passive hybrid surgical robot system control method.

[0006] The fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the above-described active-passive hybrid surgical robot system control method.

[0007] This application adopts a hybrid active-passive architecture, with a passive joint at the proximal end that is manually pushed by the surgeon to achieve coarse positioning, and a servo-driven active joint at the distal end to achieve precise path planning and surgical execution. The coarse positioning of the passive arm retains the surgeon's surgical experience and intuitive judgment, while the precise execution of the active arm ensures the high accuracy of the surgical path, realizing the complementary advantages of human-machine collaboration. Attached Figure Description

[0008] Figure 1 This is a hardware schematic diagram of a hybrid active-passive surgical robot system according to an embodiment of this application; Figure 2 This is a detailed architecture diagram of a hybrid active-passive surgical robot system according to an embodiment of this application; Figure 3 This is a schematic diagram illustrating the coordinated switching between active and passive modes in a hybrid active-passive surgical robot system according to an embodiment of this application. Figure 4 This is a flowchart of a hybrid active-passive surgical robot system control method according to an embodiment of this application; Figure 5 This is an architectural diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0009] To make the above-mentioned objects, features, and advantages of this application more apparent and understandable, specific embodiments of this application will be described in detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0010] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application pertains.

[0011] For ease of understanding, the following terms may be used and are explained below: This application provides a hybrid active-passive surgical robot system, the specific solution of which is as follows: Figures 1-3 As shown.

[0012] Combination Figure 1 , Figure 2 The diagram shown is an architectural diagram of a hybrid active-passive surgical robot system according to an embodiment of this application; wherein, the hybrid active-passive surgical robot system includes: The preoperative planning module is used to generate a three-dimensional surgical plan based on the patient's preoperative imaging data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundaries. The intraoperative registration module is used to register and map the three-dimensional surgical plan generated by the preoperative planning module with the actual intraoperative anatomical space through a navigator and a tracer. A passive robotic arm, consisting of at least one unpowered passive joint, is used to interact with the operator and indicate the positioning range for the operator to perform coarse positioning of the end effector. An active robotic arm, mounted at the distal end of the passive robotic arm, is used to plan the motion path of the end-effector to the target pose based on the registration mapping results of the intraoperative registration module within the positioning range indicated by the passive robotic arm, and to control the end-effector to reach the target pose along the motion path and to perform surgical operations along the surgical path.

[0013] In this application, the core concept of the active-passive hybrid architecture is to physically separate the coarse positioning function and the fine-tuning execution function of the robotic arm. The proximal passive robotic arm is not equipped with any drive motors. The surgeon moves it to the vicinity of the surgical target area by manually pushing it, and the navigation system guides the surgeon in real time to complete coarse positioning and lock the joints. The distal active robotic arm, within the limited workspace after the passive arm is locked, is driven by servo motors to achieve precise path planning, dynamic compensation, and force control execution. Compared with a fully active system, this architecture significantly reduces the number of servo motors required, reducing costs and complexity. At the same time, the rigid support frame formed after the passive joint is locked provides a natural mechanical constraint for the active joint. Even if the active joint experiences a control malfunction, its range of motion is limited to the workspace defined by the passive arm, providing inherent safety assurance.

[0014] This application adopts a hybrid active-passive architecture, with a passive joint at the proximal end that is manually pushed by the surgeon to achieve coarse positioning, and a servo-driven active joint at the distal end to achieve precise path planning and surgical execution. The coarse positioning of the passive arm retains the surgeon's surgical experience and intuitive judgment, while the precise execution of the active arm ensures the high accuracy of the surgical path, realizing the complementary advantages of human-machine collaboration.

[0015] Preferably, the preoperative planning module is used to generate a three-dimensional surgical plan based on the patient's preoperative imaging data and cold-region-specific bone data. The three-dimensional surgical plan includes a surgical path, target pose, and safety boundaries.

[0016] In this application, the introduction of cold-region-specific bone data enables the system to be adapted to the bone characteristics of patients who have long been exposed to cold / high-latitude environments. People living in cold environments for extended periods are prone to localized bone loss and increased accumulation of microcracks due to low temperatures and insufficient sunlight, making them more susceptible to occult bone fractures or drill bit edge breakage during surgery. This application, by incorporating cold-region-specific bone data into the preoperative planning stage and employing a microcrack-protective motion strategy by the active robotic arm during the intraoperative execution stage, effectively reduces additional damage to the fragile bone tissue of patients in cold regions during surgery.

[0017] This application employs a hybrid active-passive architecture, using a passive joint without power at the proximal end for coarse positioning by manual pushing by the surgeon, and a servo-driven active joint at the distal end for precise path planning and surgical execution. Combined with cold-region-specific bone data and a microcrack-protective motion strategy, it reduces system costs and complexity while ensuring surgical accuracy and safety, making it particularly suitable for orthopedic surgery for patients with osteoporosis in cold regions.

[0018] In this application, a hybrid active-passive architecture is used to organically combine the coarse positioning of a passive robotic arm with the fine-tuning execution of an active robotic arm. The proximal end employs a passive joint without power, manually pushed by the surgeon to achieve large-scale coarse positioning, while the distal end uses a small number of servo-driven active joints to achieve precise path planning, dynamic compensation, and force control execution. This architecture reduces the number of motors and system cost while utilizing the mechanical confinement characteristics of the passive joints to provide inherent safety boundaries for the active joints. Combined with cold-climate-specific bone data and microcrack-protective motion strategies, it significantly improves the precision and safety of surgery, making it particularly suitable for orthopedic surgery on patients with osteoporosis in cold climates.

[0019] In one implementation, combined with Figure 1 , Figure 2 As shown, the passive robotic arm includes: The multi-degree-of-freedom passive joint assembly consists of multiple rotational and / or spherical passive joints, each of which is equipped with a joint locking mechanism to lock the joint after the operator pushes the passive robotic arm to the target area; The coarse positioning navigation instruction module is used to calculate the deviation between the current end position and the target positioning range in real time based on the registration mapping results during the operation of the operator pushing the passive robotic arm, and to indicate the current positioning status and adjustment direction to the operator through the display interface.

[0020] The multi-degree-of-freedom passive joint assembly consists of multiple rotary and / or spherical passive joints connected in series. Each passive joint is equipped with a joint locking mechanism to lock the joint after the surgeon pushes the passive robotic arm to the target area. The passive joint assembly typically includes a combination of multiple rotary and spherical joints, providing multiple degrees of freedom of movement, allowing the passive robotic arm to cover a large working range. The joint locking mechanism of each passive joint can employ electromagnetic locking, pneumatic locking, or mechanical locking, etc. After the surgeon pushes the passive robotic arm to the target area, all passive joints are locked through a unified locking command or a joint-by-joint locking method, transforming the entire passive robotic arm into a rigid support frame, providing a stable base for the distal active robotic arm.

