Registration precision verification method, system, device and equipment of mechanical arm and medium

Abstract

The invention relates to a registration precision verification method, system and device of a mechanical arm, equipment and a medium. The method comprises the following steps: determining a first position of an actual verification point on a target object from a medical image; according to the first position and the registration result of the mechanical arm, multiple tail end poses of the mechanical arm are determined; when the mechanical arm is in each tail end pose, tail end tools of the mechanical arm point to the conversion verification point; the conversion verification point is obtained by converting the first position through the registration result; and controlling the mechanical arm to move based on the tail end poses so as to verify the registration precision of the mechanical arm. That is, in the embodiment of the invention, a plurality of postures under one verification point are adopted to realize spatial registration verification, so that compared with a traditional mode that a plurality of verification points are adopted and each verification point corresponds to one posture, various misjudgment situations existing in a traditional method can be avoided, the precision verification has uniqueness, and the verification accuracy is improved. Therefore, the verification accuracy and effectiveness are improved, the operation process can be simplified, and the verification efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of robotics technology, and in particular to a method, system, apparatus, device, and medium for verifying the registration accuracy of a robotic arm. Background Technology

[0002] With the development of robotics technology, robots are increasingly used in the medical field. For example, robots are frequently used to assist in neurosurgery. Before surgery, it is necessary to spatially register the patient's medical images and the robot system to obtain the spatial coordinate transformation relationship between the image coordinate system and the robot coordinate system. The accuracy of the spatial registration directly affects the accuracy of the surgical procedure; therefore, after registration, the accuracy of the obtained spatial coordinate transformation relationship needs to be verified. However, current verification methods suffer from inaccuracies. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, system, device, computer equipment, computer-readable storage medium, and computer program product for verifying the registration accuracy of a robotic arm, which can improve the verification accuracy of the robotic arm's spatial registration, in order to address the above-mentioned technical problems.

[0004] Firstly, this application provides a method for verifying the registration accuracy of a robotic arm, comprising:

[0005] Determine the first location of the actual verification point on the target object from medical images;

[0006] Based on the first position and the registration result of the robotic arm, multiple end-effector poses of the robotic arm are determined; when the robotic arm is in each end-effector pose, the end-effector tool of the robotic arm points to the conversion verification point; the conversion verification point is obtained by converting the first position through the registration result;

[0007] The robot arm's movement is controlled based on the pose of each end effector to verify the registration accuracy of the robot arm.

[0008] In one embodiment, based on the first position and the registration result of the robotic arm, multiple end-effector poses of the robotic arm are determined, including:

[0009] Identify multiple secondary locations from medical images;

[0010] Based on the second position, the first position, and the registration results, the multiple end-effector poses of the robotic arm are determined.

[0011] In one embodiment, the angle between the line connecting each second position and the first position and the preset puncture path of the target object in the medical image is a preset angle; the preset puncture path passes through the first position.

[0012] In one embodiment, the preset puncture path is perpendicular to the tangent plane at a first position on the target object.

[0013] In one embodiment, multiple second locations are determined from medical images, including:

[0014] Determine the pre-designed puncture path passing through the first location from medical images;

[0015] Based on a preset angle, multiple second positions are determined around the preset puncture path; the angle between the line connecting each second position and the first position and the preset puncture path is also a preset angle.

[0016] In one embodiment, a plurality of second positions around a preset puncture path are determined according to a preset angle, including:

[0017] Based on the first position and the preset sphere radius, determine the sphere centered on the actual verification point;

[0018] The target cross section passing through the preset puncture path is determined according to the preset angle, and the arc where the target cross section intersects the sphere is determined.

[0019] Multiple points on the arc are identified as multiple second positions around the preset puncture path.

[0020] In one embodiment, determining the target cross-section passing through the preset puncture path based on a preset angle includes:

[0021] Based on the preset angle and preset ball radius, determine the target point on the preset puncture path;

[0022] The plane that passes through the target point and is perpendicular to the preset puncture path is taken as the target cross section.

[0023] In one embodiment, the preset angle is 45°.

[0024] In one embodiment, the end effector is a light source; when the robotic arm is in each end effector pose, the light emission direction of the light source is always pointing towards the conversion verification point.

[0025] In one embodiment, the light source emits light continuously during the movement of the robotic arm; or, the light source emits light when the robotic arm moves to each end-effector pose.

[0026] In one embodiment, the movement of the robotic arm is controlled based on the pose of each end effector to verify the registration accuracy of the robotic arm, including:

[0027] The robot arm is moved sequentially based on the pose of each end effector. The registration accuracy of the robot arm is verified by the distance between the light spot on the target object and the actual verification point when the robot arm moves to each end effector pose.

[0028] In one embodiment, the method further includes:

[0029] Determine whether the movement trajectory of the robotic arm meets the preset trajectory requirements and obtain the trajectory judgment result; the preset trajectory requirements include that the offset angle between the central axis of the movement trajectory of the robotic arm and the preset puncture path of the target object is less than a preset angle threshold.

[0030] The registration accuracy of the robotic arm is verified based on the trajectory judgment results and the distance between the light spot illuminating the target object and the actual verification point when the robotic arm moves to each end pose.

[0031] In one embodiment, the method further includes:

[0032] The display interface shows the movement trajectory of the robotic arm and its corresponding end effector pose.

[0033] Secondly, this application also provides a registration accuracy verification system for a robotic arm, which includes a verification device and a robotic arm, with an end effector tool installed at the end of the robotic arm.

[0034] The verification equipment is used to perform the steps of the registration accuracy verification method for the robotic arm described in the first aspect above.

[0035] Thirdly, this application also provides a registration accuracy verification device for a robotic arm, comprising:

[0036] The first determining module is used to determine the first location of the actual verification point on the target object from the medical image;

[0037] The second determining module is used to determine multiple end-effector poses based on the first position and the registration result of the robotic arm; when the robotic arm is in each end-effector pose, the end-effector tool of the robotic arm points to the conversion verification point; the conversion verification point is obtained by converting the first position through the registration result;

[0038] The verification module is used to control the movement of the robotic arm based on the pose of each end effector in order to verify the registration accuracy of the robotic arm.

[0039] Fourthly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the registration accuracy verification method for the robotic arm described in the first aspect.

[0040] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the registration accuracy verification method for the robotic arm described in the first aspect.

[0041] Sixthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the registration accuracy verification method for the robotic arm described in the first aspect.

