Registration path point generation method and device of mechanical arm, equipment and storage medium

Abstract

The invention relates to the technical field of mechanical arm registration, provides a method, a device and equipment for generating a registration path point of a mechanical arm and a storage medium, and can ensure that the generated path point meets the registration requirement of the mechanical arm while the registration path point is automatically generated, and the distribution is dispersed as far as possible. According to the method, a physical boundary constraint model of a mechanical arm registration scene is obtained, and a registration path point constraint expression is determined; according to the registration waypoint constraint expression, automatically generating a feasible registration waypoint space, and according to the feasible registration waypoint space, generating a plurality of registration waypoints; the plurality of registered waypoints are dispersedly distributed in the feasible registered waypoint space.

Description

Technical Field

[0001] The present application relates to the technical field of robotic arm registration, and particularly to a method and device for generating registration path points of a robotic arm, a computer device, a storage medium, a registration method for a surgical robot, a registration system for a surgical robot, a surgical robot system, and a computer program product. Background Art

[0002] A robot system based on optical navigation may include a robotic arm and an optical tracking device, as Figure 1 shown. The main role of the robot in surgery is to position surgical instruments, capture the position and attitude information of the surgical instruments during the surgery, and feedback this information to the central processing unit of the surgical system in real time. The optical navigation device acts as the "eyes" of the surgical system and is used to capture the relative position between the optical tracer array on the patient (such as Figure 1 the target object tracer array) and the optical tracer array on the robotic arm base (hereinafter referred to as the robotic arm base array) to obtain the relative spatial position relationship between the patient and the robot. The position space formed by the optical navigation device is the observation space, and the position space formed by the movement of the robotic arm is the execution space. The optical navigation device cannot directly observe the position of the robot. After the "hand-eye" calibration is performed by means of the optical tracer array on the robot, the observation space and the execution space can be unified.

[0003] The hand-eye calibration of the robot mainly relies on the tracer array installed at the end of the robotic arm (this tracer array can be called the end registration array), and captures the movement of the end registration array under the optical navigation device. The movement trajectory of the end registration array in the execution space of the robotic arm and the movement trajectory in the observation space of the optical navigation device are registered and aligned to obtain the mapping relationship between the execution space and the observation space. In the prior art, when registering the robotic arm, it is difficult to generate registration path points that exist in both the execution space and the observation space, and it is difficult to ensure that the selected path points meet the registration requirements, resulting in a certain failure probability. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method and device for generating registration path points of a robotic arm, a computer device, a storage medium, a registration method for a surgical robot, a registration system for a surgical robot, a surgical robot system, and a computer program product.

[0005] The present application provides a method for generating registration path points of a robotic arm, the method comprising:

[0006] Obtaining a physical boundary constraint model of the robotic arm registration scenario, and determining a registration path point constraint expression;

[0007] Generating a feasible registration path point space according to the registration path point constraint expression;

[0008] Generate a plurality of registration path points according to the feasible registration path point space; the plurality of registration path points are distributed dispersedly in the feasible registration path point space.

[0009] In one embodiment, generating a plurality of registration path points according to the feasible registration path point space includes:

[0010] Serializing to generate a plurality of registration path points according to the feasible registration path point space;

[0011] In the process of serializing to generate non-first registration path points, obtain the distribution dispersion degree between each feasible registration path point in the feasible registration path point space and the generated registration path points, and determine a plurality of the non-first registration path points among each feasible registration path point according to the magnitudes of the distribution dispersion degrees corresponding to each feasible registration path point.

[0012] In one embodiment, the method further includes:

[0013] When generating the first registration path point, determine the first registration path point from a plurality of feasible registration path points according to the magnitude of the central distance between the feasible registration path point and the center of the feasible registration path point space.

[0014] In one embodiment, obtaining a physical boundary constraint model of the robotic arm registration scenario and determining a registration path point constraint expression includes:

[0015] Obtain the bounding box of the robotic arm base array, the bounding box of the robotic arm link, and the bounding box of the joint;

[0016] Based on the fact that the links and joints of the robotic arm are not located within the bounding box space of the robotic arm base array during the movement of the robotic arm between adjacent path points, combine the bounding box of the robotic arm base array, the bounding box of the link, and the bounding box of the joint to obtain a registration path point constraint expression for the collision between each link and joint of the robotic arm and the robotic arm base array.

[0017] In one embodiment, obtaining a physical boundary constraint model of the robotic arm registration scenario and determining a registration path point constraint expression includes:

[0018] Obtain the bounding box of the robotic arm base body, the bounding box of the robotic arm link, and the bounding box of the joint;

[0019] Based on the fact that the links and joints of the robotic arm do not collide with the robotic arm base body during the movement of the robotic arm between adjacent path points, combine the bounding box of the robotic arm base body, the bounding box of the link, and the bounding box of the joint to obtain a registration path point constraint expression for the collision between each link and joint of the robotic arm and the robotic arm base body.

[0020] In one embodiment, the method further includes:

[0021] Based on the fact that no collision occurs between the connecting rods and joints during the movement of the robotic arm between adjacent path points, combining the boundary bounding boxes of the connecting rods and the boundary bounding boxes of the joints, a registration path point constraint expression for the collision between each connecting rod and joint of the robotic arm is obtained.

[0022] In one embodiment, obtaining a physical boundary constraint model of the registration scenario of the robotic arm and determining a registration path point constraint expression includes:

[0023] Obtaining an optical path boundary bounding box, a boundary bounding box of the connecting rods of the robotic arm, and a boundary bounding box of the joints; the optical path boundary bounding box is a boundary model of the optical path between the optical tracking device and the end registration array of the robotic arm;

[0024] Based on the fact that the connecting rods and joints of the robotic arm do not block the optical path when the end registration array is at the path point, combining the optical path boundary bounding box, the boundary bounding box of the connecting rods, and the boundary bounding box of the joints, a registration path point constraint expression for optical path occlusion is obtained.

