Obstacle avoidance model generation method, obstacle avoidance method, obstacle avoidance system, device and equipment

Abstract

The invention relates to an obstacle avoidance model generation method, an obstacle avoidance method, an obstacle avoidance system, an obstacle avoidance device and equipment, and the obstacle avoidance model generation method comprises the steps: obtaining a medical image of a region of interest of an object to be subjected to obstacle avoidance when a bed body carrying the object to be subjected to obstacle avoidance moves to a preset position; controlling the bed body to move from a preset position to different target positions, and controlling the shooting equipment to shoot a plurality of initial images corresponding to the preset position and each target position of the object to be subjected to obstacle avoidance; and generating an obstacle avoidance model according to the medical image and the plurality of initial images. The efficiency of generating the obstacle avoidance model by using the obstacle avoidance model generation method provided by the invention is high.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to an obstacle avoidance model generation method, an obstacle avoidance method, an obstacle avoidance system, a device and equipment. Background Art

[0002] With the development of robotics, surgical robot systems with robotic arms have emerged. Using surgical robot systems, the robotic arm can be moved to a specified position according to a preset path during surgical preparation to perform surgery. The preset path is planned based on a model of obstacles that need to be avoided when the robotic arm moves to the specified position.

[0003] In conventional technology, a medical image of an obstacle is usually acquired using a computer tomography (CT) scanning device, and a model reconstructed from the medical image is used as the model of the obstacle.

[0004] However, the method of obtaining obstacle models using traditional techniques is inefficient. Summary of the invention

[0005] Based on this, it is necessary to provide an obstacle avoidance model generation method, obstacle avoidance method, obstacle avoidance system, device and equipment that can improve the efficiency of generating obstacle avoidance models in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for generating an obstacle avoidance model, the method comprising:

[0007] When the bed carrying the object to be avoided moves to a preset position, a medical image of a region of interest of the object to be avoided is obtained;

[0008] Controlling the bed to move from a preset position to different target positions, and controlling the photographing device to photograph a plurality of initial images corresponding to the obstacle avoidance object at the preset position and each target position;

[0009] An obstacle avoidance model is generated based on the medical image and multiple initial images.

[0010] In one embodiment, generating an obstacle avoidance model based on a medical image and a plurality of initial images includes:

[0011] constructing a first model of a region of interest based on the medical image;

[0012] The multiple initial images are stitched together to obtain a second model of the object to be avoided;

[0013] An obstacle avoidance model is generated based on the first model and the second model.

[0014] In one embodiment, generating an obstacle avoidance model according to the first model and the second model includes:

[0015] Crop the area corresponding to the first model in the second model to obtain a cropped second model;

[0016] The cropped second model is spliced ​​with the first model to obtain an obstacle avoidance model.

[0017] In a second aspect, the present application also provides an obstacle avoidance method, the method comprising:

[0018] The planned path of the needle path corresponding to the surgical robot sent by the receiving workstation is generated by the workstation according to the obstacle avoidance model;

[0019] Determine whether the planned path of the needle track meets the preset requirements. If the planned path of the needle track does not meet the preset requirements, receive a new planned path and determine whether the new planned path meets the preset requirements until the planned path of the needle track meets the preset requirements.

[0020] In one embodiment, determining whether the planned path of the needle track meets preset requirements includes:

[0021] Move to the target needle track position according to the planned path of the needle track, and do not contact the first obstacle during the movement, then determine that the planned path of the needle track meets the preset requirements;

[0022] If the needle contacts the first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0023] In one embodiment, when there is no contact with the first obstacle during the moving process, the method further includes:

[0024] In the case where a second obstacle is stored at the target needle track position, the needle track is moved to the next target needle track position according to the planned path of the next target needle track, and if the needle track does not contact the second obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements;

[0025] If the needle contacts the second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0026] In one embodiment, when it is determined that the planned path of the needle track does not meet the preset requirements, the method further includes:

[0027] A prompt message is returned to the workstation to instruct the workstation to adjust the planned path of the needle track according to the obstacle avoidance model, and the adjusted planned path of the needle track is sent to the surgical robot.