[0021] The coarse positioning navigation instruction module is used to calculate the deviation between the current end effector position and the target positioning range in real time based on the registration mapping results during the surgeon's movement of the passive robotic arm. It then displays the current positioning status and adjustment direction to the surgeon via a screen. The coarse positioning navigation instruction module obtains the real-time spatial position of the passive robotic arm's end effector through the intraoperative registration module, compares it with the pre-planned target positioning range, and calculates the distance and attitude deviations between the current end effector position and the center of the target positioning range. The screen displays the current state of the passive robotic arm's end effector relative to the target area in a clear and intuitive way (e.g., a bullseye diagram, distance gradient bars, and direction arrows), guiding the surgeon to move the passive robotic arm closer to the target area along the optimal path. When the end effector enters the target positioning range, the screen provides a confirmation prompt, instructing the surgeon to perform a joint locking operation.

[0022] In one embodiment, the active robotic arm includes: The multi-degree-of-freedom servo joint group consists of multiple active joints driven by servo motors. Each active joint is equipped with a position encoder and a torque sensor to achieve precise pose control of the end tool. The motion path planning unit is used to plan the motion path of the end effector from the current pose to the target pose based on the registration mapping result of the intraoperative registration module after the passive robotic arm is locked. The intraoperative dynamic compensation unit is used to track changes in the patient's position in real time through the navigator and tracker during the operation and automatically compensate for the positional deviation of the end effector. The end-effector force sensing unit is used to collect the interaction force information between the end-effector and bone tissue in real time through the torque sensor, and combine it with the three-dimensional distribution data of bone density to generate the real-time bone state of the current surgical area, so as to correct the surgical action and / or surgical path of the end-effector.

[0023] In one embodiment, the active robotic arm preferably comprises: The multi-degree-of-freedom servo joint group consists of multiple active joints driven by servo motors. Each active joint is equipped with a position encoder and a torque sensor to achieve precise pose control of the end tool. The motion path planning unit is used to plan the motion path of the end tool from the current pose to the target pose according to the registration mapping result of the intraoperative registration module after the passive robotic arm is locked, and automatically embed segmented feed, pulse propulsion and drill unloading operations into the surgical execution trajectory according to the microcrack protection motion strategy parameters determined by cold-region specific bone data. The intraoperative dynamic compensation unit is used to track changes in the patient's position in real time through the navigator and tracker during the operation, and drive the servo joint group to automatically compensate for the pose offset of the end effector. The end-effector force sensing unit is used to collect the interaction force information between the end-effector and bone tissue in real time through the torque sensor, and combine it with the three-dimensional distribution data of bone density to generate the real-time bone state of the current surgical area, so as to correct the surgical action and / or surgical path of the end-effector.

[0024] The multi-degree-of-freedom servo joint assembly consists of multiple active joints driven by servo motors. Each active joint is equipped with a position encoder and a torque sensor to achieve precise pose control of the end effector. The servo motors can be brushless DC motors or frameless torque motors, combined with planetary reducers or harmonic reducers to achieve high-precision output. The position encoder of each active joint provides accurate measurement of the joint angle (e.g., resolution better than 0.001 degrees), and the torque sensor is used to measure the joint output torque in real time. Together, they form the basis of joint-level position-force dual closed-loop control. The number of degrees of freedom of the active robotic arm is typically 3 to 6, configured according to the type of surgery.

[0025] The motion path planning unit, after the passive robotic arm is locked, plans the motion path of the end effector from the current pose to the target pose based on the registration mapping results of the intraoperative registration module. It also automatically embeds segmented feed, pulse propulsion, and drill retraction / unloading operations into the surgical trajectory based on microcrack protection motion strategy parameters determined from cold-region-specific bone data. After the passive robotic arm is locked, the motion path planning unit first acquires the current end effector pose of the active robotic arm, and then plans a collision-free optimal path from the current pose to the target pose in the registered intraoperative coordinate system. When generating the surgical trajectory, it automatically embeds microcrack protection motion strategies into the trajectory based on cold-region-specific bone parameters (including cumulative bone microcrack density and bone risk stratification level) determined during the preoperative planning stage. Specifically, this includes shortening the segmented feed length and increasing the pause time in high-density microcrack areas, using intermittent pulse force output instead of continuous constant force propulsion, and automatically adjusting the retraction depth and frequency of drill retraction / unloading according to the risk level.

[0026] The intraoperative dynamic compensation unit tracks patient position changes in real time via the navigator and tracker during surgery, and drives the servo joint assembly to automatically compensate for end-effector pose shifts. During surgery, the patient's bones may experience slight displacement or rotation due to respiratory movements, muscle relaxation, or external forces. The intraoperative dynamic compensation unit continuously monitors the position changes of the tracker mounted on the patient's bones, calculates the patient's positional shift in real time, and converts this shift into compensating motion commands for the active joints. This drives the servo joint assembly to automatically adjust the end-effector pose, ensuring that the end-effector remains precisely aligned with the pre-planned path.

[0027] The end-effector force sensing unit is used to collect real-time interaction force information between the end-effector and bone tissue via the torque sensor. Combined with three-dimensional bone density distribution data, it generates the real-time bone state of the current surgical area to correct the surgical movements and / or surgical path of the end-effector. The end-effector force sensing unit utilizes torque sensor data mounted on the active joint to calculate the external interaction forces and torques acting on the end-effector through a robot dynamics model. The real-time measured interaction force information is compared with the expected bone tissue mechanical parameters in the preoperative three-dimensional bone density distribution data to generate a real-time bone state assessment of the current surgical area, including bone tissue stiffness, real-time mechanical impedance, and whether abnormal mechanical responses (such as cortical bone penetration, microcrack propagation, etc.) occur in the current contact area. When an abnormal bone state is detected, the surgical movement parameters of the end-effector are automatically corrected (e.g., reducing feed speed, reducing feed force) or the surgical path is adjusted to bypass the abnormal area.

[0028] In one implementation, the preoperative planning module is further configured to: Based on the surgical path and target pose in the three-dimensional surgical plan, and combined with the kinematic parameters of the passive and active robotic arms, the target positioning range of the passive robotic arm is planned so that the active robotic arm can reach all planned target poses within the target positioning range. After the target positioning range is determined, the motion path of the end effector of the active robotic arm from the initial pose to each target pose is planned, as well as the execution trajectory for performing surgical operations along the surgical path.