[0025] In one embodiment, obtaining a physical boundary constraint model of the registration scenario of the robotic arm and determining a registration path point constraint expression includes:

[0026] Obtaining a boundary bounding box of the end registration array of the robotic arm, a boundary bounding box of the operating table, a sterile plane, and a boundary bounding box of the execution space;

[0027] Based on the fact that the end registration array of the robotic arm is in the sterile area above the operating table surface and inside the execution space during the registration movement, combining the boundary bounding box of the end registration array, the boundary bounding box of the operating table, the sterile plane, and the boundary bounding box of the execution space, a registration path point constraint expression for the working space is obtained.

[0028] The present application provides a device for generating registration path points of a robotic arm, and the device includes:

[0029] A side constraint processing module, configured to obtain a physical boundary constraint model of the registration scenario of the robotic arm and determine a registration path point constraint expression;

[0030] A feasible space generation module, configured to generate a feasible registration path point space according to the registration path point constraint expression;

[0031] A registration path point generation module, configured to generate a plurality of registration path points according to the feasible registration path point space; the plurality of registration path points are distributed dispersedly in the feasible registration path point space.

[0032] The present application provides a registration method for a surgical robot, and the method includes:

[0033] Obtain the registered path points obtained by the method for generating registered path points of the robotic arm as described above;

[0034] Control the robotic arm to perform registration according to the registered path points.

[0035] The present application provides a registration system for a surgical robot, and the system includes a processing device;

[0036] The processing device is configured to obtain registered path points according to the method for generating registered path points of the robotic arm as described above;

[0037] The processing device is further configured to send the registered path points to the robotic arm, so that the robotic arm performs registration according to the registered path points.

[0038] The present application provides a surgical robot system, and the system includes a robotic arm and a processing device; a terminal registration array is installed on the robotic arm;

[0039] The processing device is configured to obtain registered path points according to the method for generating registered path points of the robotic arm as described above;

[0040] The robotic arm is configured to drive the terminal registration array to move to the registered path points for registration.

[0041] The present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor executes the method for generating registered path points of the robotic arm as described above or the registration method of the surgical robot as described above.

[0042] The present application provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to execute the method for generating registered path points of the robotic arm as described above or the registration method of the surgical robot as described above.

[0043] The present application provides a computer program product, on which a computer program is stored, and the computer program is executed by a processor to execute the method for generating registered path points of the robotic arm as described above or the registration method of the surgical robot as described above.

[0044] The present application obtains a physical boundary constraint model of the robotic arm registration scenario, determines a registered path point constraint expression; according to the registered path point constraint expression, a computer device can automatically generate a feasible registered path point space, and generate multiple registered path points according to the feasible registered path point space, without relying on manual confirmation by the user or going through a cumbersome trial-and-error elimination process, improving the degree of automation, shortening the generation time of registered path points, and ensuring the passing rate of registered path points; moreover, the multiple generated registered path points are scattered, avoiding the situation where the automatically generated path points have a concentrated probability distribution. Description of the Drawings

[0045] Figure 1 Schematic diagram of a robot system based on optical navigation in an embodiment;

[0046] Figure 2 Flow schematic diagram of a method for generating registered path points of a robotic arm in an embodiment;

[0047] Figure 3 Schematic diagram of various constraints in an embodiment;

[0048] Figure 4 Schematic diagram of a collision model in an embodiment;

[0049] Figure 5 Schematic diagram of an optical path occlusion model in an embodiment;

[0050] Figure 6 Schematic diagram of a workspace model in an embodiment;

[0051] Figure 7 Schematic diagram of the shape of a bounding box in an embodiment;

[0052] Figure 8 Schematic diagram of selecting path points with dispersed distribution in an embodiment;

[0053] Figure 9 Structural block diagram of a device for generating registered path points of a robotic arm in an embodiment;

[0054] Figure 10 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0055] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] Referring to "embodiment" in the present application means that the specific features, structures or characteristics described in combination with the embodiment may be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments.

[0057] In a robotic system based on optical navigation, the position space formed by the movement of the robotic arm can be called the execution space, and the position space formed by the observation of the optical tracking device can be called the observation space. Before the robotic arm performs a task, robotic arm registration can be carried out. The main content of robotic arm registration is to write the position of the robotic arm base array in the robotic arm base coordinate system (the coordinate system set on the robotic arm base) into the memory.

[0058] When performing robotic arm registration, a tracer array (hereinafter referred to as the end registration array) can be installed at the end of the robotic arm. By controlling the movement of the end registration array, the movement trajectory of the end registration array in the execution space is aligned with the movement trajectory in the observation space, so as to obtain the conversion relationship between the execution space and the observation space during registration, that is, the conversion relationship between the robotic arm base coordinate system and the observation space coordinate system during registration; according to the conversion relationship between the robotic arm base coordinate system and the observation space coordinate system during registration, and the position of the robotic arm base array in the observation space coordinate system, the position of the robotic arm base array in the robotic arm base coordinate system can be obtained. After the robotic arm registration is completed, the end registration array can be removed from the end of the robotic arm, and during the operation, actuators such as surgical tools can be installed at the end of the robotic arm.

[0059] The position of the robotic arm base array relative to the robotic arm base coordinate system remains consistent during registration and during the operation; the position of the robotic arm base relative to the optical navigation device may not remain consistent during registration and during the operation. The conversion relationship between the robotic arm base coordinate system and the observation space coordinate system can be re-determined during the operation, that is, the conversion relationship between the execution space and the observation space during registration and during the operation can be re-determined.

[0060] During the operation, based on the observation of the robotic arm base array by the optical navigation device, the position of the robotic arm base array in the observation space coordinate system can be obtained; according to the position of the robotic arm base array in the observation space coordinate system and the position of the robotic arm base array in the robotic arm base coordinate system obtained through registration, the conversion relationship between the robotic arm base coordinate system and the observation space coordinate system during the operation can be obtained, so as to obtain the conversion relationship between the execution space and the observation space during registration and during the operation.