[0028] In a third aspect, the present application provides an obstacle avoidance system, which includes a workstation and a surgical robot, and the workstation is communicatively connected to the surgical robot; the workstation is used to execute the steps of the obstacle avoidance model generation method provided in the first aspect above, and the surgical robot is used to execute the steps of the obstacle avoidance method provided in the second aspect above.

[0029] In a fourth aspect, the present application provides an obstacle avoidance model generating device, the device comprising:

[0030] An acquisition module, used for acquiring a medical image of a region of interest of the object to be avoided when the bed carrying the object to be avoided moves to a preset position;

[0031] A control module, used to control the bed to move from a preset position to different target positions, and control the shooting device to shoot a plurality of initial images corresponding to the obstacle avoidance object at the preset position and each target position;

[0032] The generation module is used to generate an obstacle avoidance model according to the medical image and multiple initial images.

[0033] In a fifth aspect, the present application provides an obstacle avoidance device, the device comprising:

[0034] A receiving module is used to receive the planned path of the needle path corresponding to the surgical robot sent by the workstation; the planned path is generated by the workstation according to the obstacle avoidance model;

[0035] The determination module is used to determine whether the planned path of the needle track meets the preset requirements. If the planned path of the needle track does not meet the preset requirements, a new planned path is received and it is determined whether the new planned path meets the preset requirements until the planned path of the needle track meets the preset requirements.

[0036] In a sixth aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the first and second aspects above are implemented.

[0037] In a seventh aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the methods provided in the first and second aspects above.

[0038] In an eighth aspect, the present application further provides a computer program product, including a computer program, which implements the steps of the methods provided in the first and second aspects above when the computer program is executed by a processor.

[0039] The above obstacle avoidance model generation method, obstacle avoidance method, obstacle avoidance system, device and equipment obtain a medical image of the area of ​​interest of the object to be avoided when the bed carrying the object to be avoided moves to a preset position; control the bed to move from the preset position to different target positions, and control the shooting device to shoot multiple initial images of the object to be avoided at the preset position and corresponding to each target position; generate an obstacle avoidance model based on the medical image and the multiple initial images. In this embodiment, the obstacle avoidance model generated by combining the medical image and the multiple initial images is more efficient, and the medical image of the area of ​​interest of the object to be avoided is obtained by the medical imaging device, which can avoid the object to be avoided from receiving a large dose of radiation, improve safety, and ensure the accuracy of the area of ​​interest of the object to be avoided, so that the generated obstacle avoidance model meets the surgical requirements; the multiple initial images of the object to be avoided are obtained by the shooting device, which can improve the generation efficiency of the obstacle avoidance model. In addition, in the present embodiment, when the bed moves to the preset position, a medical image is acquired, and when the bed moves out of the preset position (i.e., moves from the preset position to different target positions), multiple initial images are acquired. In this way, in the process of completing a scanning process using a medical imaging device, both a medical image and multiple initial images can be acquired, thereby reducing the complexity of the process of generating an obstacle avoidance model and improving the efficiency and accuracy of generating the obstacle avoidance model. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of the structure of an obstacle avoidance model generating device in one embodiment;

[0041] Figure 2 A schematic diagram of a step flow of a method for generating an obstacle avoidance model in one embodiment;

[0042] Figure 3 is a schematic diagram of the movement direction of the bed in one embodiment;

[0043] Figure 4 A schematic flow chart of the steps of a method for generating an obstacle avoidance model in another embodiment;

[0044] Figure 5 A schematic flow chart of the steps of a method for generating an obstacle avoidance model in another embodiment;

[0045] Figure 6 A schematic flowchart of the steps of an obstacle avoidance method in another embodiment;

[0046] Figure 7 A schematic flowchart of the steps of an obstacle avoidance method in another embodiment;