[0029] Specifically, based on the surgical path and target pose in the 3D surgical plan, and combined with the kinematic parameters of the passive and active robotic arms, the target positioning range of the passive robotic arm is planned. After generating the 3D surgical plan, the preoperative planning module performs inverse kinematics analysis based on the kinematic model of the active robotic arm (including the range of motion of each active joint, the reachable workspace of the end effector, etc.) to determine the base position range required for the active robotic arm to reach all planned target poses. This base position range is the target positioning range that the passive robotic arm needs to reach. During planning, it must be ensured that within this target positioning range, all planned target poses of the active robotic arm are within its effective workspace, and that none of the joints reach their motion limits.

[0030] After the target positioning range is determined, the motion path of the end effector of the active robotic arm from the initial pose to each target pose, as well as the execution trajectory for performing surgical operations along the surgical path, are planned. After the target positioning range of the passive robotic arm is determined, the preoperative planning module plans the approach path of the end effector from the initial pose (i.e., the zero position or home position of the active arm after the passive arm is locked) to each surgical target pose within the workspace of the active robotic arm, as well as the execution trajectory for performing surgical operations such as osteotomy, drilling, and screw placement along the surgical path from the target pose. This planning process comprehensively considers factors such as the smoothness of the joint space, the shortest path in Cartesian space, obstacle avoidance constraints, and mechanical safety constraints.

[0031] In one implementation, combined with Figure 3 As shown, the hybrid active-passive surgical robot system further includes an active-passive coordination switching module, which is used for: During the coarse positioning stage, the distance and posture deviation between the end effector of the passive robotic arm and the target positioning range are calculated in real time, and guidance instructions are provided to the operator through a visual interface; after the operator confirms that the passive joint is locked, the control is automatically switched to the active execution mode. In active execution mode, if it is detected that the positioning range of the passive robotic arm needs to be adjusted, the operation of the active robotic arm is paused and switched back to passive positioning mode.

[0032] In one implementation, combined with Figure 3 As shown, the active / passive coordination switching module is preferably used for: During the coarse positioning phase when the operator pushes the passive robotic arm, the distance and attitude deviation between the end of the passive robotic arm and the target positioning range are calculated in real time, and guidance instructions are provided to the operator through a visual interface. When the end of the passive robotic arm enters the target positioning range and the posture deviation is less than a preset threshold, it sends a positioning confirmation signal and automatically switches the control from passive positioning mode to active execution mode after the operator confirms that the passive joint is locked. In active execution mode, if it is detected that the positioning range of the passive robotic arm needs to be adjusted, the operation of the active robotic arm is paused, the passive joint lock is released, and the system switches back to passive positioning mode to wait for the surgeon to re-coarsely position the target.

[0033] The active-passive coordination switching module is used to manage the switching of working modes between the passive robotic arm and the active robotic arm, ensuring the coordinated operation of the two robotic arms.

[0034] During the coarse positioning phase, when the surgeon pushes the passive robotic arm, the active-passive coordination switching module calculates the distance and attitude deviation between the passive robotic arm's end effector and the target positioning range in real time, and provides guidance to the surgeon through a visual interface. During this phase, the active robotic arm is in standby mode and does not perform any movement. The system displays the relative position of the passive robotic arm's end effector to the target positioning range in real time through a visual interface, using color coding (e.g., red for moving away, yellow for moving closer, and green for being in position) and directional arrows to guide the surgeon in pushing the passive robotic arm to the target area.

[0035] When the passive robotic arm's end effector enters the target positioning range and the posture deviation is less than a preset threshold, the active-passive coordination switching module sends a positioning confirmation signal, notifying the surgeon through audio-visual prompts that the current position meets the coarse positioning requirements. After the surgeon confirms that the position is appropriate, they perform a joint locking operation. Once the active-passive coordination switching module detects that all passive joints have been reliably locked, it automatically switches system control from passive positioning mode to active execution mode, activating the active robotic arm to begin planning and executing the surgical procedure.

[0036] In active execution mode, if a situation is detected requiring adjustment of the passive robotic arm's positioning range (e.g., changing the surgical target during surgery, insufficient workspace of the active arm to cover the new target pose, or a significant change in patient position exceeding the active compensation range), the active-passive coordination switching module pauses the operation of the active robotic arm, retracts the end effector to a safe position, then releases the passive joint lock and switches back to passive positioning mode to await the surgeon's re-coarse positioning. This bidirectional switching mechanism ensures the system's flexibility and safety throughout the entire surgical procedure.

[0037] In one implementation, combined with Figure 2 As shown, the hybrid active-passive surgical robot system further includes a safety monitoring module, which is used for: After the passive robotic arm locks its joints, the locking status of each passive joint is detected. Once the locking is confirmed to be reliable, the active robotic arm is allowed to start and perform the operation. During the operation of the active robotic arm, the position and force of the end tool are monitored in real time. When the end tool deviates from the safety boundary or the force exceeds the preset threshold, the active robotic arm is triggered to brake and issue a warning. When an abnormal joint locking state of the passive robotic arm is detected, the execution operation of the active robotic arm is terminated.

[0038] Preferably, the security monitoring module is used for: After the passive robotic arm reaches the target positioning range and locks the joints, the locking status of each passive joint is detected, and the active robotic arm is allowed to start and perform operations only after the locking is confirmed to be reliable. During the operation of the active robotic arm, the position and force of the end tool are monitored in real time. When the end tool deviates from the safety boundary or the force exceeds the preset threshold, the active robotic arm is triggered to brake and issue a warning. When an abnormal joint locking state of the passive robotic arm is detected, the operation of the active robotic arm is immediately stopped and the end effector is withdrawn to a safe position.

[0039] The safety monitoring module is present throughout the entire surgical procedure, providing multi-layered safety assurance.

[0040] After the passive robotic arm reaches the target positioning range and locks its joints, the safety monitoring module detects the locking status of each passive joint. This locking status detection includes checking whether the locking torque of each passive joint's locking mechanism reaches a preset safety threshold, and applying a preset test torque to the locked passive arm to verify whether its rigidity meets the surgical requirements. Only after all passive joints have passed the safety check will the safety monitoring module allow the active robotic arm to start performing the operation.

[0041] During the operation of the active robotic arm, the safety monitoring module monitors the pose and force of the end effector in real time. The pose monitoring uses dual-channel pose estimation from a navigator and encoder for cross-validation to ensure the reliability of the pose measurement. The force monitoring uses a torque sensor to acquire the interaction force between the end effector and bone tissue in real time. When the end effector deviates from the safety boundary (i.e., exceeds the safe operating range determined in the pre-operative plan) or the force exceeds a preset threshold (i.e., the interaction force exceeds the safe bearing capacity of the bone tissue), the safety monitoring module immediately triggers the active robotic arm to brake, stopping all movement and issuing an audible and visual warning. Operation can only continue after the surgeon's confirmation.