[0061] During the operation, the position of the actuators such as surgical tools installed at the end of the robotic arm in the robotic arm base coordinate system can be obtained, and the position of the optical tracer array on the patient in the observation space coordinate system can also be obtained. Based on the conversion relationship between the execution space and the observation space during registration and during the operation, the position of the actuator in the robotic arm base coordinate system and the position of the optical tracer array on the patient in the observation space coordinate system can be unified into the same space coordinate system.

[0062] Before registering the array movement at the control end, the path points used for the robot arm registration can be determined first. The method provided in this application can generate the path points used for the robot arm registration. This method can be executed by a computer device, which can be a part of a robot system. The method includes Figure 2 the steps shown:

[0063] Step S201, obtain the physical boundary constraint model of the robot arm registration scenario, and determine the registration path point constraint expression.

[0064] The registration process in the robot arm registration scenario is a dynamic process. Before registration, it is necessary to pre-generate the registration path points. The difficulty in generating the registration path points lies in the relatively complex physical boundary constraints between the robot arm and the operating environment during the registration process. For example: the collision constraint between the robot arm and the surrounding environment "obstacles", the light occlusion constraint between the end tracer array and the optical tracking device when the robot arm moves to the registration path point, the workspace constraint of the robot arm itself, the precision-coupled robot arm configuration space constraint, and the end tracer array attitude constraint, etc.

[0065] This application performs mathematical modeling on several types of physical boundary constraints involved in the registration process to obtain the analytical expressions of various physical boundary constraints. The analytical expressions of physical boundary constraints can be called physical boundary constraint models. Each physical boundary constraint model is used as the registration path point constraint expression.

[0066] The above several types of physical boundary constraints can include but are not limited to at least one of the following: the collision constraint of the robot arm, the light path occlusion constraint, the workspace constraint of the robot arm, the precision-coupled robot arm configuration constraint, and the attitude constraint of the end registration array, as Figure 3 shown.

[0067] Among them, the collision constraint of the robot arm is mainly to avoid collisions during the movement of the robot arm during registration. For example, during the movement of the robot arm, avoid collisions between the end of the robot arm and its own links at the path point attitude, avoid collisions between the robot arm links and the robot arm base array, avoid collisions between the robot arm links and the robot arm base surface, etc.

[0068] The light path occlusion constraint is mainly to avoid that the end registration array of the robot arm cannot be captured by the optical tracking array at the path point. Therefore, on the one hand, it can avoid the light path occlusion caused by the robot arm links to the end registration array, and on the other hand, it can avoid the light path crosstalk between the end registration array and the robot arm base array, and avoid the recognition of the tracer array.

[0069] The workspace constraint is mainly to meet the requirements of specific tasks, enabling the robotic arm to always be within a specific space during movement; in the scenario of performing a surgical task, the robotic arm is a sterile component in the surgical environment, and it should be within the sterile area during the movement at the time of registration of the robotic arm. The sterile area can specifically be set above the base surface of the robotic arm; in addition, the end effector of the robotic arm should be located within the workspace, the execution space, and the observation space.

[0070] The robotic arm configuration constraint can include two categories. One is the limitation on the movement range of each joint. Limiting the joint movement range can enable the robotic arm to move within a joint configuration interval with higher precision, facilitating the calibration compensation of the robotic arm and ensuring the positioning accuracy when the robotic arm performs corresponding tasks. The other is the limitation on the difference magnitude between the joint configurations of the robotic arm at adjacent path points, avoiding large changes in the joint configuration when the robotic arm moves from the previous path point to the next path point and avoiding large unexpected movements.

[0071] The attitude constraint of the end registration array. This constraint mainly considers the error characteristics of the optical tracking device and restricts the attitude of the end registration array of the robotic arm at the path point to facilitate being observed by the optical tracking device.

[0072] Step S202: Generate a feasible registration path point space according to the registration path point constraint expression.

[0073] After obtaining the registration path point constraint expression, a feasible registration path point space can be generated. The space composed of the feasible registration path points that satisfy the set registration path point constraint expression is the feasible registration path point space. For example, when the registration path point constraint expression includes a collision constraint, the space composed of all feasible registration path points that do not collide is the feasible registration path point space.

[0074] Step S203: Generate multiple registration path points according to the feasible registration path point space; the multiple registration path points are distributed dispersedly in the feasible registration path point space.

[0075] When the distribution dispersion degree of the multiple registration path points in the feasible registration path point space is higher than the set value, it can be determined that the multiple registration path points are distributed dispersedly in the feasible registration path point space.

[0076] In this embodiment, a physical boundary constraint model of the robotic arm registration scenario is obtained, and a registration path point constraint expression is determined; according to the registration path point constraint expression, the computer device can automatically generate a feasible registration path point space, and generate multiple registration path points based on the feasible registration path point space, without relying on manual confirmation by the user or going through a cumbersome trial-and-error elimination process, improving the degree of automation, shortening the generation time of the registration path points, and ensuring the passing rate of the registration path points; moreover, the multiple generated registration path points are distributed dispersedly, avoiding the situation where the automatically generated path points have a concentrated probability distribution.

[0077] In one embodiment, obtaining a physical boundary constraint model of the robotic arm registration scenario and determining a registration path point constraint expression in step S201 includes: obtaining a bounding box of the robotic arm base array boundary, a bounding box of the robotic arm base body boundary, a bounding box of the robotic arm's connecting rod boundary, and a bounding box of the joint boundary; based on the fact that the connecting rods and joints are not located within the bounding box space of the robotic arm base array during the movement of the robotic arm between adjacent path points, combining the bounding box of the robotic arm base array boundary, the bounding box of the connecting rod boundary, and the bounding box of the joint boundary, a first collision physical boundary constraint model between each connecting rod and joint of the robotic arm and the robotic arm base array is obtained; according to the first collision physical boundary constraint model, a registration path point constraint expression is obtained.

[0078] The robotic arm includes joints and connecting rods. Correspondingly, a bounding box of the joint boundary and a bounding box of the connecting rod boundary can be constructed, as Figure 4 shown. Specifically, a spherical bounding box can be used to approximate the boundary where the joint is located to obtain the bounding box of the joint boundary; specifically, a cylindrical bounding box can be used to approximate the boundary where the connecting rod is located to obtain the bounding box of the connecting rod boundary. In addition, a rectangular parallelepiped bounding box can be specifically used to approximate the active interval of the robotic arm base array to obtain the bounding box of the robotic arm base array boundary.

