Image-based surgical robot automatic registration method and device

Abstract

The invention discloses an image-based surgical robot automatic registration method and device, and the method comprises the steps: dragging a robot mechanical arm to enable an execution mechanism to accurately reach a target registration point, and enabling a robot head camera and a wrist camera to synchronously and continuously collect the feature data of the target registration point and the feature data of the mechanical arm execution mechanism respectively; inputting the collected feature data into a pre-constructed network model for pre-training to obtain a pre-trained model; based on the pre-training model, the robot automatically controls a mechanical arm execution mechanism to reach target registration points, and coordinates of each target registration point in a mechanical arm coordinate system are obtained; and calculating the conversion relation between the medical image coordinate system and the mechanical arm coordinate system. Through imitation learning and reinforcement learning based on vision, the surgical robot does not depend on subjective judgment of a doctor in the registration process, and the tail end of the mechanical arm can be intelligently, accurately and autonomously controlled to accurately reach the registration target point or the registration point.

Description

Technical Field

[0001] The present invention relates to the field of intelligent robots, and in particular to an image-based automatic registration method and device for a surgical robot, and a surgical robot. Background Art

[0002] Positioning surgical robots based on medical imaging and multi-degree-of-freedom robotic arms have been clinically applied in neurosurgery, orthopedics and other surgical fields. One of the key steps in the positioning of surgical robots is registration, which is to establish the conversion relationship between the medical imaging coordinate system and the robotic arm coordinate system.

[0003] The basic principle of registration here is:

[0004] Control the robotic arm so that the registration needle at the end of the robotic arm touches each registration point or feature point on the patient. At this point, the coordinates of the registration point or feature point in the medical image coordinate system have been obtained, thereby obtaining the coordinates of the registration point or feature point in the robotic arm coordinate system. By obtaining 3 to 4 such coordinate pairs, the conversion relationship between the robotic arm coordinate system and the medical image coordinate system can be solved.

[0005] One of the shortcomings of this method is that the end of the robotic arm needs to touch or approach each registration point or feature point. The range of movement of the robotic arm is large, the efficiency is low, and whether the end of the robotic arm accurately touches the registration point or feature point requires visual inspection or visual recognition by the doctor. The alignment accuracy error fluctuates greatly and needs to rely on the doctor's subjective judgment during each operation.

[0006] At present, the positioning accuracy of the robotic arms used in surgical robots is already very high, so the registration accuracy directly and ultimately determines the execution accuracy of the surgical robot, that is, whether the actuator of the surgical robot can accurately reach the surgical target planned and determined on the medical image. This execution accuracy directly determines the scope of indications for the surgical robot.

[0007] Therefore, a method for accurately realizing automatic registration of a surgical robot is needed, in which the actuator of the surgical robot can still accurately reach the surgical point specified on the medical image without relying on the subjective judgment of the doctor. Summary of the invention

[0008] One of the purposes of the embodiments of the present invention is to provide an image-based automatic registration method and device for a surgical robot, so as to greatly improve the accuracy of the automatic registration of the surgical robot without relying on subjective judgment.

[0009] In order to solve the above technical problems, in a first aspect, an embodiment of the present invention provides an image-based automatic registration method for a surgical robot, the method comprising:

[0010] When the robot arm is dragged so that the actuator reaches the target registration point accurately, the robot head camera and wrist camera synchronously and continuously collect the characteristic data of the target registration point and the actuator of the robot arm respectively;

[0011] Input the collected feature data into a pre-built network model for pre-training to obtain a pre-trained model;

[0012] Based on the pre-trained model, the robot automatically controls the mechanical arm actuator to reach the target registration point, and obtains the coordinates of each target registration point in the mechanical arm coordinate system;

[0013] Calculate the transformation relationship between the medical image coordinate system and the robotic arm coordinate system.

[0014] Preferably, the target registration points are set to no less than 4, which are selected and set at appropriate positions of the patient, and at least one test marking point is also set.

[0015] Preferably, the transformation relationship between the calculated medical image coordinate system and the robotic arm coordinate system specifically includes:

[0016] Calculate the mutual spatial relationship A of the coordinates of the four points in the medical image coordinate system, the mutual spatial relationship A' of the coordinates of the four points in the robotic arm coordinate system, and the error B between A and A'. If the error B is less than the preset error threshold B0, the group of data is marked as pending data, and the conversion relationship between the medical image coordinate system and the robotic arm coordinate system is calculated using the four coordinate point data.