[0042] The aforementioned method, system, device, computer equipment, storage medium, and computer program product for verifying the registration accuracy of a robotic arm involve a verification device that determines the first position of an actual verification point on a target object from medical images. Based on this first position and the registration result of the robotic arm, multiple end-effector poses of the robotic arm are determined. In each end-effector pose, the end-effector tool of the robotic arm points towards a converted verification point. The converted verification point is obtained by converting the first position based on the registration result. Furthermore, the movement of the robotic arm is controlled based on each end-effector pose to verify the registration accuracy of the robotic arm. In other words, this embodiment uses multiple poses under a single verification point to achieve spatial registration verification. Compared to the traditional method of using multiple verification points, each corresponding to a single pose, this not only avoids various misjudgments inherent in traditional methods, ensuring uniqueness in accuracy verification and thus improving accuracy and effectiveness, but also simplifies the operation process and increases verification efficiency. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1(a) shows the first type of misjudgment in the traditional robotic arm registration accuracy verification method in one embodiment;

[0045] Figure 1(b) illustrates a second misjudgment scenario in the traditional robotic arm registration accuracy verification method in one embodiment;

[0046] Figure 1(c) shows a third type of misjudgment in the traditional robotic arm registration accuracy verification method in one embodiment;

[0047] Figure 2 This is an application environment diagram of the registration accuracy verification method for a robotic arm in one embodiment;

[0048] Figure 3 This is a flowchart illustrating a method for verifying the registration accuracy of a robotic arm in one embodiment.

[0049] Figure 4 This is a flowchart illustrating the registration accuracy verification method for a robotic arm in another embodiment;

[0050] Figure 5(a) is a schematic diagram of multiple second positions in one embodiment;

[0051] Figure 5(b) is a schematic diagram of multiple second positions in another embodiment;

[0052] Figure 6 This is a flowchart illustrating the registration accuracy verification method for a robotic arm in another embodiment;

[0053] Figure 7 This is a flowchart illustrating the registration accuracy verification method for a robotic arm in another embodiment;

[0054] Figure 8 This is a schematic diagram of a structure in one embodiment that defines multiple second positions centered on the puncture path;

[0055] Figure 9 This is a schematic diagram showing the relationship between the offset angle and the end offset distance in one embodiment;

[0056] Figure 10 This is a flowchart illustrating the registration accuracy verification method for a robotic arm in another embodiment;

[0057] Figure 11 This is a schematic diagram of the complete process of a robotic arm registration accuracy verification method in one embodiment;

[0058] Figure 12 This is a schematic diagram of the registration accuracy verification system for a robotic arm in one embodiment;

[0059] Figure 13 This is a structural block diagram of a registration accuracy verification device for a robotic arm in one embodiment;

[0060] Figure 14 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] In the medical field, stereotactic surgery typically involves three main components: preoperative planning, spatial registration, and path execution. Spatial registration determines the transformation relationship between the stereotactic device (such as a robotic arm) and the patient's spatial position (e.g., the patient's coordinates in medical images). Path execution, based on the preoperative path planned from medical images and the transformation relationship obtained from spatial registration, moves the stereotactic device's execution channel to the designated position for subsequent surgical procedures. The accuracy of spatial registration directly impacts the success rate of the surgery. It is generally assessed by verifying whether the instrument tip reaches a verification point; however, this method is complex and insufficiently comprehensive when verifying multiple verification points.

[0063] Traditionally, after spatial registration is completed, the verification system usually provides some verification points for doctors to confirm the accuracy of the spatial registration. For example, in neurosurgery, markers or physiological features on the patient's head are usually selected as verification points. The difference between this and the actual path execution is that accuracy verification is limited to the patient's external features and cannot be equated with the actual path that will enter the patient's skull.

[0064] This verification method has the following problems. Referring to Figure 1, in Figure 1(a), the tip of the verification tool just reaches the actual verification point (which can be the actual entry point E), but the direction is incorrect, that is, it is not the same as the actual puncture direction (the puncture direction formed by the entry point E and the target point T). It still appears to meet the accuracy standard, resulting in a misjudgment. In Figure 1(b), the direction is correct, but because the verification tool moves axially, the tip of the verification tool will still contact the entry point E along the axial direction during the verification process. However, in reality, the tip of the verification tool does not just reach the entry point E. It still appears to meet the accuracy standard, resulting in a misjudgment. In Figure 1(c), the direction and position are inaccurate, but because the axis of the verification tool intersects with the entry point E, the verification process will still produce the illusion that the accuracy standard is met.

[0065] Therefore, traditional verification point-based verification methods are prone to various misjudgments, resulting in low verification accuracy. Furthermore, the process of switching between multiple verification points requires repeated needle removal and placement, which is cumbersome and inefficient.

[0066] Based on this, this application proposes a method for verifying the registration accuracy of a robotic arm. By performing multi-pose verification for a single verification point, the accuracy and effectiveness of the verification are ensured. Since the pose transformation relationship between the robotic arm coordinate system and the image coordinate system is obtained after spatial registration, and this relationship is also being verified, multiple channel poses leading to a single verification point can be calculated. This avoids the accidental phenomena mentioned above. If the accuracy verification is successful in a certain pose, and other poses also point to the verification point, the accuracy of the spatial registration can be proven.

[0067] The registration accuracy verification method for robotic arms provided in this application can be applied to, for example... Figure 2 In the application environment shown, the verification device 201 can be a computer device equipped with an imaging system, or other computer devices such as a verification terminal or verification server. For example, the verification device can be equipped with a verification system that can communicate with the robotic arm that needs to be verified. The verification system can also display the patient's medical images, and can also support users to mark verification points in the medical images, or automatically identify markers in the medical images as verification points.

[0068] In one exemplary embodiment, such as Figure 3 As shown, a method for verifying the registration accuracy of a robotic arm is provided, which is then applied to... Figure 2 The following steps, 302 to 306, are used as an example of the verification equipment in the process.

[0069] Step 302: Determine the first location of the actual verification point on the target object from the medical image.

[0070] The target object can be a phantom, or a living human or animal. When the target object is a phantom, it can be used for experimental verification or simulated operation scenarios. During registration verification, actual verification points can be determined on the target object. These actual verification points can be markers pasted or drawn on the target object, or feature points on the target object, such as facial feature points, including but not limited to points with significant characteristics such as the tip of the nose, eyeballs, lips, and eyebrows. They can also be points of markers fixed on the target object, such as the apex of a bone nail fixed to the skull of the target object. It should be noted that the bone nail used can be of any form or structure, and the apex structure of different bone nails may be different; for example, if the top of the bone nail has a groove structure, the actual verification point can be the center point of the largest cross-section of the groove at the top of the bone nail. In this embodiment, the form and position of the actual verification points on the target object are not specifically limited.