[0079] The collision constraints between each connecting rod of the robotic arm and the robotic arm base array and the collision constraints between each joint of the robotic arm and the robotic arm base array belong to the collision constraints between the robotic arm and the robotic arm base array. This collision constraint requires that during the movement of the robotic arm from the previous registration path point to the next registration path point, the connecting rods and joints are not located within the active space of the robotic arm base array; thus, according to the bounding box of the robotic arm base array boundary, the bounding box of the connecting rod boundary, and the bounding box of the joint boundary, a collision physical boundary constraint model between each connecting rod and joint of the robotic arm and the robotic arm base array can be obtained. To distinguish it from other collision physical boundary constraint models, the collision physical boundary constraint model between each connecting rod and joint of the robotic arm and the robotic arm base array is called the first collision physical boundary constraint model, and this first collision physical boundary constraint model is used as one of the registration path point constraint expressions.

[0080] The first collision physical boundary constraint model between each link of the robotic arm and the robotic arm base array can specifically be: an analytical expression for calculating the minimum directed distance from a point on the axis of the link bounding box to the surface of the active interval bounding box of the robotic arm base array (the distance direction can be defined as positive from the surface to the axis), and this minimum directed distance is greater than the size of the link bounding box.

[0081] The first collision physical boundary constraint model between the robotic arm joint and the robotic arm base array can specifically be: an analytical expression for calculating the minimum directed distance from the center of the sphere of the joint bounding box to the surface of the robotic arm base array bounding box (the distance direction can be defined as positive from the surface to the center of the sphere), and this minimum directed distance is greater than the size of the joint bounding box.

[0082] In one embodiment, obtaining the physical boundary constraint model of the robotic arm registration scenario in step S201 and determining the registration path point constraint expression includes: obtaining the boundary bounding box of the robotic arm base body, the link boundary bounding box of the robotic arm, and the joint boundary bounding box; based on the fact that the links and joints of the robotic arm do not collide with the robotic arm base body during the movement of the robotic arm between adjacent path points, combining the boundary bounding box of the robotic arm base body, the link boundary bounding box, and the joint boundary bounding box to obtain the second collision physical boundary constraint model between each link and joint of the robotic arm and the robotic arm base body; and obtaining the registration path point constraint expression according to the second collision physical boundary constraint model.

[0083] For the collision constraints between each link of the robotic arm and the robotic arm base body and the collision constraints between each joint of the robotic arm and the robotic arm base body, it is required that during the movement of the robotic arm from the previous registration path point to the next registration path point, the links and joints do not collide with the robotic arm base body. The robotic arm base body can be approximated by a cuboid bounding box to obtain the boundary bounding box of the robotic arm base body.

[0084] Combining the link boundary bounding box and the boundary bounding box of the robotic arm base body, the collision physical boundary constraint model between each link of the robotic arm and the robotic arm base body can be obtained. For the sake of distinction, the collision physical boundary constraint model between each link of the robotic arm and the robotic arm base body can be called the second collision physical boundary constraint model; using the second collision physical boundary constraint model between each link of the robotic arm and the robotic arm base body as one of the expressions for obtaining the registration path point constraint. The second collision physical boundary constraint model between each link of the robotic arm and the robotic arm base body can specifically be: an analytical expression for calculating the minimum directed distance from a point on the axis of the link bounding box to the surface of the robotic arm base bounding box (the distance direction can be defined as positive from the surface to the axis), and this minimum directed distance is greater than the size of the link bounding box.

[0085] Combining the joint bounding box and the robotic arm base body bounding box, a collision physical boundary constraint model between each joint of the robotic arm and the robotic arm base body can be obtained. For the sake of distinction, the collision physical boundary constraint model between each joint of the robotic arm and the robotic arm base body can be referred to as the second collision physical boundary constraint model. The second collision physical boundary constraint model between each joint of the robotic arm and the robotic arm base body can specifically be: an analytical expression for calculating the minimum directed distance from the center of the sphere of the joint bounding box to the surface of the robotic arm base bounding box (it can be defined that the direction of the distance from the surface to the center of the sphere is the positive direction), and this minimum directed distance is greater than the size of the joint bounding box.

[0086] In one embodiment, the method provided by the present application further includes: based on the fact that the connecting rods and joints do not collide during the movement of the robotic arm between adjacent path points, combining the connecting rod bounding box and the joint bounding box to obtain a third collision physical boundary constraint model between each connecting rod and joint of the robotic arm; according to the third collision physical boundary constraint model, obtaining a registered path point constraint expression.

[0087] The collision constraint between each connecting rod and joint of the robotic arm requires that: during the process of the robotic arm moving from the previous path point to the next path point, no collision occurs between the connecting rods and joints.

[0088] Combining the connecting rod bounding box and the joint bounding box, a collision physical boundary constraint model between each connecting rod and joint of the robotic arm can be obtained. For the sake of distinction, the collision physical boundary constraint model between each connecting rod and joint of the robotic arm can be referred to as the third collision physical boundary constraint model.

[0089] In one embodiment, obtaining the physical boundary constraint model of the robotic arm registration scenario and determining the registered path point constraint expression in step S201 may include: obtaining the optical path bounding box, the connecting rod bounding box of the robotic arm, and the joint bounding box; the optical path bounding box is the boundary model of the optical path between the optical tracking device and the end registration array of the robotic arm; based on the fact that the connecting rods and joints of the robotic arm do not block the optical path when the end registration array is at the path point, combining the optical path bounding box, the connecting rod bounding box, and the joint bounding box to obtain an optical path occlusion physical boundary constraint model; according to the optical path occlusion physical boundary constraint model, obtaining a registered path point constraint expression.

[0090] The optical path occlusion constraint is mainly to ensure that the optical path between the optical tracking device and the end registration array is not blocked. The end registration array and the optical tracking device can be connected by a line to form a polyhedral bounding box as shown in Figure 5 The optical path between the optical tracking device and the end registration array is located inside the polyhedral bounding box, and this polyhedral bounding box can be referred to as the optical path bounding box.