[0047] Figure 8 A schematic flowchart of the steps of an obstacle avoidance method in another embodiment;

[0048] Fig. 9 A schematic diagram of a needle channel sorting rule in one embodiment;

[0049] Fig.10 A schematic diagram of a needle channel sorting rule in another embodiment;

[0050] Fig.11 A schematic flow chart of the steps of a method for generating an obstacle avoidance model in another embodiment;

[0051] Fig.12 A schematic flowchart of the steps of an obstacle avoidance method in another embodiment;

[0052] Fig.13 is a schematic structural diagram of an obstacle avoidance system in one embodiment;

[0053] Fig.14 is a schematic structural diagram of an obstacle avoidance model generating device in one embodiment;

[0054] Fig.15 is a schematic structural diagram of an obstacle avoidance device in one embodiment;

[0055] Fig.16 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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.

[0057] The serial numbers assigned to the components in this article, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0058] Before specifically introducing the technical solution of the embodiment of the present application, the technical background and technical evolution context on which the embodiment of the present application is based are first introduced. In the medical field, with the development of robotics technology, surgical technical systems with robotic arms have emerged. Using a surgical robot system, the robotic arm can be moved to a designated position according to a preset path to perform surgery during surgical preparation. Among them, the preset path is planned based on a model of obstacles that need to be avoided during the movement of the robotic arm to the designated position. In traditional technology, a structured light camera is usually used to scan the human body, the scanning results are modeled and a corresponding human body model is generated. The generated human body model is used to plan the needle path before surgery, and the feasibility of the needle path is verified. When using a surgical robot, the model can be applied to the robotic arm to avoid obstacles. However, the accuracy of the human body model obtained using a structured light camera does not meet the requirements of the surgery. In this regard, the traditional technology proposes to obtain a medical image of the obstacle according to a computer tomography (CT) scanning device, and the model reconstructed according to the medical image is used as the model of the obstacle. However, the efficiency of generating a model in this way is low. In this regard, the present application provides a method for generating an obstacle avoidance model.

[0059] The following is an introduction to the technical solutions involved in the embodiments of the present application in combination with the scenarios in which the embodiments of the present application are applied.

[0060] The obstacle avoidance model provided in the present application can be applied to an obstacle avoidance model generating device. The structure of the obstacle avoidance model generating device 10 is as follows: Figure 1 As shown, it includes a medical imaging device 11, a shooting device 12 and a workstation 13. The medical imaging device 11 and the shooting device 12 are both connected to the workstation 13 in communication. The specific connection method can be a wired communication connection or a wireless communication connection, which is not limited in this embodiment. The medical imaging device 11 is used to obtain a medical image of the area of ​​interest of the object to be avoided. The medical imaging device 11 can be a computer tomography (CT) scanning device or a magnetic resonance imaging device. Specifically, as Figure 1The medical imaging device 11 shown is a CT scanning device, which includes a CT machine and a CT host computer. The CT host computer is used to control the CT machine to scan the obstacle avoidance object carried on the bed to obtain a CT image of the area of ​​interest. The shooting device 12 can be any one of a structured light camera, a time-of-flight depth camera or a binocular camera. The shooting device 12 can obtain three-dimensional point cloud data of the obstacle avoidance object. The workstation 13 is used to receive the medical image obtained by the medical imaging device 11 and the three-dimensional point cloud data of the obstacle avoidance object obtained by the shooting device, and generate an obstacle avoidance model based on the medical image and the three-dimensional point cloud data. The specific description of generating the obstacle avoidance model can refer to the description of the obstacle avoidance model generation method in the following embodiment. The workstation 13 can be a computer device, which can be but not limited to an industrial computer, a laptop computer, and a tablet computer. The workstation 13 performs path planning according to the obstacle avoidance model, and sends the planned path to the surgical robot 14, so that the surgical robot 14 uses the planned path to avoid obstacles. The specific description of the surgical robot using the planned path to avoid obstacles can refer to the description of the obstacle avoidance method in the following embodiment.