[0071] For example, if a marker exists on the target object, the medical image obtained after scanning the target object may include the marker. In this case, the verification device can identify the marker in the medical image to determine the actual verification point in the medical image corresponding to the marker on the target object, and then obtain the first position of the actual verification point from the medical image. The first position of the actual verification point can be its coordinate position in the image coordinate system of the medical image. Furthermore, in physical space, the actual verification point corresponding to the marker on the target object can serve as the end effector reference point of the robotic arm to verify the registration information of the robotic arm after it moves.

[0072] For example, the verification device can also determine the actual verification point on the target object by identifying and extracting the feature points of the target object in the medical image, thereby determining the first position of the actual verification point in the image coordinate system from the medical image.

[0073] For example, when an actual verification point is identified in a medical image, the actual verification point in the medical image can be marked to enhance the display effect of the actual verification point in the medical image.

[0074] Step 304: Based on the first position and the registration result of the robotic arm, determine multiple end-effector poses of the robotic arm; when the robotic arm is in each end-effector pose, the end-effector tool of the robotic arm points to the conversion verification point, which is obtained by converting the first position through the registration result.

[0075] The first position of the actual verification point is the coordinate position in the image coordinate system. Based on the registration result of the robotic arm, that is, the coordinate transformation relationship between the robotic arm coordinate system and the image coordinate system, after performing coordinate transformation on the first position, the transformed position corresponding to the first position in the robotic arm coordinate system can be obtained, thereby obtaining the position of the transformed verification point corresponding to the actual verification point in the physical space.

[0076] It should be noted that when the registration result of the robotic arm meets a certain accuracy requirement, the conversion verification point is the same as the actual verification point on the target object. However, when the registration accuracy of the robotic arm does not meet the accuracy requirement, the conversion verification point obtained based on the registration result is not the same as the actual verification point on the target object.

[0077] The end effector pose of the robotic arm includes end position and end pose. In other words, when the end tool of the robotic arm is in different spatial positions, the end pose of the robotic arm makes the end tool of the robotic arm point to the transformation verification point corresponding to the actual verification point calculated by the registration result.

[0078] In traditional methods, for a given actual verification point, only one end-effector pose is typically set, ensuring that the end-effector tool is within a preset range of the verification point after the robotic arm moves according to the preset end-effector pose. Preferably, for a single pose of the actual verification point, the direction vector corresponding to the puncture path formed by the actual verification point and the corresponding target point can be used as the end-effector pose of the robotic arm's end-effector tool corresponding to the preset verification point. The end-effector pose of the robotic arm is then determined based on this end-effector pose, the first position of the actual verification point, and the registration result. This ensures that after the robotic arm moves based on this end-effector pose, the tip of the end-effector tool is within the preset range of the actual verification point. In this way, if the verification registration result is accurate under this end-effector pose, the accuracy of the robotic arm during actual puncture can be ensured as much as possible.

[0079] In this embodiment, for a specific verification point on the target object, multiple end-effector poses corresponding to that verification point are set, thereby obtaining multiple end-effector poses of the robotic arm. During spatial registration verification, the robotic arm is controlled to move so that the end-effector of the robotic arm can perform multiple pose transformations around the same specific verification point on the target object. For example, the end-effector of the robotic arm is controlled to move in a circle around the specific verification point. Exemplarily, when determining the multiple end-effector poses of the robotic arm corresponding to the specific verification point, the multiple end-effector poses of the robotic arm corresponding to the specific verification point can be determined based on the first position of the specific verification point, the multiple second positions of the end-effector of the robotic arm, and the registration result of the robotic arm.

[0080] For example, the verification device can randomly determine multiple second positions around the actual verification point determined from the medical image as multiple second positions of the end effector of the robotic arm, based on the first position of the actual verification point. Here, the multiple second positions of the end effector of the robotic arm can be coordinate positions in the image coordinate system, or coordinate positions in the robotic arm coordinate system after coordinate transformation based on the registration results of the robotic arm. Furthermore, based on the multiple second positions and the first position, multiple end effector poses of the robotic arm corresponding to the actual verification point are determined.

[0081] For example, when the second position is a coordinate position in the image coordinate system, the verification device can perform coordinate transformation on the first position and each of the second positions based on the registration result of the robotic arm to obtain the third position of the actual verification point in the physical space in the robotic arm coordinate system, and multiple fourth positions of the end tool of the robotic arm in the robotic arm coordinate system; then, based on the third position and each of the fourth positions, multiple end poses of the robotic arm are determined.

[0082] For example, when the second position is the coordinate position in the image coordinate system, the verification device can first determine the multiple end poses of the robot arm in the image coordinate system based on the first position of the actual verification point and the multiple second positions of the end tool; then, based on the registration result of the robot arm, the multiple end poses are transformed to obtain the multiple end poses of the robot arm in the robot arm coordinate system.

[0083] Specifically, taking an end-effector pose as an example, the first position of the actual verification point and the second position of the end-effector tool in the image coordinate system can be transformed to obtain the third position of the actual verification point and the fourth position of the end-effector tool in the robot arm coordinate system. The fourth position of the end-effector tool can be used as the end position of the robot arm end-effector tool in physical space, and the direction vector between the fourth position and the third position can be used as the end pose of the robot arm end-effector tool. Then, an end-effector pose of the robot arm can be generated based on the end position and end pose of the robot arm end-effector tool.

[0084] Step 306: Control the movement of the robotic arm based on the pose of each end effector to verify the registration accuracy of the robotic arm.

[0085] For example, the verification device can send the multiple end-effector poses to the robotic arm to instruct the robotic arm to move sequentially according to each end-effector pose. That is, the robotic arm is controlled to move around the actual verification point on the target object. During the movement, it can be determined whether the end-effector tool of the robotic arm accurately points to the actual verification point at each end-effector pose. If the end-effector tool can accurately point to the actual verification point at each end-effector pose, or within a preset range of the actual verification point, then the spatial registration can be considered accurate, or the spatial registration accuracy is high. Conversely, if the end-effector tool fails to point to the actual verification point or within the preset range of the actual verification point at at least one end-effector pose, then the spatial registration can be considered inaccurate, or the spatial registration accuracy is low, that is, the coordinate transformation relationship between the image coordinate system and the robotic arm coordinate system is inaccurate, and spatial registration needs to be performed again.