[0042] When an abnormal joint locking state of the passive robotic arm is detected (e.g., the locking torque of a passive joint is below a safety threshold, or a mechanical failure occurs in the locking mechanism), the safety monitoring module immediately stops the operation of the active robotic arm, retracts the end effector along a safe retraction path to a safe position away from bone tissue, and notifies the surgeon via audio-visual and interface alerts. Passive joint locking abnormalities are the highest priority safety event because the rigid support of the passive arm is the foundation for the precise execution of the active arm; any displacement of the passive arm will directly lead to the failure of the surgical coordinate system.

[0043] In one implementation, combined with Figure 2 As shown, the aforementioned active-passive hybrid surgical robot system further includes: The intelligent assessment module is used to conduct targeted disease assessments on patients based on their medical data and cold-region-specific data, generating personalized auxiliary assessment results for each patient. The auxiliary rehabilitation module is used to generate personalized preoperative rehabilitation plans for patients based on their medical data, surgical plans, and cold-region-specific data; and to generate personalized postoperative rehabilitation plans for patients based on their medical data, postoperative assessment results, and cold-region-specific data.

[0044] The intelligent assessment module is used to conduct targeted disease assessments of patients based on their medical data and cold-region-specific data, generating personalized auxiliary assessment results for each patient.

[0045] The core of the intelligent assessment module is a multi-task deep learning model. This model is based on a hybrid architecture of convolutional neural networks (CNN) and fully connected networks, which can simultaneously process image data and structured clinical data to output personalized disease assessment results.

[0046] The specific architecture of the model is as follows: Image Feature Extraction Branch: A ResNet-50-based convolutional neural network is used as the backbone network for image feature extraction. The input is a slice of the patient's CT or MRI image, normalized to 512×512 pixels. The network contains four residual stages, with 3, 4, 6, and 3 residual blocks respectively. Each residual block contains three convolutional layers: 1×1, 3×3, and 1×1. Feature residual learning is achieved through skip connections. After global average pooling, a 2048-dimensional image feature vector is output. This branch design enables the network to automatically learn imaging features such as bone microstructure, joint space, and soft tissue morphology without the need for manually designing feature extraction rules.

[0047] Clinical data processing branch: A multi-layer fully connected network is used to process structured clinical data. The input is a preprocessed clinical feature vector, with the dimension dynamically determined based on the number of features. The network consists of three fully connected layers with 256, 128, and 64 neurons respectively. Each layer is followed by a BatchNorm layer, a ReLU activation function, and a Dropout layer (dropout rate of 0.3) to prevent overfitting. The output is a 64-dimensional clinical feature vector.

[0048] Cold-region-specific data processing branch: A dedicated fully connected network is used to process cold-region-specific data. The input cold-region-specific feature vector is processed through two fully connected layers (64 and 32 neurons respectively), each followed by a BatchNorm layer and a ReLU activation function, outputting a 32-dimensional cold-region-specific feature vector. The independent design of this branch allows the model to focus on learning the influence of cold environmental factors on disease states.

[0049] Multimodal feature fusion layer: The image feature vector (2048-dimensional), clinical feature vector (64-dimensional), and cold-region-specific feature vector (32-dimensional) are concatenated to obtain a 2144-dimensional fused feature vector. This fused feature vector passes through two fully connected layers (512 and 256 neurons respectively), each followed by a BatchNorm layer and a ReLU activation function to achieve deep interaction and fusion of cross-modal features.

[0050] Multi-task output layer: The fused feature vectors are fed into multiple parallel output heads, each corresponding to an evaluation task. In a specific embodiment, the output heads include: an osteoporosis risk assessment head (outputting fracture risk probability values, using a sigmoid activation function), a joint degeneration assessment head (outputting the probability distribution of the Kellgren-Lawrence grade, using a softmax activation function), a surgical difficulty assessment head (outputting a comprehensive surgical difficulty score, using a linear activation function), and a cold-related complication risk assessment head (outputting the risk probability of specific complications in cold environments, such as increased joint stiffness and delayed wound healing, using a sigmoid activation function).

[0051] The training process of the above multi-task deep learning model is as follows: A phased training strategy is adopted. In the first phase, the ResNet-50 backbone network is initialized using ImageNet pre-trained weights, the backbone network parameters are frozen, and only the clinical data processing branch, the cold-region-specific data processing branch, the multimodal fusion layer, and the multi-task output layer are trained. The learning rate is set to 1×10⁻³, and the Adam optimizer is used for training for 50 epochs. In the second phase, the last two residual phases of the ResNet-50 backbone network are unfrozen, and a smaller learning rate (1×10⁻³) is used. 4The entire network was trained end-to-end for 100 epochs. Throughout the training process, a cosine annealing learning rate scheduling strategy was employed, with a warm restart period of 20 epochs. After each epoch, model performance was evaluated on the validation set using an early stopping strategy: training stopped when the total loss on the validation set no longer decreased for 15 consecutive epochs, and the optimal model parameters from the validation set were saved. The batch size was set to 32.

[0052] In this application, the preoperative rehabilitation plan generation model adopts an encoder-decoder architecture. The encoder part includes three parallel feature extraction branches: the first branch uses a one-dimensional convolutional neural network to process the patient's temporal medical data (such as data from previous physical examinations, bone density change trends, etc.), consisting of three one-dimensional convolutional layers with kernel sizes of 7, 5, and 3, and channel numbers of 32, 64, and 128, respectively. Each layer is followed by a BatchNorm layer, a ReLU activation function, and a max pooling layer, finally outputting a 128-dimensional feature vector through global average pooling; the second branch uses a fully connected network to process static clinical data and surgical planning parameters (such as surgical type, prosthesis specifications, approach method, etc.), consisting of two fully connected layers, outputting a 64-dimensional feature vector; the third branch uses a fully connected network to process cold-region-specific data, outputting a 32-dimensional feature vector. The outputs of the three branches are concatenated and then passed through an attention mechanism layer for adaptive adjustment of feature weights before being fed into the decoder.

[0053] The decoder section employs a multi-layer fully connected network to sequentially output the various components of the preoperative rehabilitation plan, including: a preoperative functional exercise plan (containing recommended values ​​for specific exercise types, intensity, frequency, and duration), a preoperative nutritional supplementation plan (containing recommended vitamin D supplement dosage, calcium supplement dosage, and protein intake, and personalized adjustments based on baseline vitamin D levels and sunlight conditions from cold-region-specific data), preoperative psychological preparation suggestions, and preoperative environmental adaptation suggestions (such as strategies for keeping warm in cold weather and alternative indoor exercise options).