[0091] To avoid optical path occlusion, when the end registration array is at the path point, the linkages and joints of the robotic arm are restricted outside the polyhedral bounding box. Thus, a physical boundary constraint model for optical path occlusion corresponding to the linkages and a physical boundary constraint model for optical path occlusion corresponding to the joints can be constructed. The physical boundary constraint model for optical path occlusion corresponding to the linkages and the physical boundary constraint model for optical path occlusion corresponding to the joints are used as one of the registration path point constraint expressions.

[0092] The physical boundary constraint model for optical path occlusion corresponding to the linkages can specifically be: an analytical expression for calculating the minimum directed distance from a point on the axis of the linkage bounding box to the surface of the polyhedral bounding box, where this minimum directed distance is greater than the size of the linkage bounding box.

[0093] The physical boundary constraint model for optical path occlusion corresponding to the joints can specifically be: an analytical expression for calculating the minimum directed distance from the center of the sphere of the joint bounding box to the surface of the polyhedral bounding box, where this minimum directed distance is greater than the size of the joint bounding box.

[0094] In one embodiment, obtaining the physical boundary constraint model of the robotic arm registration scenario and determining the registration path point constraint expression in step S201 may include: obtaining the boundary bounding box of the end registration array of the robotic arm, the boundary bounding box of the operating table, the sterile plane, and the boundary bounding box of the execution space; based on the fact that the end registration array of the robotic arm is in the sterile area above the operating table surface and inside the execution space during the registration movement process, combining the end registration array model, the boundary bounding box of the operating table, the sterile plane, and the boundary bounding box of the execution space to obtain the physical boundary constraint model of the working space; and obtaining the registration path point constraint expression according to the physical boundary constraint model of the working space.

[0095] In the scenario where the robotic arm performs a surgical task, as Figure 6 shown, the working space can be defined as the area where the patient's surgical site is located when the robotic arm and the operating table are in a specified pose, and it can be described using a cuboid bounding box. To meet the sterile requirements of the surgery, the robotic arm needs to move in the sterile area above the operating table surface. Therefore, a sterile plane can be defined, requiring the robotic arm to always be above the sterile plane during the movement process. Additionally, it can be set that the end effector of the robotic arm is inside the execution space, and correspondingly, the end registration array is inside the execution space.

[0096] Therefore, by combining the boundary bounding box of the end registration array, the boundary bounding box of the operating table, the sterile plane, and the boundary bounding box of the execution space, the physical boundary constraint model of the working space can be obtained, and the physical boundary constraint model of the working space is used as one of the registration path point constraint expressions.

[0097] It can be understood that the shapes of the above-mentioned bounding boxes are not limited to spherical, cylindrical, and cuboid shapes, and convex geometric bodies composed of lines and planes can be used, as Figure 7 shown.

[0098] In one embodiment, mathematical models are established for various physical boundary constraints involved in the registration process to obtain various physical boundary constraint models. Based on the various physical boundary constraint models, the registration path point constraint expressions are formed as follows:

[0099] (1)

[0100] (2)

[0101] (3)

[0102] (4)

[0103] (5)

[0104] Wherein, represents the joint angle corresponding to a certain joint at the th path point; represents the interval for restricting the motion range of the joint; represents the difference in the joint angles of a certain joint at adjacent path points, represents the interval for restricting the change amount of the joint angles at adjacent path points; represents the position of the end of the robotic arm in the execution space coordinate system under the th path point; represents the position of the end of the robotic arm in the observation space coordinate system under the th path point; represents the working space; represents the observable space of the optical tracking device; wherein, represents the position function of all discrete points on each joint of the robotic arm, represents the polyhedron bounding box function of the collision boundary (such as the bounding box function of the robotic arm base enclosure, the bounding box function of the active interval of the robotic arm base array) and the optical path occlusion. The condition of no collision and no occlusion is that the points on each joint of the robotic arm do not intersect with the corresponding bounding box function.

[0105] Formula (1) is the constraint on the motion range of the joint in the robotic arm configuration constraint, so that the robotic arm moves within the joint configuration interval with higher precision. Formula (2) is the constraint on the difference in joint configurations at adjacent path points in the robotic arm configuration constraint, to avoid large changes in joint configurations when the robotic arm moves between two adjacent path points. Formula (3) is the working space constraint. Formula (4) is the observable space constraint of the optical tracking device. Formula (5) is the optical path occlusion constraint and the collision constraint.

[0106] On the motion trajectory between adjacent path points, the motion trajectory of the robotic arm can be discretized into nodes. The position of the robotic arm at each discrete point can be described as a function of joint angles, as shown in the following formula: ;

[0107] To simplify the calculation, any point on the joints and links of the robotic arm, as its position changes with the joint angles, can be described in polar coordinate form. Discretize the motion trajectory of the robotic arm between adjacent path points at certain time and space intervals to obtain discrete trajectory points, from which the positions of multiple discrete points on the joints and links of the robotic arm at different discrete trajectory points can be obtained. Calculate the minimum distances between the discrete points on the joints and links of the robotic arm, and between each discrete point and the bounding box of the robotic arm base, the active interval bounding box of the robotic arm base array, and the polyhedral bounding box of the optical path occlusion, and then it can be determined whether the robotic arm collides or there is optical path occlusion.

[0108] In one embodiment, generating multiple registration path points according to the feasible registration path point space in step S203 may include: serially generating multiple registration path points according to the feasible registration path point space; in the process of serially generating non-first registration path points, obtain the distribution dispersion degree between each feasible registration path point in the feasible registration path point space and the generated registration path points, and determine, among each feasible registration path point, the ones to be used as the multiple non-first registration path points according to the magnitudes of the distribution dispersion degrees corresponding to each feasible registration path point.

[0109] In the process of generating a certain number of registration path points, the position of the next registration path point to be generated can be dynamically adjusted according to the positions of the generated registration path points. Therefore, it is necessary to serially construct the objective function of each registration path point to maximize the sum of the distance norms between the registration path point to be generated and the generated registration path points, so as to ensure that the generated registration path points are as scattered as possible.