[0086] For example, when the multiple end poses are end poses in the image coordinate system, the verification device can convert the obtained end poses in the image coordinate system into end poses in the robot arm coordinate system based on the coordinate transformation relationship obtained by spatial registration when sending each end pose to the robot arm, and then send the end poses in the robot arm coordinate system to the robot arm to control the movement of the robot arm.

[0087] For example, the verification device can also obtain the joint angle of the robotic arm corresponding to the end-effector pose through inverse kinematics calculation based on the end-effector pose in the robotic arm coordinate system, and then send the joint angle of the robotic arm corresponding to the end-effector pose to the robotic arm to control the movement of the robotic arm.

[0088] In the aforementioned method for verifying the registration accuracy of a robotic arm, the verification device determines the first position of the actual verification point on the target object from medical images, and determines multiple end-effector poses of the robotic arm based on the first position and the registration result of the robotic arm. In each end-effector pose, the end-effector tool of the robotic arm points to a converted verification point, which is obtained by converting the first position using the registration result. Then, the robotic arm is moved based on each end-effector pose to verify the registration accuracy of the robotic arm. In other words, this embodiment uses multiple poses under a single verification point to achieve spatial registration verification. Compared to the traditional method of using multiple verification points, each corresponding to a single pose, this not only avoids various misjudgments inherent in traditional methods, ensuring uniqueness in accuracy verification and thus improving accuracy and effectiveness, but also simplifies the operation process and increases verification efficiency.

[0089] In one exemplary embodiment, such as Figure 4 As shown, step 304 above may include steps 402 to 406. Wherein:

[0090] Step 402: Identify multiple secondary locations from medical images.

[0091] When the end tool is in each of the second positions, the axis of the end tool points to the conversion verification point.

[0092] For example, the verification device can randomly determine multiple second positions around the actual verification point in a medical image and obtain the position coordinates of each second position in the image coordinate system; alternatively, it can uniformly select multiple second positions around the actual verification point according to a preset path and obtain the position coordinates of each second position in the image coordinate system. The preset path can be a straight line path, a polyline path, or a curved path, etc., and the curved path can include a circular path, an elliptical path, or other curved paths. Furthermore, the preset path can also be used to characterize the movement path of the robotic arm; that is, the robotic arm can move sequentially to each second position according to the movement path, and at each second position, the axis of the end effector can point towards the verification point or the area surrounding the verification point.

[0093] It should be noted that when selecting a second position around the actual verification point, multiple second positions should be selected outside the target object around the actual verification point so that when the end effector of the robotic arm moves to each second position, its posture can point to the conversion verification point on the target object.

[0094] Step 404: Determine multiple end-effector poses of the robotic arm based on each second position, first position, and registration result.

[0095] For example, for each second position, based on the second position and the first position, a direction vector between the second position and the actual verification point can be determined. This direction vector can be used to characterize the end pose of the robotic arm at the second position; here, the end pose can be the end pose in the image coordinate system.

[0096] For example, for each second position, the second position can be taken as the end position of the end tool of the robotic arm, and combined with the end pose corresponding to the second position, the end pose of the robotic arm when the end tool is at the second position can be obtained. The end pose can be the end pose in the image coordinate system.

[0097] Next, based on the registration results of the robotic arm, the end-effector pose in the image coordinate system can be transformed to obtain multiple end-effector poses in the robotic arm coordinate system. Based on the multiple end-effector poses in the robotic arm coordinate system, the movement of the robotic arm can be controlled to verify the registration accuracy of the robotic arm.

[0098] For example, when multiple second positions are obtained, the first position and each second position can be transformed according to the registration result to obtain the third position and multiple fourth positions in the base coordinates of the robotic arm; then, each fourth position is used as the end position of the robotic arm end tool, and the direction vector between each fourth position and the third position is used as the end pose of the robotic arm end tool corresponding to each fourth position. By combining the end position and the corresponding end pose, multiple end poses of the robotic arm can be obtained.

[0099] In this embodiment, the verification device first determines multiple second positions from medical images. At each second position, the axis of the robotic arm's end effector points towards the verification conversion point. Then, based on each second position, the first position, and the registration result, multiple end effector poses of the robotic arm are determined. Using the method in this embodiment, multiple poses corresponding to a verification point can be determined, i.e., the end effector poses of the robotic arm whose end effector points towards the verification conversion point at different spatial positions can be determined. This allows for subsequent control of the robotic arm's movement based on multiple end effector poses, enabling verification of the spatial registration accuracy of the robotic arm and improving verification accuracy and efficiency.

[0100] In an exemplary embodiment, the multiple second positions can be multiple positions on the same straight line or the same plane, or multiple positions on the same curve or the same curved surface; for example, the end effector of the robotic arm can move along a straight line, and during the movement, the axis direction of the end effector of the robotic arm always points to the conversion verification point on the target object corresponding to the actual verification point.

[0101] For example, the multiple second positions can be multiple positions that rotate around a preset puncture path passing through the actual verification point. The preset puncture path can be a puncture path passing through both the actual verification point and the target point, or it can be a puncture path passing through the first position of the actual verification point and perpendicular to the tangent plane at the first position on the target object. It should be noted that this perpendicularity can be perfectly perpendicular or approximately perpendicular; that is, the angle between the preset puncture path and the axis passing through the first position and perfectly perpendicular to the tangent plane at the first position can be less than or equal to a preset angle threshold.

[0102] In one optional implementation, the multiple second positions can be multiple positions during circular motion around a preset puncture path. That is, the angle between the line connecting each second position and the first position and the preset puncture path in the medical image is a preset angle. In this case, the distance between each second position and the first position can be the same, such as multiple positions being different positions on the bottom circle of a cone with the first position as the vertex at a preset angle, as shown in Figure 5(a), where the black dots on the bottom circle of the cone represent multiple second positions. Of course, the distance between each second position and the first position can also be different, such as multiple positions being different positions on the elliptical circumference of the oblique section of a cone with the first position as the vertex at a preset angle, as shown in Figure 5(b), where the black dots on the elliptical circumference of the oblique section of the cone represent multiple second positions.

[0103] In both cases, the angle between the line connecting each second position and the first position and the preset puncture path (the central axis of the cone) is a preset angle α.

[0104] In one exemplary embodiment, such as Figure 6 As shown, step 402 above may include steps 602 to 604. Wherein:

[0105] Step 602: Determine the preset puncture path passing through the first position from the medical images.

[0106] The preset puncture path can be a puncture path that passes through the first position of the actual verification point and the position of the preset target point, or it can be a puncture path that passes through the first position of the actual verification point and is perpendicular to the tangent plane at the first position on the target object.