[0054] In this application, the postoperative rehabilitation plan generation model also adopts an encoder-decoder architecture, but a postoperative assessment data processing branch is added to the encoder. Postoperative assessment data includes: actual surgical operation records (such as actual surgical path deviation, actual prosthesis installation angle, etc.), immediate postoperative imaging assessment results, postoperative pain assessment scores, and initial postoperative motor function assessment data. This branch uses a one-dimensional convolutional network to process the temporal postoperative assessment data, outputting a 64-dimensional feature vector.

[0055] The decoder outputs the various components of the postoperative rehabilitation plan, including: a phased functional exercise plan (dividing the rehabilitation process into acute, recovery, and intensive phases, with each phase containing a specific exercise prescription; the type and intensity of exercise are personalized based on the patient's postoperative condition and cold-climate-specific data, such as increasing the proportion of indoor exercise and reducing exercise intensity in cold seasons to avoid the risk of muscle damage in low-temperature environments), a weight-bearing progression plan (determining the time points for permissible weight-bearing and the strategy for gradually increasing weight based on bone density data and surgical type), a medication management plan (including recommendations for the use of analgesics, management of anticoagulants, and adjustments to osteoporosis treatment medications), a nutritional management plan (personalized based on the characteristics of cold-climate diets and nutritional needs), and recommendations for adapting to the rehabilitation environment (such as joint protection measures in cold environments, and recommendations for preventing slips and falls).

[0056] The training process of the rehabilitation program generation model is as follows: Model training: The one-dimensional convolutional network branch in the encoder part is initialized using Xavier, and the fully connected network branch is initialized using He. The training loss function is the multi-component mean squared error loss, which is the weighted sum of the mean squared errors between each output element of the rehabilitation program (exercise prescription parameters, nutritional supplementation parameters, etc.) and the label value. The Adam optimizer is used, with an initial learning rate of 5×10⁻⁻⁶. 4 The batch size is 16, and training lasts for 200 epochs. A cosine annealing learning rate scheduling strategy is used, with a warm restart cycle of 30 epochs. An early stopping strategy is employed on the validation set, with a patience value set to 20 epochs.

[0057] In one implementation, the surgical planning module is specifically used for: A three-dimensional skeletal model is constructed based on the patient's medical images; Based on a 3D skeletal model, targeted surgical planning is performed for patients, generating personalized 3D surgical plans. Acquire cold-region-specific data of the patient, which is generated based on the patient's medical images; The three-dimensional surgical plan was revised based on cold-region-specific data.

[0058] The modified surgical planning scheme described in this application may include biomechanical modifications.

[0059] In one implementation, in constructing a three-dimensional skeletal model based on a patient's medical images, the skeletal medical images are segmented using a segmentation model, and then a three-dimensional skeletal model is constructed based on the bone edges in the segmentation results.

[0060] In one implementation, the segmentation process of the segmentation model includes: The image to be segmented is downsampled sequentially to obtain downsampled images at multiple levels; Upsampling based on multi-scale extraction and multi-attention extraction is performed sequentially on downsampled images at multiple levels to obtain upsampled images at multiple levels. The highest-level upsampled image is processed to obtain the segmentation result.

[0061] Specifically, in the segmentation process: The image to be segmented is downsampled sequentially to obtain the first downsampled image, the second downsampled image, the third downsampled image, the fourth downsampled image, and the fifth downsampled image. Multi-scale extraction processing is performed on the fifth downsampled image to obtain the fifth upsampled image; Multi-attention extraction is performed on the first downsampled image, the second downsampled image, the third downsampled image, and the fourth downsampled image respectively to obtain the first attention map, the second attention map, the third attention map, and the fourth attention map; Upsampling is performed on the fifth upsampled image, the fourth attention image, the third attention image, the second attention image, and the first attention image to obtain the fourth upsampled image, the third upsampled image, the second upsampled image, and the first upsampled image in sequence. The first upsampled image, after convolution processing, becomes the segmentation result.

[0062] The technical details of upsampling are as follows: The fifth upsampled image and the fourth attention image are upsampled to obtain the fourth upsampled image.

[0063] The upsampling and downsampling processes can be referred to existing similar processes and will not be described in detail in this application.

[0064] The process of multi-attention extraction is as follows: The input feature map is divided into three branches, and convolutions of different sizes are performed to extract the feature maps. The feature maps of the three branches are then concatenated to obtain the concatenated feature map. The spliced ​​feature map is divided into two branches; Within the first branch, the concatenated feature map is convolved and positional information is added. Then, it is multiplied with the original concatenated feature map to obtain the multiplied feature map. The multiplied feature map is added to the original concatenated feature map and then convolved to obtain the branch feature map of the first branch. In the second branch, the concatenated feature map is convolved and channel features are added. Then it is multiplied with the original concatenated feature map to obtain the multiplied feature map. The multiplied feature map is added to the original concatenated feature map and then convolved to obtain the branch feature map of the second branch. By concatenating the branch feature maps of the first and second branches, the output feature map of multi-attention extraction is obtained.

[0065] In this way, by extracting positional attention features and channel attention features through branching, more contextual information can be captured using positional and channel attention at different scales, and the importance of each channel can be selectively weighted to produce the best output characteristics.

[0066] The multi-scale extraction process is as follows: The input feature map is subjected to convolution, normalization, and activation processing to obtain the first convolutional map; The first convolutional image is convolved, normalized, and activated to obtain the second convolutional image. The input feature map is subjected to feature extraction in multiple branches to obtain the corresponding feature maps; the convolution kernel of each branch is different. After concatenating and merging the feature maps of multiple branches, a concatenated convolutional map is obtained. After combining the concatenated convolutional map and the input feature map, multi-head attention, normalization, and multi-layer perception processing are performed to obtain a multi-layer perception map. By combining the second convolutional map and the multilayer perceptron map, we obtain the output feature map extracted at multiple scales.

[0067] In this way, the context extracted by larger convolutional kernels is integrated with deeper information flow, and multi-scale features are formed by integrating convolutional kernels of different depths and sizes. Multi-head attention is then used to fuse multi-scale features, thereby achieving further integration of features.

[0068] In this application, it should be noted that if inconsistent sizes occur during the specific feature extraction process, they can be unified by reshaping. The specific location for this reshaping can be determined based on the actual situation, and will not be elaborated upon in this application.