[0110] Exemplarily, when generating the i-th registration path point, the feasible registration path point space corresponding to the i-th registration path point can be obtained. For each feasible registration path point in the feasible registration path point space, the distances between this feasible registration path point and the 1st to the i-1th registration path points can be obtained, and the sum of these distances is calculated to obtain the distance sum corresponding to this feasible registration path point, from which the distribution dispersion degree between this feasible registration path point and the generated registration path points is obtained; the larger the distance sum, the larger the distribution dispersion degree. The larger the distribution dispersion degree, the greater the probability of being selected as the i-th registration path point.

[0111] Further, based on the distance sum of each feasible registration path point, the distribution dispersion degree between each feasible registration path point and the generated registration path point can be obtained, which may include: dividing the distance corresponding to each feasible registration path point by the number of generated registration path points to obtain the average distance corresponding to each feasible registration path point; and based on the average distance corresponding to each feasible registration path point, obtaining the distribution dispersion degree between each feasible registration path point and the generated registration path point.

[0112] When generating a non-first registration path point, it can be set that the to-be-generated registration path point is as far away from the generated registration path point as possible, and the sum of the squared distances between the to-be-generated registration path point and the generated registration path points is as large as possible. The corresponding objective function can be . Wherein, represents the average value of the positions of the generated registration path points.

[0113] In one embodiment, the method provided in this application further includes: when generating the first registration path point, determining the first registration path point from multiple feasible registration path points according to the magnitude of the central distance between the feasible registration path point and the center of the feasible registration path point space.

[0114] When generating the first registration path point, it can be set that the first registration path point is as much as possible inside the feasible registration path point space, and the central distance between the first registration path point and the center of the feasible registration path point space is the smallest. The corresponding objective function can be expressed as .

[0115] The path point selection in this application can be sequential selection, so that the position of the next to-be-generated path point can be dynamically adjusted according to the positions of the already selected path points; as Figure 8 shown, the area composed of polygons represents the physical boundary of one of the characteristics that the path points need to satisfy. The solid dots represent the already selected path points, and the hollow dots represent the to-be-generated path points. The positions of the hollow dots can be dynamically adjusted according to the positions of the solid dots to avoid concentration with the solid dots.

[0116] In one embodiment, various physical boundary constraints involved in the robotic arm registration process can be mathematically modeled to obtain various physical boundary constraint models, and based on various physical boundary constraint models, a registration path point constraint expression can be obtained. If the physical boundary constraints shown in Figure 3 are mathematically modeled, a registration path point constraint expression including the above formulas (1) to (5) can be obtained.

[0117] Based on the above registration path point constraint expressions, select the registration path points in sequence; when selecting each registration path point, based on the registration path point constraint expressions, determine the feasible registration path point space used for the current selection (which can be simply referred to as the current feasible space), and aim at the scattered distribution of the selected feasible registration path points to determine the currently selected registration path point in the current feasible space.

[0118] For example, when selecting the (i - 1)-th registration path point, based on the registration path point constraint expressions, obtain the feasible space required for selecting the (i - 1)-th registration path point, and aim at the scattered distribution of the selected feasible registration path points to select the (i - 1)-th registration path point in the feasible space required for selecting the (i - 1)-th registration path point.

[0119] For another example, when selecting the i-th registration path point, based on the registration path point constraint expressions, obtain the feasible space required for selecting the i-th registration path point, and aim at the scattered distribution of the selected feasible registration path points to select the i-th registration path point in the feasible space required for selecting the i-th registration path point.

[0120] The feasible space required for selecting the (i - 1)-th registration path point and the feasible space required for selecting the i-th registration path point may be different or the same, which mainly depends on whether the registration path point constraint expressions involve variables related to the already selected registration path points. For example, when the registration path point constraint expressions include formula (2), formula (2) involves variables related to the (i - 1)-th registration path point, that is, variables related to the already selected registration path points, and the feasible space required for selecting the (i - 1)-th registration path point and the feasible space required for selecting the i-th registration path point will change.

[0121] When determining the current feasible space based on the registration path point constraint expressions, specifically, the first-order Taylor method can be adopted to linearly expand the registration path point constraint expressions, thereby approximately linearizing the non-linear optimization problem, finding the iterative direction of the optimal point through the linear convex optimization algorithm, and performing one-dimensional search in this iterative direction to obtain the current feasible space that satisfies the registration path point constraint expressions.

[0122] If the registration path point constraint expressions include the above formulas (1) to (5), then formulas (1) to (5) can be linearly expanded to obtain:

[0123] (6)

[0124] (7)

[0125] (8)

[0126] (9)

[0127] (10)

[0128] where , is the Jacobian gradient matrix of the end - effector pose of the robotic arm with respect to the joint angles. Formulas (6) to (10) respectively correspond to the first - order Taylor expansions of Formulas (1) to (5). Thus, the non - linear optimization problem can be approximated as a linear one. By using a linear convex optimization algorithm to find the iterative direction of the optimal point and performing a one - dimensional search along this iterative direction, the current feasible space that satisfies the registration path point constraint expression can be obtained.

[0129] When approximating the non - linear optimization problem as a linear one, other algorithms can also be used, such as modern optimization strategies like quadratic programming, non - linear programming, genetic algorithms, and evolutionary algorithms.

[0130] Aiming at the scattered distribution of the selected feasible registration path points, the currently selected registration path points are determined in the current feasible space. Specifically, a number of already - selected feasible registration path points are obtained, and an objective function is constructed based on these already - selected feasible registration path points. This objective function can be called the objective function used for the current selection (abbreviated as the current objective function). With the goal of minimizing the current objective function, the currently selected registration path points are determined in the current feasible space.