[0107] The preset target point can be the lesion point when actually punctured with a puncture needle. During puncture, the puncture needle can reach the lesion point in the tissue by passing through the actual verification point. In this example, the puncture path of the puncture needle can be used as the puncture path during registration verification. For example, in medical images, the actual verification point and the preset target point on the target object can be marked. Then, based on the first position of the actual verification point and the position of the preset target point, the puncture path, that is, the line segment passing through the actual verification point and the preset target point, can be determined.

[0108] For example, when the first position of the actual verification point on the medical image is determined, a cutting plane that passes through the first position and is tangent to the surface of the target object can also be determined, and then the axis that passes through the first position and is perpendicular to the cutting plane can be determined as the preset puncture path.

[0109] Step 604: Determine multiple second positions around the preset puncture path according to the preset angle.

[0110] The angle between the line connecting each second position and the first position and the preset puncture path is a preset angle.

[0111] For example, when a preset puncture path is determined, multiple second positions can be determined around the preset puncture path as the central axis. That is, the multiple second positions can be multiple positions that rotate around the preset puncture path by a preset angle.

[0112] For example, based on the preset puncture path, preset angle, and first position, a cone with the first position as its vertex, the preset puncture path as its central axis, and the cone deflection angle as its preset angle can be determined. Then, multiple second positions that rotate around the preset puncture path are determined on the surface of the cone. For example, any position on the surface of the cone can be used as the second position, or a position on the bottom circumference of the cone can be used as the second position, or a position on the circumference of a cross section of the cone parallel to the bottom can be used as the second position, or a position on the circumference of a cross section of the cone at a certain angle to the bottom can be used as the second position, etc.

[0113] In this embodiment, the verification device can first determine a preset puncture path passing through a first position from medical images; then, based on a preset angle, determine multiple second positions around the preset puncture path; wherein, the angle between the line connecting each second position and the first position and the preset puncture path is a preset angle. In other words, in this embodiment, by determining multiple second positions around the preset puncture path, the robotic arm can rotate and move around the preset puncture path, and during this rotation, the end effector of the robotic arm always points towards the verification point. Using this method, circular movement verification can be performed based on the preset puncture path, and multiple postures at a single verification point can ensure the accuracy of registration accuracy verification. Furthermore, when the preset puncture path is perpendicular to the target object surface, during the circular verification process, it also helps the user to more intuitively grasp whether there is a deviation in the movement trajectory of the robotic arm's end effector, further improving the accuracy of registration accuracy verification.

[0114] In one exemplary embodiment, such as Figure 7 As shown, step 604 above may further include steps 702 to 706. Wherein:

[0115] Step 702: Determine the sphere centered on the actual verification point based on the first position and the preset sphere radius.

[0116] The preset sphere radius can be set by the user or it can be a default value for verification. In this embodiment, the size of the preset sphere radius is not specifically limited.

[0117] In this embodiment, a sphere can be determined first based on a preset sphere radius and with the actual verification point as the center; alternatively, the equation of the sphere with the actual verification point as the center can be determined based on mathematical principles. (See reference) Figure 8 As shown, the center point of the sphere is the actual verification point, and the preset sphere radius is R.

[0118] Step 704: Determine the target cross section passing through the preset puncture path according to the preset angle, and determine the arc where the target cross section intersects the sphere.

[0119] Continue to refer to Figure 8 As shown, the preset puncture path can be... Figure 8 The straight line containing the z-axis. Using the preset puncture path as the central axis, the angle between the preset puncture path and the preset angle can be determined as the preset angle. Figure 8 In The cone and the intersection of the cone and the sphere are the target sections that pass through the preset puncture path; here, the target section where the cone and the sphere intersect are perpendicular to the preset puncture path; once the target section is determined, the arc where the target section intersects with the sphere can be further determined.

[0120] It should be noted that, Figure 8 The z-axis can point to the outside of the target object, while the opposite direction of the z-axis can point to the inside of the target object. When determining the second position, a cross section passing through the preset puncture path should be determined on one side of the positive half-axis of the z-axis, that is, multiple end positions of the robotic arm should be determined on the sphere where the positive half-axis of the z-axis is located.

[0121] For example, when determining the target cross-section, the actual verification point can be used as the vertex, the preset puncture path as the central axis, and the cone equation can be determined according to a preset angle. Then, based on the cone equation and the sphere equation, the cross-sectional equation at the intersection of the cone and the sphere is determined, and the target cross-section perpendicular to the preset puncture path is determined based on the cross-sectional equation. Optionally, the verification device can also directly determine the arc at the intersection of the cone and the sphere based on the cone equation and the sphere equation.

[0122] For example, when determining the target cross-section, a target point on the preset puncture path can be determined based on a preset angle and a preset sphere radius; then, the plane passing through the target point and perpendicular to the preset puncture path is taken as the target cross-section; wherein, the target point is also the center point of the arc, determined based on the preset sphere radius R and the preset angle. The distance between the center point of the arc and the actual verification point can be determined, thereby identifying the target point at that distance from the actual verification point. Figure 8 Points on the positive z-axis (preset puncture path).

[0123] Step 706: Determine multiple points on the arc as multiple second positions around the preset puncture path.

[0124] For example, multiple points can be uniformly determined on the arc according to a preset step size as multiple second positions of the robotic arm end effector. In addition, the arc can serve as the movement path of the robotic arm end effector, that is, the movement trajectory of the robotic arm end effector; for example, any second position on the arc can be used as the starting position of the robotic arm end effector, and it can move sequentially to the next second position along the preset direction of the arc (clockwise or counterclockwise), thereby realizing the rotational movement of the robotic arm end effector around the preset puncture path.

[0125] In this embodiment, when determining multiple second positions of the robotic arm end effector that rotates around the puncture path based on the puncture path and a preset angle, a sphere centered on the actual verification point can be first determined based on the first position and a preset sphere radius. Then, a target cross-section passing through the preset puncture path is determined based on the preset angle, and the arc intersecting the target cross-section with the sphere is determined. Subsequently, multiple points on the arc are determined as multiple second positions around the preset puncture path. Using this method, the second positions can be quickly determined, improving verification efficiency.

[0126] In one exemplary embodiment, the end effector of the robotic arm can be a light source, including but not limited to a collimated beam emitter such as a laser. The light emission direction of this light source is the axial direction of the end effector of the robotic arm. When the robotic arm is in each end effector pose, the light emission direction of the light source points towards the conversion verification point. In other words, by replacing the traditional puncture needle used for verification with a light source, the light emitted by the light source points towards the conversion verification point, avoiding the adverse effects on the patient caused by the puncture needle, and also solving the tedious work of frequently disassembling and assembling the puncture needle.