[0069] In this application, the training process of the above-mentioned segmentation model involves obtaining training samples, which include the input image to be segmented and the labeled segmentation results; inputting the image to be segmented from the training samples into the segmentation model to obtain a predicted segmentation result; calculating a loss function, namely the DiceLoss function, based on the predicted segmentation result and the sample segmentation result; and iterating the parameters of the entire segmentation model based on the loss function until the loss function converges. During training, the learning rate ranges from 1e-4 to 1e-3, the weight decay is 1e-4, and the total number of training epochs is 200-500.

[0070] It should be noted that, unless otherwise specified, the personalized processing model in this application can be obtained by targeted fine-tuning of an existing large model. The specific fine-tuning process may include: acquiring the patient's multimodal features and output information as sample data for the model based on its input and output requirements; modifying the input and output layers of the pre-trained large model to adapt it to the model's input and output; adding a low-rank adapter module next to the model's key layer (attention mechanism) so that only these few new parameters are trained during training; training the large model based on the sample data and updating the parameters within the low-rank adapter module and the modified input and output layer parameters until the loss converges. Further details can be found in the training requirements of existing models and will not be elaborated upon in this application.

[0071] This application provides a navigation and positioning method for a hybrid active-passive surgical robot system as described above. The specific scheme of this method is as follows: Figure 4 As shown below, the control method of the hybrid active and passive surgical robot system will be described in detail.

[0072] Combination Figure 4 As shown, the control method for the hybrid active-passive surgical robot system includes: S101, Generate a three-dimensional surgical plan based on the patient's preoperative image data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundary. S102, the three-dimensional surgical plan is registered and mapped with the actual intraoperative anatomical space through the navigator and tracer; S103, the operator pushes the passive robotic arm and locks the joint after reaching the target positioning range according to the coarse positioning navigation instructions; S104, within the target positioning range, the active robotic arm plans the motion path of the end effector based on the registration mapping result, and controls the end effector to reach the target pose along the motion path and perform surgical operations along the surgical path.

[0073] Preferably, in step S101, a three-dimensional surgical plan is generated based on the patient's preoperative imaging data and cold-region-specific bone data. The three-dimensional surgical plan includes a surgical path, target pose, and safety boundaries.

[0074] The procedure involves generating a three-dimensional surgical plan based on the patient's preoperative imaging data and cold-region-specific bone quality data. This plan includes the surgical path, target pose, and safety boundaries. Specifically, preoperative CT scans and other medical images of the patient are acquired, and a cold-region-specific bone quality database is accessed. The patient's individual bone density distribution, bone microstructure characteristics, and cold-region bone quality risk stratification are comprehensively analyzed to generate a three-dimensional surgical plan containing a three-dimensional spatial coordinate sequence of the surgical path, target pose parameters for each path point, and safety boundary distances. Simultaneously, based on the kinematic parameters of the active and passive robotic arms, the target positioning range of the passive robotic arm and the execution trajectory of the active robotic arm are planned.

[0075] Specifically, the three-dimensional surgical plan is registered and mapped to the actual anatomical space during surgery using a navigator and a tracer. The navigation tracer is rigidly fixed to a preset position on the patient's bone surface. The navigator (e.g., an optical binocular tracking system) acquires the spatial position of the tracer in real time, establishing a registration transformation matrix between the preoperative image coordinate system and the intraoperative physical coordinate system. This allows the preoperatively planned three-dimensional surgical plan to be mapped to the actual anatomical space during surgery in real time.

[0076] In this process, the surgeon pushes the passive robotic arm, and after reaching the target positioning range according to the coarse positioning navigation instructions, the joints are locked. Specifically, the surgeon manually pushes the passive robotic arm, and the coarse positioning navigation instruction module calculates the deviation between the current end effector position and the target positioning range in real time based on the registration mapping results, and instructs the surgeon to adjust the direction through the display interface. The active-passive coordination switching module monitors the position of the passive arm end effector in real time. When the end effector enters the target positioning range and the attitude deviation meets the requirements, it issues a positioning confirmation signal. After the surgeon confirms, all passive joints are locked. The safety monitoring module detects the locking status of each passive joint. After confirming that the locking is reliable, the system switches from passive positioning mode to active execution mode.

[0077] Within the target positioning range, the active robotic arm plans the motion path of the end effector based on the registration mapping results, and controls the end effector to reach the target pose and perform surgical operations along the surgical path. Specifically, the motion path planning unit plans the motion path of the end effector from the current pose to the target pose based on the registered target pose data, and embeds a microcrack protection motion strategy into the execution trajectory based on cold-region-specific bone data. The servo joint group drives the end effector to move along the planned path, the intraoperative dynamic compensation unit tracks changes in patient position in real time and automatically compensates for pose deviations, and the end effector force sensing unit monitors interactive forces in real time and assesses bone condition to correct surgical actions. The safety monitoring module is present throughout the entire execution process, continuously monitoring pose safety and force safety.

[0078] In one embodiment, the passive robotic arm includes: The multi-degree-of-freedom passive joint assembly consists of multiple rotational and / or spherical passive joints, each of which is equipped with a joint locking mechanism to lock the joint after the operator pushes the passive robotic arm to the target area; The coarse positioning navigation instruction module is used to calculate the deviation between the current end position and the target positioning range in real time based on the registration mapping results during the operation of the operator pushing the passive robotic arm, and to indicate the current positioning status and adjustment direction to the operator through the display interface.

[0079] In one embodiment, the active robotic arm includes: The multi-degree-of-freedom servo joint group consists of multiple active joints driven by servo motors. Each active joint is equipped with a position encoder and a torque sensor to achieve precise pose control of the end tool. The motion path planning unit is used to plan the motion path of the end tool from the current pose to the target pose according to the registration mapping result of the intraoperative registration module after the passive robotic arm is locked, and automatically embed segmented feed, pulse propulsion and drill unloading operations into the surgical execution trajectory according to the microcrack protection motion strategy parameters determined by cold-region specific bone data. The intraoperative dynamic compensation unit is used to track changes in the patient's position in real time through the navigator and tracker during the operation, and drive the servo joint group to automatically compensate for the pose offset of the end effector. The end-effector force sensing unit is used to collect the interaction force information between the end-effector and bone tissue in real time through the torque sensor, and combine it with the three-dimensional distribution data of bone density to generate the real-time bone state of the current surgical area, so as to correct the surgical action and / or surgical path of the end-effector.

[0080] In one embodiment, the method further includes: Based on the surgical path and target pose in the three-dimensional surgical plan, and combined with the kinematic parameters of the passive and active robotic arms, the target positioning range of the passive robotic arm is planned so that the active robotic arm can reach all planned target poses within the target positioning range. After the target positioning range is determined, the motion path of the end effector of the active robotic arm from the initial pose to each target pose is planned, as well as the execution trajectory for performing surgical operations along the surgical path.