[0131] For example, when selecting the (i - 1) - th registration path point, the number of already - selected feasible registration path points includes: the 1st to the (i - 2) - th feasible registration path points. An objective function is constructed based on the 1st to the (i - 2) - th feasible registration path points, and this objective function is called the objective function used for selecting the (i - 1) - th registration path point. With the goal of minimizing the objective function used for selecting the (i - 1) - th registration path point, the (i - 1) - th registration path point is selected in the feasible space required for selecting the (i - 1) - th registration path point.

[0132] For example, when selecting the i - th registration path point, the number of already - selected feasible registration path points includes: the 1st to the (i - 1) - th feasible registration path points. An objective function is constructed based on the 1st to the (i - 1) - th feasible registration path points, and this objective function is called the objective function used for selecting the i - th registration path point. With the goal of minimizing the objective function used for selecting the i - th registration path point, the i - th registration path point is selected in the feasible space required for selecting the i - th registration path point.

[0133] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0134] In one embodiment, as Figure 9 shown, a registration path point generation device for a robotic arm is provided, including:

[0135] A constraint processing module 901, configured to obtain a physical boundary constraint model of the robotic arm registration scenario and determine a registration path point constraint expression;

[0136] A feasible space generation module 902, configured to generate a feasible registration path point space according to the registration path point constraint expression;

[0137] A registration path point generation module 903, configured to generate a plurality of registration path points according to the feasible registration path point space; the plurality of registration path points are distributed dispersedly in the feasible registration path point space.

[0138] In one embodiment, the registration path point generation module 903 is configured to serially generate a plurality of registration path points according to the feasible registration path point space; during the process of serially generating non-first registration path points, obtain the distribution dispersion degree between each feasible registration path point in the feasible registration path point space and the already generated registration path points, and determine a plurality of the non-first registration path points among each feasible registration path point according to the magnitudes of the distribution dispersion degrees corresponding to each feasible registration path point.

[0139] In one embodiment, the registration path point generation module 903 is configured to determine the first registration path point from a plurality of feasible registration path points according to the magnitude of the central distance between the feasible registration path point and the center of the feasible registration path point space when generating the first registration path point.

[0140] In one embodiment, the constraint processing module 901 is configured to obtain the bounding box of the robotic arm base array, the bounding box of the link of the robotic arm, and the bounding box of the joint; based on the fact that the links and joints are not located within the bounding box space of the robotic arm base array during the movement of the robotic arm between adjacent path points, and combining the bounding box of the robotic arm base array, the bounding box of the link, and the bounding box of the joint, obtain a first collision physical boundary constraint model between each link and joint of the robotic arm and the robotic arm base array; according to the first collision physical boundary constraint model, obtain a registered path point constraint expression.

[0141] In one embodiment, the constraint processing module 901 is configured to obtain the bounding box of the robotic arm base body, the bounding box of the link of the robotic arm, and the bounding box of the joint; based on the fact that the links and joints do not collide with the robotic arm base body during the movement of the robotic arm between adjacent path points, and combining the bounding box of the robotic arm base body, the bounding box of the link, and the bounding box of the joint, obtain a second collision physical boundary constraint model between each link and joint of the robotic arm and the robotic arm base body; according to the second collision physical boundary constraint model, obtain a registered path point constraint expression.

[0142] In one embodiment, the constraint processing module 901 is configured to, based on the fact that the links and joints do not collide during the movement of the robotic arm between adjacent path points, and combining the bounding box of the link and the bounding box of the joint, obtain a third collision physical boundary constraint model between each link and joint of the robotic arm; according to the third collision physical boundary constraint model, obtain a registered path point constraint expression.

[0143] In one embodiment, the constraint processing module 901 is configured to obtain the bounding box of the optical path, the bounding box of the link of the robotic arm, and the bounding box of the joint; the bounding box of the optical path is the bounding box of the optical path between the optical tracking device and the end registration array of the robotic arm; based on the fact that the links and joints of the robotic arm do not block the optical path when the end registration array is at the path point, and combining the bounding box of the optical path, the bounding box of the link, and the bounding box of the joint, obtain an optical path occlusion physical boundary constraint model; according to the optical path occlusion physical boundary constraint model, obtain a registered path point constraint expression.

[0144] In one embodiment, a constraint processing module 901 is configured to obtain a bounding box of the end registration array of the robotic arm, a bounding box of the operating table, a sterile plane, and a bounding box of the execution space boundary; based on the fact that the end registration array of the robotic arm is in the sterile area above the operating table surface and inside the execution space during the registration movement, and in combination with the end registration array bounding box, the operating table bounding box, the sterile plane, and the execution space boundary bounding box, obtain a physical boundary constraint model of the working space; and according to the physical boundary constraint model of the working space, obtain a constraint expression of the registration path points.

[0145] For the specific limitations on the registration path point generation device of the robotic arm, reference may be made to the limitations on the registration path point generation method of the robotic arm in the foregoing text, which will not be elaborated here. Each module in the above-mentioned registration path point generation device of the robotic arm can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0146] In one embodiment, a computer device is provided, and its internal structure diagram can be as Figure 10 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the registration path point generation data of the robotic arm. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer device also includes an input / output interface, and the input / output interface is a connection circuit for exchanging information between the processor and external devices. They are connected to the processor through a bus, abbreviated as the I / O interface. When the computer program is executed by the processor, it implements a method for generating registration path points of a robotic arm.

[0147] Those skilled in the art can understand that Figure 10 the structure shown in

[0148] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps in the embodiment of the method for generating registered path points of the above robotic arm, or the steps in the embodiment of the registration method of the above surgical robot.

[0149] In one embodiment, a registration method for a surgical robot is provided. The method includes:

[0150] Obtain the registered path points obtained in any one of the embodiments of the method for generating registered path points of the above robotic arm;

[0151] Control the robotic arm to perform registration according to the registered path points.

[0152] In one embodiment, a registration system for a surgical robot is provided. The system includes a processing device;

[0153] The processing device is configured to obtain registered path points according to any one of the embodiments of the method for generating registered path points of the above robotic arm;

[0154] The processing device is further configured to send the registered path points to the robotic arm so that the robotic arm performs registration according to the registered path points.