[0127] For example, when the robotic arm performs a circular motion at its end effector to verify registration accuracy, the light source can continuously emit light during the movement of the robotic arm. That is, the light source emits light when the end effector moves to each second position, and it continues to emit light as it moves from the current second position to the next second position. Of course, the light source can also emit light when the robotic arm moves to each end effector pose, that is, it does not emit light while moving from one end effector pose to another. In this case, it is necessary to determine whether to control the light source to emit light based on the current pose of the robotic arm. For example, if the current pose of the robotic arm is consistent with the end effector pose corresponding to the desired second position, the light source is controlled to emit light; if the current pose of the robotic arm is inconsistent with the end effector pose corresponding to the desired second position, including during the period from the current second position to the next second position, the light source is controlled not to emit light.

[0128] In an exemplary embodiment, step 306 may include: controlling the robotic arm to move sequentially based on each end pose, and verifying the registration accuracy of the robotic arm based on the distance between the light spot illuminating the target object and the actual verification point when the robotic arm moves to each end pose.

[0129] For example, when the robotic arm moves to each end pose, if the distance between the light spot illuminating the target object and the actual verification point is less than a preset distance threshold under that end pose, it can be said that the converted verification point after the registration result is converted is approximately the same verification point as the actual verification point on the target object. In other words, the conversion of the end pose based on the registration result is accurate, which means that the accuracy of the registration result is high under that end pose.

[0130] For example, the verification device can determine that the registration accuracy of the robotic arm meets the registration accuracy requirements if the distance between the light spot corresponding to each of the end poses and the actual verification point is less than a preset distance threshold.

[0131] For example, the verification device can also determine that the registration accuracy of the robotic arm meets the registration accuracy requirements when the number of end poses whose distance between the light spot corresponding to the end pose and the actual verification point is less than a preset distance threshold is greater than a preset number threshold, or when the proportion of end poses whose distance is less than a preset distance threshold is greater than a preset proportion threshold.

[0132] For example, if, in a certain end pose, the distance between the light spot illuminating the target object and the actual verification point is greater than or equal to a preset distance threshold, it can be said that, for that end pose, the converted verification point after registration result conversion and the actual verification point on the target object are not the same verification point, and the distance between the converted verification point and the actual verification point is relatively large. In order to further quantitatively determine the distance between the converted verification point and the actual verification point, for example, the preset angle can be set to 45°. Based on this, in that end pose, the distance between the light spot and the actual verification point can be approximately equal to the distance between the converted verification point and the actual verification point.

[0133] refer to Figure 9 As shown, when the robotic arm moves to a certain end-effector pose, the end-effector (such as a puncture needle or light source) does not point precisely to the actual verification point E, but rather to a position next to the actual verification point E, such as the position of the light spot E'. At this time, there is a certain distance deviation err between the tip of the end-effector (i.e., the conversion verification point) and the actual verification point E. Since the end-effector moves up and down along the axis of the robotic arm end during actual verification, the user cannot quantitatively determine the magnitude of the distance deviation. Therefore, this embodiment proposes to determine the distance deviation based on the distance err' between the actual verification point E and the light spot E' and a preset angle. The distance deviation err between the tip of the end tool (i.e., the conversion verification point) and the actual verification point E is quantitatively determined by using trigonometric function relationships.

[0134] For example, when the preset angle is 45°, it can be approximately assumed that the distance err' between the actual verification point E and the light spot E' is equal to the distance deviation err between the tip of the end tool (i.e., the conversion verification point) and the actual verification point E. Once the distance err' between the actual verification point E and the light spot E' is determined, the distance deviation err between the tip of the end tool (i.e., the conversion verification point) and the actual verification point E can be directly determined; thus, the deviation between the end of the end tool and the actual verification point can be determined quickly and quantitatively.

[0135] The method in this embodiment allows users to semi-quantitatively determine the deviation distance. The deviation distance is the distance between the actual tool tip (i.e., the conversion verification point) and the actual verification point (such as the actual cranial entry point). It can be seen that when the angle is 45°, if there is a displacement deviation err, this deviation can be visually reflected in the user-observable plane direction, i.e., err', and the magnitudes are equal (ignoring minor deviations in the curved surface). In other words, the method in this embodiment can solve the problem of unverifiable distances encountered in Figures 1(b) and 1(c).

[0136] It should be noted that when the preset angle is not 45°, it is also possible to use the principle of trigonometric functions, based on the distance err' between the actual verification point E and the light spot E' and the preset angle. The distance deviation err between the tip of the end effector (i.e., the conversion verification point) and the actual verification point E is calculated. For example, the preset angle can also be 30 degrees, 60 degrees, etc. The distance deviation err between the tip of the end effector (i.e., the conversion verification point) and the actual verification point E is equal to the quotient between the distance err' between the actual verification point E and the light spot E' and the tangent of the preset angle. ;exist At 45°, ,therefore, ;exist When = 30°, ,therefore, ;exist When = 60°, ,therefore, .

[0137] Therefore, compared to the preset angle of 45°, the process of determining the distance deviation is relatively more complicated at other preset angles; while the preset angle of 45° can approximate the distance err' between the actual verification point E and the light spot E' as the distance deviation err between the converted verification point and the actual verification point E, making the determination of the distance deviation more efficient and faster.

[0138] In one exemplary embodiment, such as Figure 10 As shown, the above method may further include:

[0139] Step 1002: Determine whether the movement trajectory of the robotic arm meets the preset trajectory requirements, and obtain the trajectory judgment result.

[0140] The preset trajectory requires that the offset angle between the central axis of the robotic arm's movement trajectory and the preset puncture path of the robotic arm be less than a preset angle threshold.

[0141] If the registration accuracy of the robotic arm is low, meaning the registration result is inaccurate, then the actual puncture path, after being converted from the preset puncture path determined from the medical images based on the registration result, will also deviate from the preset puncture path. Therefore, during the robotic arm's rotational movement around the preset puncture path, the actual robotic arm will not rotate or move around the preset puncture path as its center. In this case, the user can verify the registration accuracy of the robotic arm by judging whether its movement trajectory is centered on the preset puncture path.

[0142] For example, before the robotic arm performs its circular motion, it can be controlled to move to the end pose corresponding to the preset puncture path, and the offset angle between the light emission direction of the light source and the preset puncture path can be determined in this end pose. If the offset angle is less than a preset angle threshold, it can be determined that the movement trajectory of the robotic arm meets the preset trajectory requirements; if the offset angle is greater than or equal to the preset angle threshold, it can be determined that the movement trajectory of the robotic arm does not meet the preset trajectory requirements.