[0081] In one embodiment, the method further includes: During the coarse positioning phase when the operator pushes the passive robotic arm, the distance and attitude deviation between the end of the passive robotic arm and the target positioning range are calculated in real time, and guidance instructions are provided to the operator through a visual interface. When the end of the passive robotic arm enters the target positioning range and the posture deviation is less than a preset threshold, it sends a positioning confirmation signal and automatically switches the control from passive positioning mode to active execution mode after the operator confirms that the passive joint is locked. In active execution mode, if it is detected that the positioning range of the passive robotic arm needs to be adjusted, the operation of the active robotic arm is paused, the passive joint lock is released, and the system switches back to passive positioning mode to wait for the surgeon to re-coarsely position the target.

[0082] In one embodiment, the method further includes: After the passive robotic arm reaches the target positioning range and locks the joints, the locking status of each passive joint is detected, and the active robotic arm is allowed to start and perform operations only after the locking is confirmed to be reliable. During the operation of the active robotic arm, the position and force of the end tool are monitored in real time. When the end tool deviates from the safety boundary or the force exceeds the preset threshold, the active robotic arm is triggered to brake and issue a warning. When an abnormal joint locking state of the passive robotic arm is detected, the operation of the active robotic arm is immediately stopped and the end effector is withdrawn to a safe position.

[0083] In one embodiment, the method further includes: Based on the patient's medical data and cold-region-specific data, a targeted disease assessment is conducted to generate personalized auxiliary assessment results for the patient. Based on the patient's medical data, surgical plan, and cold-region-specific data, a personalized preoperative rehabilitation plan is generated for the patient; and based on the patient's medical data, postoperative assessment results, and cold-region-specific data, a personalized postoperative rehabilitation plan is generated for the patient.

[0084] The active-passive hybrid surgical robot system control method provided in the above embodiments of this application corresponds to the active-passive hybrid surgical robot system provided in the embodiments of this application. Therefore, the specific content of the method corresponds to the active-passive hybrid surgical robot system. The specific content can be referred to the records in the active-passive hybrid surgical robot system, which will not be repeated in this application.

[0085] The active-passive hybrid surgical robot system control method provided in the above embodiments of this application is based on the same inventive concept as the active-passive hybrid surgical robot system provided in the embodiments of this application, and has the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0086] Based on the same inventive concept, another embodiment of the present invention provides an electronic device for implementing the active-passive hybrid surgical robot system control method described in the above embodiments. Figure 5 As shown, the electronic device includes a memory 301 and a processor 303.

[0087] Memory 301 can be configured to store a program.

[0088] Additionally, memory 301 can also be configured to store various other data to support operation on the electronic device. Examples of this data include instructions for any application or method used to operate on the electronic device, contact data, phonebook data, messages, pictures, videos, etc.

[0089] Memory 301 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Processor 303, coupled to memory 301, is used to execute programs in memory 301 for: A three-dimensional surgical plan is generated based on the patient's preoperative imaging data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundaries. The three-dimensional surgical plan is registered and mapped with the actual intraoperative anatomical space using a navigator and a tracer; The operator pushes the passive robotic arm and locks the joint after reaching the target positioning range according to the coarse positioning navigation instructions; Within the target positioning range, the active robotic arm plans the motion path of the end effector based on the registration mapping results, and controls the end effector to reach the target pose along the motion path and perform surgical operations along the surgical path.

[0090] Preferably, a three-dimensional surgical plan is generated based on the patient's preoperative imaging data and cold-region-specific bone data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundaries.

[0091] In one embodiment, the passive robotic arm includes: The multi-degree-of-freedom passive joint assembly consists of multiple rotational and / or spherical passive joints, each of which is equipped with a joint locking mechanism to lock the joint after the operator pushes the passive robotic arm to the target area; The coarse positioning navigation instruction module is used to calculate the deviation between the current end position and the target positioning range in real time based on the registration mapping results during the operation of the operator pushing the passive robotic arm, and to indicate the current positioning status and adjustment direction to the operator through the display interface.

[0092] In one embodiment, the active robotic arm includes: The multi-degree-of-freedom servo joint group consists of multiple active joints driven by servo motors. Each active joint is equipped with a position encoder and a torque sensor to achieve precise pose control of the end tool. The motion path planning unit is used to plan the motion path of the end tool from the current pose to the target pose according to the registration mapping result of the intraoperative registration module after the passive robotic arm is locked, and automatically embed segmented feed, pulse propulsion and drill unloading operations into the surgical execution trajectory according to the microcrack protection motion strategy parameters determined by cold-region specific bone data. The intraoperative dynamic compensation unit is used to track changes in the patient's position in real time through the navigator and tracker during the operation, and drive the servo joint group to automatically compensate for the pose offset of the end effector. The end-effector force sensing unit is used to collect the interaction force information between the end-effector and bone tissue in real time through the torque sensor, and combine it with the three-dimensional distribution data of bone density to generate the real-time bone state of the current surgical area, so as to correct the surgical action and / or surgical path of the end-effector.

[0093] In one implementation, the processor 303 is further configured to: Based on the surgical path and target pose in the three-dimensional surgical plan, and combined with the kinematic parameters of the passive and active robotic arms, the target positioning range of the passive robotic arm is planned so that the active robotic arm can reach all planned target poses within the target positioning range. After the target positioning range is determined, the motion path of the end effector of the active robotic arm from the initial pose to each target pose is planned, as well as the execution trajectory for performing surgical operations along the surgical path.

[0094] In one implementation, the processor 303 is further configured to: During the coarse positioning phase when the operator pushes the passive robotic arm, the distance and attitude deviation between the end of the passive robotic arm and the target positioning range are calculated in real time, and guidance instructions are provided to the operator through a visual interface. When the end of the passive robotic arm enters the target positioning range and the posture deviation is less than a preset threshold, it sends a positioning confirmation signal and automatically switches the control from passive positioning mode to active execution mode after the operator confirms that the passive joint is locked. In active execution mode, if it is detected that the positioning range of the passive robotic arm needs to be adjusted, the operation of the active robotic arm is paused, the passive joint lock is released, and the system switches back to passive positioning mode to wait for the surgeon to re-coarsely position the target.

[0095] In one implementation, the processor 303 is further configured to: After the passive robotic arm reaches the target positioning range and locks the joints, the locking status of each passive joint is detected, and the active robotic arm is allowed to start and perform operations only after the locking is confirmed to be reliable. During the operation of the active robotic arm, the position and force of the end tool are monitored in real time. When the end tool deviates from the safety boundary or the force exceeds the preset threshold, the active robotic arm is triggered to brake and issue a warning. When an abnormal joint locking state of the passive robotic arm is detected, the operation of the active robotic arm is immediately stopped and the end effector is withdrawn to a safe position.