[0155] In one embodiment, a surgical robot system is provided. The system includes a robotic arm and a processing device; the robotic arm is equipped with an end registration array;

[0156] The processing device is configured to obtain registered path points according to any one of the embodiments of the method for generating registered path points of the above robotic arm;

[0157] The robotic arm is configured to drive the end registration array to move to the registered path points for registration.

[0158] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the embodiment of the method for generating registered path points of the above robotic arm, or the steps in the embodiment of the registration method of the above surgical robot.

[0159] In one embodiment, a computer program product is provided, on which a computer program is stored. The computer program is executed by a processor to implement the steps in the embodiment of the method for generating registered path points of the above robotic arm, or the steps in the embodiment of the registration method of the above surgical robot.

[0160] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The above computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0161] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0162] The above embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for generating registered path points of a robotic arm, characterized in that, The method includes: Obtaining a physical boundary constraint model of the robotic arm registration scenario and determining a registration path point constraint expression; Generating a feasible registration path point space according to the registration path point constraint expression; Generating a plurality of registration path points according to the feasible registration path point space; the plurality of registration path points are distributed dispersedly in the feasible registration path point space.

2. The method according to claim 1, wherein Generating a plurality of registration path points according to the feasible registration path point space includes: Sequentially generating a plurality of registration path points according to the feasible registration path point space; During the process of sequentially generating non-first registration path points, obtaining the distribution dispersion degree between each feasible registration path point in the feasible registration path point space and the generated registration path points, and determining a plurality of the non-first registration path points among each feasible registration path point according to the magnitudes of the distribution dispersion degrees corresponding to each feasible registration path point.

3. The method according to claim 2, characterized in that, The method further includes: When generating the first registration path point, determining the first registration path point from a plurality of feasible registration path points according to the magnitude of the central distance between the feasible registration path point and the center of the feasible registration path point space.

4. The method according to claim 1, wherein Obtaining a physical boundary constraint model of the robotic arm registration scenario and determining a registration path point constraint expression includes: Obtaining the bounding box of the robotic arm base array, the bounding box of the robotic arm link, and the bounding box of the joint; Based on the fact that the links and joints of the robotic arm are not located within the bounding box space of the robotic arm base array during the movement of the robotic arm between adjacent path points, combining the bounding box of the robotic arm base array, the bounding box of the link, and the bounding box of the joint, obtaining a first collision physical boundary constraint model between each link and joint of the robotic arm and the robotic arm base array; Obtaining a registration path point constraint expression according to the first collision physical boundary constraint model.

5. The method according to claim 1, characterized in that Obtaining a physical boundary constraint model of the robotic arm registration scenario and determining a registration path point constraint expression includes: Obtaining the bounding box of the robotic arm base body, the bounding box of the robotic arm link, and the bounding box of the joint; Based on the fact that the links and joints of the robotic arm do not collide with the robotic arm base body during the movement of the robotic arm between adjacent path points, combining the bounding box of the robotic arm base body, the bounding box of the link, and the bounding box of the joint, obtaining a second collision physical boundary constraint model between each link and joint of the robotic arm and the robotic arm base body; Obtaining a registration path point constraint expression according to the second collision physical boundary constraint model.

6. The method according to claim 4 or 5, characterized in that, The method further includes: Based on the fact that the links and joints of the robotic arm do not collide during the movement of the robotic arm between adjacent path points, combining the bounding box of the link and the bounding box of the joint, obtaining a third collision physical boundary constraint model between each link and joint of the robotic arm; Obtaining a registration path point constraint expression according to the third collision physical boundary constraint model.

7. The method according to claim 1, characterized in that, Obtaining a physical boundary constraint model of the robotic arm registration scenario and determining a registration path point constraint expression includes: Obtaining the bounding box of the optical path, the bounding box of the robotic arm link, and the bounding box of the joint; the bounding box of the optical path is the bounding box of the optical path between the optical tracking device and the end registration array of the robotic arm; Based on the fact that the linkages and joints of the robotic arm do not block the optical path when at the path points of the end registration array, combining the optical path boundary bounding box, the linkage boundary bounding box, and the joint boundary bounding box, an optical path occlusion physical boundary constraint model is obtained; According to the optical path occlusion physical boundary constraint model, a registration path point constraint expression is obtained.

8. The method according to claim 1, wherein Obtain the physical boundary constraint model of the robotic arm registration scenario and determine the registration path point constraint expression, including: Obtain the boundary bounding box of the end registration array of the robotic arm, the boundary bounding box of the operating table, the sterile plane, and the boundary bounding box of the execution space; Based on the fact that the end registration array of the robotic arm is in the sterile area above the operating table surface and inside the execution space during the registration movement, combining the boundary bounding box of the end registration array, the boundary bounding box of the operating table, the sterile plane, and the boundary bounding box of the execution space, a working space physical boundary constraint model is obtained; According to the working space physical boundary constraint model, a registration path point constraint expression is obtained.

9. A registration path point generation device for a robotic arm, characterized in that, The device includes: A constraint processing module, configured to obtain the physical boundary constraint model of the robotic arm registration scenario and determine the registration path point constraint expression; A feasible space generation module, configured to generate a feasible registration path point space according to the registration path point constraint expression; A registration path point generation module, configured to generate a plurality of registration path points according to the feasible registration path point space; the plurality of registration path points are distributed dispersedly in the feasible registration path point space.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the method described in any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the method described in any one of claims 1 to 8 is implemented.

12. A registration method for a surgical robot, characterized in that, The method includes: Obtain the registration path points obtained by the method described in any one of claims 1 to 8; Control the robotic arm to perform registration according to the registration path points.

13. A registration system for a surgical robot, characterized in that, The system includes a processing device; The processing device is configured to obtain the registration path points by the method described in any one of claims 1 to 8; The processing device is further configured to send the registration path points to the robotic arm so that the robotic arm performs registration according to the registration path points.

14. A surgical robot system, characterized in that, The system includes a robotic arm and a processing device; the robotic arm is equipped with an end registration array; The processing device is configured to obtain the registration path points by the method described in any one of claims 1 to 8; The robotic arm is configured to drive the end registration array to move to the registration path points for registration.

Images