[0061] In one embodiment, Figure 2 As shown, a method for generating an obstacle avoidance model is provided. In this embodiment, the method is applied to Figure 1 In this embodiment, the steps of the method may include the following steps:

[0062] Step 200: When the bed carrying the object to be avoided moves to a preset position, a medical image of the region of interest of the object to be avoided is obtained.

[0063] The bed of the medical imaging device carries an object to be avoided, which may be a human model or other obstacle. The preset position is determined by the user based on the region of interest of the object to be avoided, which refers to the surgical area of ​​the object to be avoided. After the user moves the bed carrying the object to be avoided to the preset position, the medical imaging device will scan the region of interest of the object to be avoided, obtain a medical image of the region of interest of the object to be avoided, and send the medical image to the workstation. The type of medical image is related to the type of medical imaging device. If the medical imaging device is a CT scanning device, the medical image obtained is a CT image; if the medical imaging device is a magnetic resonance device, the medical image obtained is a magnetic resonance image.

[0064] The workstation receives the medical image sent by the medical imaging device. The medical image may be sent to the workstation by the medical imaging device in real time.

[0065] Step 210: Control the bed to move from the preset position to different target positions, and control the shooting device to shoot a plurality of initial images of the obstacle to be avoided at the preset position and corresponding to each target position.

[0066] After receiving the medical image, the workstation sends a control instruction to the medical imaging device to control the bed in the medical imaging device to move from a preset position to a different target position according to a preset moving distance (bed moving value); wherein the preset moving distance can be determined by the user based on the shooting range of the shooting device and the distance that the bed can move (from the preset position to the outermost position of the medical imaging device), and this embodiment does not impose any restrictions on this.

[0067] When the workstation sends control instructions to the medical imaging device, it also sends control instructions to the shooting device to control the shooting device to shoot the object to be avoided when the bed carrying the object to be avoided is at the preset position and each target position, and obtain multiple initial images of the object to be avoided. That is to say, when the bed is at the preset position, the shooting device shoots the object to be avoided and obtains an initial image. When the bed moves to each target position, the shooting device shoots the object to be avoided and obtains the initial images of the object to be avoided at different target positions, so that multiple initial images can be obtained. After obtaining multiple initial images of the object to be avoided, the shooting device sends the multiple initial images to the workstation.

[0068] In one embodiment, the workstation controls the direction of movement of the bed. Figure 3 shown.

[0069] Step 220: Generate an obstacle avoidance model based on the medical image and the multiple initial images.

[0070] After the workstation receives the medical image of the area of ​​interest of the object to be avoided scanned by the medical imaging device and the multiple initial images of the object to be avoided taken by the shooting device, it can obtain the obstacle avoidance model, that is, the three-dimensional image of the object to be avoided, based on the medical image and the multiple initial images.

[0071] The obstacle avoidance model generation method provided in the embodiment of the present application obtains a medical image of the region of interest of the object to be avoided when the bed carrying the object to be avoided moves to a preset position; controls the bed to move from the preset position to different target positions, and controls the shooting device to shoot multiple initial images corresponding to the object to be avoided at the preset position and each target position; generates an obstacle avoidance model based on the medical image and the multiple initial images. In this embodiment, the obstacle avoidance model generated by combining the medical image and the multiple initial images is more efficient, and the medical image of the region of interest of the object to be avoided is obtained by the medical imaging device, which can avoid the object to be avoided from receiving a large dose of radiation, improve safety, and ensure the accuracy of the region of interest of the object to be avoided, so that the generated obstacle avoidance model meets the surgical requirements; the multiple initial images of the object to be avoided are obtained by the shooting device, which can improve the generation efficiency of the obstacle avoidance model. In addition, in the present embodiment, when the bed moves to a preset position, a medical image is acquired, and when the bed moves out of the preset position (i.e., moves from the preset position to a different target position), a plurality of initial images are acquired. In this way, in the process of completing a scanning process using a medical imaging device, both a medical image and a plurality of initial images can be acquired, thereby reducing the complexity of the process of generating an obstacle avoidance model and improving the efficiency and accuracy of generating the obstacle avoidance model.