[0017] Furthermore, the method further comprises:

[0018] If the error B is greater than a preset error threshold B0, the group of data is set as negative excitation data.

[0019] Furthermore, the method further comprises:

[0020] According to the conversion relationship between the medical image coordinate system and the robotic arm coordinate system, the surgical robot automatically controls the end of the robotic arm to navigate to the test mark point, and the camera observes whether the matching accuracy reaches the preset accuracy value. If so, the group of data is set as positive training data;

[0021] The pending data is modified into positive training data, and continuously fed into the pre-training model for training to optimize the parameters of the model.

[0022] In a second aspect, in order to solve the technical problem of the present invention, an embodiment of the present invention further provides an image-based automatic registration device for a surgical robot, the device comprising:

[0023] A camera unit, wherein the camera unit includes a head camera and a wrist camera. When the robot arm is dragged so that the actuator reaches the target registration point accurately, the head camera and the wrist camera of the robot respectively and synchronously continuously collect feature data of the target registration point and the actuator of the robot arm;

[0024] A pre-training unit, used for inputting the collected feature data into a pre-built network model for pre-training to obtain a pre-trained model;

[0025] An automatic control unit, used for automatically controlling the robot arm actuator to reach the target registration point based on the pre-trained model, and obtaining the coordinates of each target registration point in the robot arm coordinate system;

[0026] The registration unit is used to calculate the transformation relationship between the medical image coordinate system and the robotic arm coordinate system.

[0027] Preferably, the registration unit calculates the conversion relationship between the medical image coordinate system and the robotic arm coordinate system specifically including:

[0028] Calculate the mutual spatial relationship A of the coordinates of the four points in the medical image coordinate system, the mutual spatial relationship A' of the coordinates of the four points in the robotic arm coordinate system, and the error B between A and A'. If the error B is less than the preset error threshold B0, the group of data is marked as pending data, and the conversion relationship between the medical image coordinate system and the robotic arm coordinate system is calculated using the four coordinate point data.

[0029] Furthermore, the device also includes:

[0030] The test marking unit is used to automatically control the end of the robotic arm to navigate to the test marking point according to the conversion relationship between the medical image coordinate system and the robotic arm coordinate system. The camera observes whether the matching accuracy reaches the preset accuracy value. If so, the group of data is set as positive training data;

[0031] The model optimization unit is used to modify the pending data into positive training data, continuously feed it into the pre-training model for training, and optimize the parameters of the model.

[0032] On the other hand, an embodiment of the present invention further provides a surgical robot, including a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method as described above.

[0033] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method as described above.

[0034] Compared with the prior art, the image-based automatic registration device and method for a surgical robot provided by the embodiments of the present invention have at least the following beneficial effects:

[0035] The embodiments of the present invention use ordinary optical cameras without the need for special and expensive depth sensors (such as 3D lidar, medical surgical navigators or industrial high-precision depth cameras). Through vision-based imitation learning and reinforcement learning, the surgical robot does not rely on the doctor's subjective judgment during the alignment process, but can also intelligently and accurately control the end of the robotic arm to accurately reach the alignment target point or registration point. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The preferred implementation modes will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.

[0037] Figure 1 This is a flow chart of an image-based automatic registration method for a surgical robot according to an embodiment of the present invention;

[0038] Figure 2 This is a flow chart of another image-based automatic registration method for a surgical robot according to an embodiment of the present invention;

[0039] Figure 3 This is a schematic structural diagram of an image-based automatic registration device for a surgical robot according to an embodiment of the present invention;

[0040] Figure 4 Schematic diagram of the structure of another image-based automatic registration device for a surgical robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0042] In order to simplify the drawings, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0043] The following mainly takes some specific embodiments as examples to describe in detail the implementation of the technical solution of the present invention.

[0044] like Figure 1 As shown, in order to achieve the purpose of the present invention, an embodiment of the present invention provides an image-based automatic registration method for a surgical robot, comprising the following steps:

[0045] S1. In the process of dragging the robot arm so that the actuator reaches the target registration point accurately, the robot head camera and wrist camera respectively and synchronously and continuously collect feature data of the target registration point and the robot arm actuator;

[0046] S2, inputting the collected feature data into a pre-built network model for pre-training to obtain a pre-trained model;

[0047] S3. Based on the pre-trained model, the robot automatically controls the mechanical arm actuator to reach the target registration point, and obtains the coordinates of each target registration point in the mechanical arm coordinate system;

[0048] S4. Calculate the conversion relationship between the medical image coordinate system and the robotic arm coordinate system.