[0096] In one implementation, the processor 303 is further configured to: Based on the patient's medical data and cold-region-specific data, a targeted disease assessment is conducted to generate personalized auxiliary assessment results for the patient. Based on the patient's medical data, surgical plan, and cold-region-specific data, a personalized preoperative rehabilitation plan is generated for the patient; and based on the patient's medical data, postoperative assessment results, and cold-region-specific data, a personalized postoperative rehabilitation plan is generated for the patient.

[0097] In this application, Figure 5 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 5 The components shown.

[0098] The electronic device provided in this embodiment is based on the same inventive concept as the force-optimized robotic arm osteotomy control method provided in the embodiments of this application, and has the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0099] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0103] This application also provides a computer-readable storage medium corresponding to the force-optimized robotic arm osteotomy control method provided in the foregoing embodiments, wherein a computer program (i.e., a program product) is stored thereon. When the computer program is run by a processor, it executes the interactive image analysis assistance method for 3D aerial imaging provided in any of the foregoing embodiments.

[0104] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, optical disc read-only memory (CDROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0105] The computer-readable storage medium provided in the above embodiments of this application and the active-passive hybrid surgical robot system control method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0106] It should be noted that numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known structures and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, system, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, system, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, system, article, or apparatus that includes said element.

[0108] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A hybrid active-passive surgical robot system, characterized in that, include: The preoperative planning module is used to generate a three-dimensional surgical plan based on the patient's preoperative imaging data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundaries. The intraoperative registration module is used to register and map the three-dimensional surgical plan generated by the preoperative planning module with the actual intraoperative anatomical space through a navigator and a tracer. A passive robotic arm, consisting of at least one unpowered passive joint, is used to interact with the operator and indicate the positioning range for the operator to perform coarse positioning of the end effector. An active robotic arm, mounted at the distal end of the passive robotic arm, is used to plan the motion path of the end-effector to the target pose based on the registration mapping results of the intraoperative registration module within the positioning range indicated by the passive robotic arm, and to control the end-effector to reach the target pose along the motion path and to perform surgical operations along the surgical path.

2. The active-passive hybrid surgical robot system according to claim 1, characterized in that, The passive robotic arm includes: The multi-degree-of-freedom passive joint assembly consists of multiple rotary and / or spherical passive joints, each of which is equipped with a joint locking mechanism to lock the joint after the surgeon pushes the passive robotic arm to the target area; The coarse positioning navigation instruction module is used to calculate the deviation between the current end position and the target positioning range in real time based on the registration mapping results during the operation of the operator pushing the passive robotic arm, and to indicate the current positioning status and adjustment direction to the operator through the display interface.

3. The active-passive hybrid surgical robot system according to claim 1, characterized in that, The active robotic arm includes: The multi-degree-of-freedom servo joint assembly consists of multiple active joints driven by servo motors. Each active joint is equipped with a position encoder and a torque sensor to achieve precise pose control of the end tool. The motion path planning unit is used to plan the motion path of the end effector from the current pose to the target pose based on the registration mapping result of the intraoperative registration module after the passive robotic arm is locked. The intraoperative dynamic compensation unit is used to track changes in the patient's position in real time through the navigator and tracker during the operation and automatically compensate for the positional deviation of the end effector. The end-effector force sensing unit is used to collect the interaction force information between the end-effector and bone tissue in real time through the torque sensor, and combine it with the three-dimensional distribution data of bone density to generate the real-time bone state of the current surgical area, so as to correct the surgical action and / or surgical path of the end-effector.

4. The active-passive hybrid surgical robot system according to claim 1, characterized in that, The preoperative planning module is also used for: Based on the surgical path and target pose in the three-dimensional surgical plan, and combined with the kinematic parameters of the passive and active robotic arms, the target positioning range of the passive robotic arm is planned so that the active robotic arm can reach all planned target poses within the target positioning range.

5. The active-passive hybrid surgical robot system according to claim 1, characterized in that, It also includes an active / passive coordination switching module, which is used for: During the coarse positioning stage, the distance and attitude deviation between the end effector of the passive robotic arm and the target positioning range are calculated in real time, and guidance instructions are provided to the operator through a visual interface. After the operator confirms that the passive joint is locked, the control is automatically switched to active execution mode; In active execution mode, if it is detected that the positioning range of the passive robotic arm needs to be adjusted, the operation of the active robotic arm is paused and switched back to passive positioning mode.

6. The active-passive hybrid surgical robot system according to claim 1, characterized in that, It also includes a security monitoring module, which is used for: After the passive robotic arm locks its joints, the locking status of each passive joint is detected. Once the locking is confirmed to be reliable, the active robotic arm is allowed to start and perform the operation. During the operation of the active robotic arm, the position and force of the end tool are monitored in real time. When the end tool deviates from the safety boundary or the force exceeds the preset threshold, the active robotic arm is triggered to brake and issue a warning. When an abnormal joint locking state of the passive robotic arm is detected, the execution operation of the active robotic arm is terminated.

7. The active-passive hybrid surgical robot system according to claim 1, characterized in that, Also includes: The intelligent assessment module is used to conduct targeted disease assessments on patients based on their medical data and cold-region-specific data, generating personalized auxiliary assessment results for each patient. The auxiliary rehabilitation module is used to generate personalized preoperative rehabilitation plans for patients based on their medical data, surgical plans, and cold-region-specific data. Furthermore, based on the patient's medical data, postoperative assessment results, and cold-region-specific data, a personalized postoperative rehabilitation plan is generated for the patient.

8. A control method for a hybrid active-passive surgical robot system, applied to the hybrid active-passive surgical robot system according to any one of claims 1 to 7, characterized in that, Includes the following steps: A three-dimensional surgical plan is generated based on the patient's preoperative imaging data. The three-dimensional surgical plan includes the surgical path, target pose, and safety boundaries. The three-dimensional surgical plan is registered and mapped with the actual intraoperative anatomical space using a navigator and a tracer; The operator pushes the passive robotic arm and locks the joint after reaching the target positioning range according to the coarse positioning navigation instructions; Within the target positioning range, the active robotic arm plans the motion path of the end effector based on the registration mapping results, and controls the end effector to reach the target pose along the motion path and perform surgical operations along the surgical path.

9. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores computer-executable instructions, and the processor executes the computer-executable instructions to implement the steps of the control method for the active-passive hybrid surgical robot system of claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the steps of the control method for the active-passive hybrid surgical robot system of claim 8.

Images