[0072] In one embodiment, Figure 4 As shown, it is related to an implementation method of generating an obstacle avoidance model according to a medical image and multiple initial images, and the steps of the implementation method include:

[0073] Step 400: construct a first model of a region of interest according to a medical image.

[0074] After obtaining the medical image of the region of interest of the object to be avoided sent by the medical imaging device, the workstation constructs a first model of the region of interest of the object to be avoided based on the medical image. The medical imaging device obtains multiple two-dimensional tomographic images of the region of interest, and the workstation reconstructs a three-dimensional model of the region of interest, i.e., the first model, based on the multiple two-dimensional tomographic images. This embodiment does not limit the specific method of constructing the first model of the region of interest based on the medical image, as long as its function can be achieved.

[0075] The workstation can send control instructions to the bed and the photographing device while constructing a first model of the region of interest based on the medical image.

[0076] In an optional embodiment, after obtaining multiple two-dimensional tomographic images, the workstation generates coronal and sagittal images based on the tomographic images, extracts the contour of the region of interest, and uses a region growing tool to perform edge segmentation, remove redundant data, perform selective encoding and hole filling on each layer of the tomographic images, thereby generating a first model of the region of interest.

[0077] Step 410: stitching the multiple initial images to obtain a second model of the object to be avoided.

[0078] After acquiring multiple initial images of the obstacle object to be avoided taken by the shooting device, the workstation stitches the multiple initial images to obtain a second model of the obstacle object to be avoided. The multiple initial images acquired from the shooting device are three-dimensional point cloud data, and there may be repeated areas in the multiple initial images. After the workstation stitches the repeated areas in the multiple initial images, it can obtain complete three-dimensional point cloud data of the obstacle object to be avoided, that is, the second model of the obstacle object to be avoided. This embodiment does not limit the specific method of stitching multiple initial images, as long as its function can be achieved.

[0079] In an optional embodiment, the user may set a marker on the bed, and the workstation may perform splicing processing on the multiple initial images by extracting feature points from the multiple initial images.

[0080] In another optional embodiment, the multiple initial images are acquired when the bed moves from a preset position to different target positions, and the workstation may perform splicing processing on the multiple initial images according to the moving distance corresponding to each initial object.

[0081] Step 420: Generate an obstacle avoidance model based on the first model and the second model.

[0082] After obtaining the first model of the region of interest of the object to be avoided and the first model of the object to be avoided, the workstation generates an obstacle avoidance model according to the first model and the second model. The first model is a model of the region of interest in the object to be avoided, and the second model is a model of the complete object to be avoided. By splicing the two models, the obstacle avoidance model can be obtained.

[0083] In this embodiment, a first model of the region of interest is constructed by using the obtained medical image, a second model is constructed by using multiple initial images, and an obstacle avoidance model is generated based on the first model and the second model. In this way, by constructing the first model and the second model respectively, and then generating the obstacle avoidance model based on the first model and the second model, the efficiency of generating the obstacle avoidance model can be improved. Moreover, by constructing a model using the medical image and multiple initial images acquired during a scanning process of a medical imaging device, the consistency of the first model and the second model can be ensured, thereby improving the accuracy of the generated obstacle avoidance model.

[0084] In one embodiment, Figure 5 As shown, it is related to an implementation method of generating an obstacle avoidance model according to the first model and the second model, and the steps of the implementation method include:

[0085] Step 500: crop the area corresponding to the first model in the second model to obtain a cropped second model.

[0086] The second model is a model of a complete obstacle avoidance object, and the first model is a model of an area of ​​interest of the obstacle avoidance object, that is, the second model includes an area of ​​the first model. After the workstation determines the area corresponding to the first model in the second model, it cuts the area out of the second model to obtain a cut second model.