[0143] Step 1004: Verify the registration accuracy of the robotic arm based on the trajectory judgment results and the distance between the light spot illuminating the target object and the actual verification point when the robotic arm moves to each end pose.

[0144] For example, the verification device can also combine the trajectory judgment result of the robotic arm with the distance between the light spot of the light source illuminating the target object and the actual verification point when the robotic arm moves to each end pose to comprehensively verify the registration accuracy of the robotic arm. The method in this example can accurately verify the misjudgment situation shown in Figure 1(a); when the converted verification point and the actual verification point are the same verification point, the accuracy is verified by using the offset angle between the actual central axis around which the robotic arm rotates in a circle and the preset central axis.

[0145] In this embodiment, the trajectory judgment result is obtained by determining whether the movement trajectory of the robotic arm meets the preset trajectory requirements. Then, based on the trajectory judgment result and the distance between the light spot illuminating the target object when the robotic arm moves to each end pose and the actual verification point, the registration accuracy of the robotic arm is verified. This method can accurately verify different misjudgment situations, comprehensively improving the accuracy of accuracy verification.

[0146] In an exemplary embodiment, when verifying the registration accuracy of a robotic arm, in order to more accurately grasp the movement of the robotic arm, the verification device can also display the movement of the robotic arm in real time on the display interface. For example, the verification device can display the movement trajectory of the robotic arm and the corresponding end-effector pose on the display interface.

[0147] In other words, when the robotic arm moves to each end pose, that is, when the end of the robotic arm moves to each second position, the verification device can display or mark the end pose corresponding to the current second position on the display device; at the same time, it can also display the complete movement trajectory of the robotic arm in real time.

[0148] Using this method, users can better understand the movement status and situation of the robotic arm by combining the content displayed on the interface, and more intuitively understand which second position the current end effector pose corresponds to. This is beneficial for users to perform accuracy verification operations and accurately record abnormal positions, so as to facilitate users to re-register the robotic arm based on abnormal positions, thereby improving registration accuracy and precision.

[0149] In one exemplary embodiment, such as Figure 11 As shown, a complete workflow for verifying the spatial registration of a robotic arm is provided. It includes the following steps:

[0150] Step 1: Obtain the first position of the actual verification point, the preset puncture path of the target object, and the radius of the sphere, and construct the spherical equation.

[0151] The first position of the actual verification point and the preset puncture path can both be coordinate positions in the image coordinate system.

[0152] Step 2: Determine the preset angle, and construct the arc equation of the cross section intersecting the sphere with the actual verification point as the vertex and the preset puncture path as the central axis.

[0153] Step 3: Select multiple points evenly on the arc as the second position of the end effector of the robotic arm. Based on each second position and the first position, determine multiple end effector poses of the robotic arm.

[0154] Here, the multiple end-effector poses of the robotic arm can be end-effector poses in the robotic arm coordinate system; alternatively, multiple initial end-effector poses in the image coordinate system can be determined first based on the first position and each of the second positions in the image coordinate system; then, based on the registration results of the robotic arm, the multiple initial end-effector poses are converted into end-effector poses in the robotic arm coordinate system.

[0155] Alternatively, based on the registration results of the robotic arm, the first position and each of the second positions in the image coordinate system can be transformed to obtain the third position of the actual verification point in the robotic arm coordinate system and each of the second positions in the robotic arm coordinate system as the fourth position; then, based on the third position and each of the fourth positions in the robotic arm coordinate system, the multiple end poses of the robotic arm in the robotic arm coordinate system can be determined.

[0156] Step 4: Using each end-effector pose as input, inverse kinematics is called to obtain the joint angles of the robotic arm in each end-effector pose.

[0157] Step 5: Plan the motion trajectory of the robotic arm based on each of the second positions of the robotic arm.

[0158] Step 6: Control the movement of the robotic arm based on the motion trajectory and the joint angles at each end pose to verify the registration accuracy.

[0159] Using the above-mentioned registration accuracy verification method for robotic arms, it is only necessary to keep the robotic arm running continuously and then observe whether the light source always points to the actual verification point on the target object to determine the accuracy of the registration result, without having to repeatedly disassemble and reassemble the end effector. Furthermore, by using a semi-quantitative method, it is also possible to determine the deviation between the end effector and the actual verification point in the corresponding end effector pose when the light source does not point accurately to the actual verification point, thereby determining the execution accuracy of the robotic arm.

[0160] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed 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 performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0161] In one exemplary embodiment, this application also provides a registration accuracy verification system for a robotic arm, such as... Figure 12 As shown, the registration accuracy verification system for the robotic arm includes a verification device 201 and a robotic arm 202, with an end-effector tool installed at the end of the robotic arm 202; the verification device 201 is used to perform the steps of the registration accuracy verification method for the robotic arm in any of the above embodiments.

[0162] For example, the end effector of the robotic arm 202 can also be a light source, which may include, but is not limited to, a collimated beam emission source, such as a laser light. When performing registration verification, using a light source instead of a puncture needle can, on the one hand, avoid frequent disassembly of the puncture needle, reduce human operation, and improve the efficiency of registration verification; on the other hand, it can also avoid the damage that the puncture needle may cause to the target object and improve the safety of registration verification.

[0163] When using this verification system for robotic arm registration verification, spatial registration verification is achieved by setting multiple postures under a single verification point. Compared to the traditional method of using multiple verification points, each corresponding to a single posture, this not only avoids various misjudgments inherent in traditional methods, ensuring uniqueness in accuracy verification and thus improving accuracy and effectiveness, but also simplifies the operation process and increases verification efficiency. Furthermore, by using the robotic arm to rotate around a single verification point for verification, semi-quantitative assessment of the robotic arm's execution accuracy under different end-effector postures can be achieved during the verification process, further enhancing the accuracy and comprehensiveness of registration verification.

[0164] Based on the same inventive concept, this application also provides a robotic arm registration accuracy verification device for implementing the above-described robotic arm registration accuracy verification method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more robotic arm registration accuracy verification device embodiments provided below can be found in the limitations of the robotic arm registration accuracy verification method described above, and will not be repeated here.

[0165] In one exemplary embodiment, such as Figure 13 As shown, a registration accuracy verification device for a robotic arm is provided, comprising: a first determining module 1302, a second determining module 1304, and a verification module 1306, wherein:

[0166] The first determining module 1302 is used to determine the first position of the actual verification point on the target object from the medical image.