[0049] The image-based automatic registration method for surgical robots in the embodiment of the present invention requires the deployment of the following positioning components:

[0050] 1. Equip the end of the surgical robot's mechanical arm with a camera (hereinafter referred to as the wrist camera)

[0051] 2. Equip a camera (hereinafter referred to as head camera) at the appropriate position of the robot's head (i.e. the robot's torso)

[0052] At the same time, preferably, the target registration points are set to no less than 4, which are selected and set at appropriate positions of the patient, and at least one test marking point is also set.

[0053] That is, set no less than 4 target registration points and at least 1 test marking point at appropriate positions of the patient.

[0054] First, the robot arm is manually dragged so that the actuator at the end of the robot arm reaches the registration point accurately. At the same time, the robot's head camera and wrist camera continuously collect image data during the process of manually dragging the robot arm, and obtain the characteristic data of the registration point and the actuator at the end of the robot arm from the image data.

[0055] After collecting a predetermined amount (such as hundreds of groups) of feature data, it is sent to the constructed neural network for pre-training to obtain a pre-trained model.

[0056] Based on the pre-trained model, the surgical robot system autonomously controls the robotic arm to reach each target registration point and obtains the coordinates of each target registration point in the robotic arm coordinate system.

[0057] Preferably, the conversion relationship between the computed medical image coordinate system and the robotic arm coordinate system specifically includes:

[0058] The mutual spatial relationship A of the coordinates of 4 points in the computed medical image coordinate system, the mutual spatial relationship A' of the coordinates of 4 points in the robotic arm coordinate system, and the error B between A and A'. If the error B is less than the preset error threshold B0, this set of data is marked as pending data, and the conversion relationship between the medical image coordinate system and the robotic arm coordinate system is calculated using the data of these 4 coordinate points.

[0059] The mutual spatial relationship A of the coordinates of 4 points in the computed medical image coordinate system, the mutual spatial relationship A' of the coordinates of 4 points in the robotic arm coordinate system, and the error B between A and A'. If B < B0, this set of data is marked as pending data, and the conversion relationship between the medical image coordinate system and the robotic arm coordinate system is obtained using the data of these 4 coordinate points, and continue to the next step.

[0060] If B > B0, this set of data is negative incentive data, and the surgical robot returns to the previous step.

[0061] As Figure 2 shown, the embodiments of the present invention provide a method for automatic registration of an image-based surgical robot, including the following steps:

[0062] S1. During the process of dragging the robotic arm of the robot so that the actuator precisely reaches the target registration point, the head camera and the wrist camera of the robot respectively and continuously collect the feature data of the target registration point and the robotic arm actuator synchronously;

[0063] S2. Input the collected feature data into a pre-constructed network model for pre-training to obtain a pre-trained model;

[0064] S3. Based on the pre-trained model, the robot automatically controls the robotic arm actuator to reach the target registration point, and obtains the coordinates of each target registration point in the robotic arm coordinate system;

[0065] S4. Calculate the conversion relationship between the computed medical image coordinate system and the robotic arm coordinate system;

[0066] S5. According to the conversion relationship between the computed medical image coordinate system and the robotic arm coordinate system, the surgical robot automatically controls the end of the robotic arm to navigate to the test marking point, and the camera observes whether the matching accuracy reaches the preset accuracy value. If so, set this set of data as positive training data;

[0067] S6. Modify the pending data to positive training data, and continuously send it into the pre-trained model for training to optimize the parameters of the model.

[0068] According to the conversion relationship between the medical image coordinate system and the robotic arm coordinate system, the surgical robot automatically controls the end of the robotic arm to navigate to the test mark point. The camera observes the final matching accuracy. If the composite accuracy requirement is met, the corresponding data is corrected from "pending data" to "positive training data"

[0069] Continuously feed the "forward training data" into the neural network for training and optimizing the model parameters.