[0087] In an optional embodiment, the workstation can determine the area where the first model is located in the second model according to the position of the area of ​​interest on the bed and the position of the obstacle to be avoided on the bed. The workstation can also determine the area where the first model is located in the second model according to the position of the area of ​​interest in the obstacle to be avoided.

[0088] Step 510: splice the cropped second model and the first model to obtain an obstacle avoidance model.

[0089] After obtaining the cropped second model, the workstation splices the first model with the cropped second model, that is, splices the first model to the cropped area in the cropped first model, so as to obtain a complete model of the object to be avoided, that is, the obstacle avoidance model. The model of the area of ​​interest in the obstacle avoidance model is a model constructed by medical images, which can meet the accuracy required for surgery; the models of other areas are models constructed by images obtained by the shooting equipment.

[0090] In this embodiment, the workstation obtains an obstacle avoidance model by cropping the area corresponding to the first model in the second model, and then splicing the cropped second model with the first model. This method of obtaining the obstacle avoidance model is quick and easy to implement, and can improve the efficiency of generating the obstacle avoidance model.

[0091] See also Figure 6 An embodiment of the present application provides an obstacle avoidance method. The present embodiment applies the method to Figure 1 In this embodiment, the method comprises the following steps:

[0092] Step 600: receiving the planned path of the needle path corresponding to the surgical robot sent by the workstation; the planned path is generated by the workstation according to the obstacle avoidance model.

[0093] After generating the obstacle avoidance model, the workstation plans the path for the robotic arm of the surgical robot to move to the target position according to the obstacle avoidance model. The target position may be the position of the needle track preset by the user, that is, the workstation can obtain the planned path of the needle track corresponding to the surgical robot according to the obstacle avoidance model. There may be multiple needle tracks corresponding to the surgical robot, and each needle track has a corresponding planned path. After generating the planned path of the needle track corresponding to the surgical robot, the workstation will send the planned path to the surgical robot, and the surgical robot will receive the planned path. After generating the planned path, the workstation can directly send the planned path to the surgical robot; it can also store the generated planned path in the corresponding memory first, and then send it to the surgical robot when the surgical robot needs it, such as when it is in an idle state.

[0094] Step 610, determine whether the planned path of the needle tract meets the preset requirements. If the planned path of the needle tract does not meet the preset requirements, receive a new planned path and determine whether the new planned path meets the preset requirements until the planned path of the needle tract meets the preset requirements.

[0095] After receiving the corresponding planned path of the needle tract, the surgical robot will determine whether the planned path of the needle tract meets the preset requirements. The preset requirements are used to indicate that the surgical robot will not collide with obstacles when moving along the planned path of the needle tract. This embodiment does not limit the specific method of determining whether the planned path meets the preset requirements, as long as its function can be achieved.

[0096] If the surgical robot determines that the planned path of the needle tract does not meet the preset requirements, the workstation will re-plan the path according to the obstacle avoidance model and send the new planned path to the surgical robot. After receiving the new planned path, the surgical robot will judge whether the new planned path meets the preset requirements until the surgical robot determines that the received planned path of the needle tract meets the preset requirements. In other words, when the surgical robot determines that the planned path of the needle tract does not meet the preset requirements, it will return to the step of determining whether the planned path of the needle tract meets the preset requirements until the planned path of the needle tract meets the preset requirements.

[0097] The obstacle avoidance method provided in the embodiment of the present application is through receiving the planned path of the needle tract corresponding to the surgical robot sent by the workstation; the planned path is generated by the workstation according to the obstacle avoidance model; determining whether the planned path of the needle tract meets the requirements; if the planned path of the needle tract does not meet the preset requirements, receiving a new planned path, and determining whether the new planned path meets the preset requirements until the planned path of the needle tract meets the preset requirements. In this embodiment, the surgical robot determines whether the planned path of the needle tract generated according to the obstacle avoidance model received from the workstation meets the preset requirements. If the planned path does not meet the preset requirements, the workstation will re-plan the path according to the obstacle avoidance model and send it to the surgical robot until the planned path meets the preset requirements, which can ensure that the planned path of the needle tract corresponding to the surgical robot obtained by the workstation through the obstacle avoidance model is more accurate.