[0167] The second determining module 1304 is used to determine multiple end poses of the robotic arm based on the first position and the registration result of the robotic arm; when the robotic arm is in each end pose, the end tool of the robotic arm points to the conversion verification point, which is obtained by converting the first position through the registration result.

[0168] The verification module 1306 is used to control the movement of the robotic arm based on the pose of each end effector in order to verify the registration accuracy of the robotic arm.

[0169] In one embodiment, the second determining module 1304 includes:

[0170] The first determination submodule is used to determine multiple second locations from medical images;

[0171] The first determination submodule is used to determine multiple end poses of the robotic arm based on each second position, the first position, and the registration result.

[0172] In one embodiment, the angle between the line connecting each second position and the first position and the preset puncture path in the medical image is a preset angle; the preset puncture path passes through the first position.

[0173] In one embodiment, the preset puncture path is perpendicular to the tangent plane at a first position on the target object.

[0174] In one embodiment, the first determining submodule includes:

[0175] The first determining unit is used to determine the preset puncture path passing through the first position from the medical image;

[0176] The second determining unit is used to determine multiple second positions around the preset puncture path according to a preset angle; the angle between the line connecting each second position and the first position and the preset puncture path is a preset angle.

[0177] In one embodiment, the second determining unit is specifically used to determine a sphere centered on the actual verification point based on the first position and the preset sphere radius; determine a target cross section passing through the preset puncture path based on the preset angle, and determine the arc where the target cross section intersects the sphere; and determine multiple points on the arc as multiple second positions around the preset puncture path.

[0178] In one embodiment, the second determining unit is specifically used to determine the target point on the preset puncture path according to the preset angle and the preset sphere radius; and to take the plane that passes through the target point and is perpendicular to the preset puncture path as the target cross section.

[0179] In one embodiment, the preset angle is 45°.

[0180] In one embodiment, the end effector is a light source; when the robotic arm is in each end effector pose, the light emission direction of the light source is always pointing towards the conversion verification point.

[0181] In one embodiment, the light source emits light continuously during the movement of the robotic arm; or, the light source emits light when the robotic arm moves to each end-effector pose.

[0182] In one embodiment, the verification module 1306 is used to control the movement of the robotic arm sequentially based on each end pose, and to verify the registration accuracy of the robotic arm based on the distance between the light spot of the light source on the target object and the actual verification point when the robotic arm moves to each end pose.

[0183] In one embodiment, the device further includes: a judgment module, used to judge whether the movement trajectory of the robotic arm meets the preset trajectory requirements, and obtain a trajectory judgment result; the preset trajectory requirements include that the offset angle between the central axis of the movement trajectory of the robotic arm and the preset puncture path of the robotic arm is less than a preset angle threshold; and a verification module 1306, used to verify the registration accuracy of the robotic arm based on the trajectory judgment result and the distance between the light spot of the light source illuminating the target object and the actual verification point when the robotic arm moves to each end pose.

[0184] In one embodiment, the device further includes a display module for displaying the movement trajectory of the robotic arm and the corresponding end-effector pose on a display interface.

[0185] Each module in the aforementioned robotic arm registration accuracy verification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0186] In one exemplary embodiment, a computer device is provided, which may be a verification device. When the verification device is a terminal, its internal structure diagram may be as follows: Figure 14 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for verifying the registration accuracy of a robotic arm. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0187] Those skilled in the art will understand that Figure 14 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0188] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the registration accuracy verification method for the robotic arm in any of the above embodiments.

[0189] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the registration accuracy verification method for the robotic arm in any of the above embodiments.

[0190] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the registration accuracy verification method for the robotic arm in any of the above embodiments.

[0191] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0192] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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, they should be considered to be within the scope of this specification.

[0193] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A registration accuracy verification method of a robot arm, characterized by, The method comprises: determining a first position of an actual verification point on a target object from a medical image; determining a plurality of end poses of the mechanical arm according to the first position and a registration result of the mechanical arm; when the mechanical arm is in each of the end poses, an end tool of the mechanical arm points to a converted verification point, the converted verification point being obtained by converting the first position through the registration result; controlling the mechanical arm to move based on each of the end poses to verify registration accuracy of the mechanical arm.

2. The method of claim 1, wherein, The method further comprises: determining a plurality of second positions from the medical image; determining a plurality of end poses of the mechanical arm according to each of the second positions, the first position and the registration result.

3. The method of claim 2, wherein, The angle between the line connecting each of the second positions and the first position and the preset puncture path of the target object in the medical image is a preset angle; the preset puncture path passes through the first position.

4. The method of claim 3, wherein, The preset puncture path is perpendicular to a tangent plane at the first position on the target object.

5. The method of claim 3, wherein, The preset angle is 45°.

6. The method of claim 1, wherein, The end tool is a light source; when the mechanical arm is in each of the end poses, the light source points to the converted verification point.

7. The method of claim 6, wherein, The light source continuously emits light during the movement of the mechanical arm; or the light source emits light when the mechanical arm moves to each of the end poses.

8. The method of claim 6, wherein, The method further comprises: controlling the mechanical arm to move based on each of the end poses to verify registration accuracy of the mechanical arm according to the distance between the light spot on the target object irradiated by the light source when the mechanical arm moves to each of the end poses and the actual verification point.

9. The method of claim 8, wherein, The method further comprises: judging whether a movement trajectory of the mechanical arm meets a preset trajectory requirement to obtain a trajectory judgment result; the preset trajectory requirement comprises that the offset angle between the central axis of the movement trajectory of the mechanical arm and the preset puncture path of the target object is less than a preset angle threshold; verifying registration accuracy of the mechanical arm according to the trajectory judgment result and the distance between the light spot on the target object irradiated by the light source when the mechanical arm moves to each of the end poses and the actual verification point.

10. A registration accuracy verification system for a robotic arm, characterized in that, The system comprises a verification device and a mechanical arm, and an end tool is installed at an end of the mechanical arm; The verification device is configured to perform the steps of the method for verifying registration accuracy of the mechanical arm according to any one of claims 1 to 9.

11. A registration accuracy verification device for a robot arm, characterized by The device comprises: a first determination module configured to determine a first position of an actual verification point on a target object from a medical image; a second determination module configured to determine a plurality of end poses of the mechanical arm according to the first position and a registration result of the mechanical arm; when the mechanical arm is in each of the end poses, an end tool of the mechanical arm points to a converted verification point; the converted verification point being obtained by converting the first position through the registration result. A verification module is configured to control the robot arm to move based on the end pose to verify the registration accuracy of the robot arm.

12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1-9.

13. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1-9.

Images