[0070] The embodiments of the present invention use ordinary optical cameras and do not require special and expensive depth sensors (such as 3D lidar, medical surgical navigators or industrial high-precision depth cameras). Through vision-based imitation learning and reinforcement learning, the surgical robot does not rely on the doctor's subjective judgment during the alignment process, but can also intelligently and accurately control the end of the robotic arm to accurately reach the alignment target point or registration point.

[0071] In order to solve the technical problems of the present invention, Figure 3 As shown, an embodiment of the present invention further provides an image-based automatic registration device for a surgical robot, the device comprising:

[0072] A camera unit, wherein the camera unit includes a head camera and a wrist camera. When the robot arm is dragged so that the actuator reaches the target registration point accurately, the head camera and the wrist camera of the robot respectively and synchronously continuously collect feature data of the target registration point and the actuator of the robot arm;

[0073] A pre-training unit, used for inputting the collected feature data into a pre-built network model for pre-training to obtain a pre-trained model;

[0074] An automatic control unit, used for automatically controlling the robot arm actuator to reach the target registration point based on the pre-trained model, and obtaining the coordinates of each target registration point in the robot arm coordinate system;

[0075] The registration unit is used to calculate the transformation relationship between the medical image coordinate system and the robotic arm coordinate system.

[0076] Preferably, the registration unit calculates the conversion relationship between the medical image coordinate system and the robotic arm coordinate system specifically including:

[0077] Calculate the mutual spatial relationship A of the coordinates of the four points in the medical image coordinate system, the mutual spatial relationship A' of the coordinates of the four points in the robotic arm coordinate system, and the error B between A and A'. If the error B is less than the preset error threshold B0, the group of data is marked as pending data, and the conversion relationship between the medical image coordinate system and the robotic arm coordinate system is calculated using the four coordinate point data.

[0078] Further, such as Figure 4As shown, an embodiment of the present invention further provides an image-based automatic registration device for a surgical robot, the device comprising:

[0079] A camera unit, wherein the camera unit includes a head camera and a wrist camera. When the robot arm is dragged so that the actuator reaches the target registration point accurately, the head camera and the wrist camera of the robot respectively and synchronously continuously collect feature data of the target registration point and the actuator of the robot arm;

[0080] A pre-training unit, used for inputting the collected feature data into a pre-built network model for pre-training to obtain a pre-trained model;

[0081] An automatic control unit, used for automatically controlling the robot arm actuator to reach the target registration point based on the pre-trained model, and obtaining the coordinates of each target registration point in the robot arm coordinate system;

[0082] A registration unit, used to calculate the conversion relationship between the medical image coordinate system and the robotic arm coordinate system;

[0083] The device also includes:

[0084] The test marking unit is used to automatically control the end of the robotic arm to navigate to the test marking point according to the conversion relationship between the medical image coordinate system and the robotic arm coordinate system. The camera observes whether the matching accuracy reaches the preset accuracy value. If so, the group of data is set as positive training data;

[0085] The model optimization unit is used to modify the pending data into positive training data, continuously feed it into the pre-training model for training, and optimize the parameters of the model.

[0086] Compared with the prior art, the image-based automatic registration device and method for a surgical robot provided by the embodiments of the present invention have at least the following beneficial effects:

[0087] The embodiments of the present invention use ordinary optical cameras without the need for special and expensive depth sensors (such as 3D lidar, medical surgical navigators or industrial high-precision depth cameras). Through vision-based imitation learning and reinforcement learning, the surgical robot does not rely on the doctor's subjective judgment during the alignment process, but can also intelligently and accurately control the end of the robotic arm to accurately reach the alignment target point or registration point.

[0088] A surgical robot provided in an embodiment of the present application includes a processor 1001 and a memory 1002. The processor 1001 and the memory 1002 can be interconnected via a communication bus 1003. The communication bus 1003 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1003 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the memory 1002 is used to store a computer program, and the computer program includes program instructions. The processor 1001 is configured to call the program instructions, and the above program includes steps for executing some or all of the steps in the aforementioned method.

[0089] The processor 1001 may be a general purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the above program.

[0090] The memory 1002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a bus. The memory may also be integrated with the processor.

[0091] The surgical robot 1000 may further include a communication module 1004 and a display 1005. The communication module 1004 may be connected to the optical tracking device for communication. The communication module 1004 may be a wireless communication module (eg, a WiFi module, a Bluetooth module, etc.) or a wired communication module.