[0098] In one embodiment, Figure 7 As shown, an implementation method for determining whether the planned path of the needle track meets the preset requirements includes the following steps:

[0099] Step 700: Move to the target needle track position according to the planned path of the needle track, and if the needle track does not come into contact with the first obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements.

[0100] When the surgical robot determines whether the received planned path of the needle track meets the preset requirements, it does so through a simulation method, and the first obstacle is the phantom and scanning device used in the simulation. The surgical robot moves to the target needle track position according to the planned path of the needle track, that is, the surgical robot controls the robotic arm to move to the target needle track position according to the planned path of the needle track. During the movement, the surgical robot monitors in real time whether the robotic arm contacts the first obstacle; if the surgical robot determines that it does not contact the first obstacle during the movement, it determines that the planned path of the needle track meets the preset requirements.

[0101] Step 710: If the needle contacts a first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0102] If the surgical robot determines that the robotic arm contacts the first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0103] In this embodiment, when the surgical robot controls the robotic arm to move according to the received planned path of the needle tract, it determines whether the planned path of the needle tract meets the preset requirements by judging whether the robotic arm contacts the first obstacle. This method of determining whether the planned path of the needle tract meets the preset requirements is simple, fast, and easy to implement.

[0104] In one embodiment, when the surgical robot receives multiple planned paths of needle tracks, it is necessary to ensure that the surgical robot does not collide with other needle tracks when moving to the target needle track position according to the planned paths. Figure 8 As shown, when the surgical robot does not contact the first obstacle during the movement, that is, for each needle track, the surgical robot does not contact the first obstacle during the process of moving to the target needle track position according to the planned path, the obstacle avoidance method further includes:

[0105] Step 800: When there is a second obstacle at the target needle track position, move to the next target needle track position according to the planned path of the next target needle track, and if there is no contact with the second obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements.

[0106] After the surgical robot moves the robotic arm to the target needle track position according to the planned path of the needle track, it performs a puncture operation, that is, inserts the needle into the target needle track. The puncture operation is a simulation of the puncture in the actual scene.

[0107] In an optional embodiment, after the surgical robot moves the robotic arm to the target needle track position according to the planned path of the needle track, the doctor can manually insert the needle in the scanning room according to the position of the robotic arm; or the doctor can use a controller in the operating room outside the scanning room to adjust the posture of the robotic arm and remotely control the robotic arm to complete the puncture.

[0108] In an optional embodiment, when the doctor uses the controller to adjust the posture of the robotic arm in the operating room outside the scanning room, the surgical robot will monitor the proximity between the robotic arm and the phantom in real time. When the surgical robot detects that the distance between the robotic arm and the phantom is less than a preset distance threshold, it will issue a warning message to remind the doctor that the distance between the robotic arm and the phantom is too close; when the surgical robot detects that the robotic arm collides with the phantom, it will issue a warning message to remind the doctor that the robotic arm collides with the phantom.

[0109] If there is a second obstacle at the target needle track position, the surgical robot will control the robotic arm to move to the next target needle track position according to the planned path of the next needle track. During the movement, the surgical robot will monitor in real time whether the robotic arm contacts the second obstacle; if the surgical robot determines that it does not contact the second obstacle during the movement, it determines that the planned path of the needle track meets the preset requirements. Among them, the second obstacle refers to the puncture needle of other needle tracks.

[0110] In an optional embodiment, during the puncture process, the medical imaging device will continuously expose and acquire some images of the region of interest of the phantom, and display them on a display in the scanning room to provide the doctor with a reference for the position of the puncture needle.