[0092] In addition, the surgical robot 1000 may also include common components such as a communication interface (eg, a USB interface, a microphone interface, etc.) and an antenna, which will not be described in detail here.

[0093] An embodiment of the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the boundary-merging-based unstructured grid combinations recorded in the above method embodiments.

[0094] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0095] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0099] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0100] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0101] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0102] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. An image-based automatic registration method for a surgical robot, characterized in that: The method comprises: When the robot arm is dragged so that the actuator reaches the target registration point accurately, the robot head camera and wrist camera synchronously and continuously collect the characteristic data of the target registration point and the actuator of the robot arm respectively; Input the collected feature data into a pre-built network model for pre-training to obtain a pre-trained model; Based on the pre-trained model, the robot automatically controls the mechanical arm actuator to reach the target registration point, and obtains the coordinates of each target registration point in the mechanical arm coordinate system; Calculate the transformation relationship between the medical image coordinate system and the robotic arm coordinate system.

2. The image-based automatic registration method for a surgical robot according to claim 1, characterized in that: The target registration points are set to no less than 4, which are selected and set at appropriate positions of the patient, and at least one test marking point is also set.

3. The image-based automatic registration method for a surgical robot according to claim 1, characterized in that: The transformation relationship between the computing medical image coordinate system and the robotic arm coordinate system specifically includes: Calculate the mutual spatial relationship A of the coordinates of the four points in the medical image coordinate system, the mutual spatial relationship A' of the coordinates of the four points in the robotic arm coordinate system, and the error B between A and A'. If the error B is less than the preset error threshold B0, the group of data is marked as pending data, and the conversion relationship between the medical image coordinate system and the robotic arm coordinate system is calculated using the four coordinate point data.

4. The image-based automatic registration method for a surgical robot according to claim 3, characterized in that: The method further comprises: If the error B is greater than a preset error threshold B0, the group of data is set as negative excitation data.

5. The image-based automatic registration method for a surgical robot according to claim 3, characterized in that: The method further comprises: According to the conversion relationship between the medical image coordinate system and the robotic arm coordinate system, the surgical robot automatically controls the end of the robotic arm to navigate to the test mark point, and the camera observes whether the matching accuracy reaches the preset accuracy value. If so, the group of data is set as positive training data; The pending data is modified into positive training data, and continuously fed into the pre-training model for training to optimize the parameters of the model.

6. An image-based automatic registration device for a surgical robot, characterized in that: The device comprises: A camera unit, wherein the camera unit includes a head camera and a wrist camera. When the robot arm is dragged so that the actuator reaches the target registration point accurately, the head camera and the wrist camera of the robot respectively and synchronously continuously collect feature data of the target registration point and the actuator of the robot arm; A pre-training unit, used for inputting the collected feature data into a pre-built network model for pre-training to obtain a pre-trained model; An automatic control unit, used for automatically controlling the robot arm actuator to reach the target registration point based on the pre-trained model, and obtaining the coordinates of each target registration point in the robot arm coordinate system; The registration unit is used to calculate the transformation relationship between the medical image coordinate system and the robotic arm coordinate system.

7. The image-based automatic registration device for a surgical robot according to claim 6, characterized in that: The registration unit calculates the conversion relationship between the medical image coordinate system and the robotic arm coordinate system specifically including: Calculate the mutual spatial relationship A of the coordinates of the four points in the medical image coordinate system, the mutual spatial relationship A' of the coordinates of the four points in the robotic arm coordinate system, and the error B between A and A'. If the error B is less than the preset error threshold B0, the group of data is marked as pending data, and the conversion relationship between the medical image coordinate system and the robotic arm coordinate system is calculated using the four coordinate point data.

8. The image-based automatic registration device for a surgical robot according to claim 6, characterized in that: The device also includes: The test marking unit is used to automatically control the end of the robotic arm to navigate to the test marking point according to the conversion relationship between the medical image coordinate system and the robotic arm coordinate system. The camera observes whether the matching accuracy reaches the preset accuracy value. If so, the group of data is set as positive training data; The model optimization unit is used to modify the pending data into positive training data, continuously feed it into the pre-training model for training, and optimize the parameters of the model.

9. A surgical robot, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is enabled to perform the method according to any one of claims 1 to 5.

Images