[0111] Step 810: If the needle contacts a second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0112] If the surgical robot determines that it contacts the second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0113] In this embodiment, when the surgical robot determines that it does not contact the first obstacle during movement, after completing the puncture operation at the target needle track position, it will also determine whether it contacts the second obstacle during the process of moving to the next target needle track position according to the planned path of the next target needle track to determine whether the planned path of the needle track meets the preset requirements. This can improve the accuracy and reliability of the needle track planning path ultimately determined according to the obstacle avoidance model.

[0114] In an optional embodiment, when a plurality of needle tracks are included in the phantom, the order of the plurality of needle tracks is obtained; according to the order of the plurality of needle tracks and the planned path of the next target needle track, the needle tracks are moved to the next target needle track position; the order of the plurality of needle tracks is sorted according to a preset sorting rule, and the preset sorting rule is related to the shape of the needle locator in the robotic arm. When the shape of the needle locator is L-shaped, the sorting rule is to sort the needle tracks from far away from the robotic arm to close to the robotic arm, and to sort the needle tracks from outside the aperture to inside the aperture. When the shape of the needle locator is I-shaped, the sorting rule is to sort the needle tracks from inside the aperture to outside the aperture, and to sort the needle tracks from far away from the robotic arm to close to the robotic arm. Among them, inside and outside the aperture refer to the inside and outside of the aperture in the medical imaging device (CT), and the needle locator is installed at the end of the robotic arm.

[0115] When the needle locator is L-shaped, the planned needle path is as follows Fig. 9 shown. Fig. 9 Multiple dots in the middle represent multiple needle tracks. The order of the needle tracks is as follows: Fig. 9 When the needle locator is in the shape of I, the planned needle path is as follows: Fig.10 As shown, Fig.10 The figure includes Figure a, Figure b and Figure c. Figure a shows the order of the needle channels when multiple needle channels are arranged regularly; Figures b and c show the order of the needle channels when multiple needle channels are arranged irregularly. Fig.10 Multiple dots in the middle represent multiple needle tracks. The order of the needle tracks is as follows: Fig.10 The order indicated by the arrows.

[0116] In one embodiment, when it is determined that the planned path of the needle track does not meet the preset requirements, the obstacle avoidance method further includes:

[0117] A prompt message is returned to the workstation to instruct the workstation to adjust the planned path of the needle track according to the obstacle avoidance model, and the adjusted planned path of the needle track is sent to the surgical robot.

[0118] When the surgical robot determines that the planned path of the needle path does not meet the preset requirements, the surgical robot will send a prompt message to the workstation, and the prompt message is used to instruct the workstation to adjust the planned path of the needle path according to the obstacle avoidance model. In other words, when the workstation receives the prompt message sent by the surgical robot, indicating that the planned path of the needle path sent by the workstation to the surgical robot last time is inaccurate, the workstation will adjust the planned path of the needle path according to the obstacle avoidance model, and resend the adjusted planned path of the needle path to the surgical robot, so that the surgical robot can judge whether the received planned path of the needle path can avoid obstacles, that is, execute steps 600 and 610.

[0119] In this embodiment, when the surgical robot determines that the planned path of the needle tract does not meet the preset requirements, a prompt message is sent to the workstation to instruct the workstation to adjust the planned path of the needle tract according to the obstacle avoidance model. This makes it easier for the workstation to adjust the planned path of the needle tract to ensure the accuracy and reliability of the final planned path of the needle tract.

[0120] See also Fig.11 The present application provides a method for generating an obstacle avoidance model. In this embodiment, the medical imaging device is a CT scanning device, and the shooting device is a structured light camera. The method includes the following steps:

[0121] Step 111: The user moves the bed carrying the object to be avoided to a preset position;

[0122] Step 112: The CT scanning device scans the region of interest of the object to be avoided to obtain a CT image;

[0123] Step 113, sending the CT image to a workstation;

[0124] Step 114, the workstation constructs a CT model of the region of interest based on the medical image;

[0125] Step 115: The workstation sends a shooting instruction to the structured light camera and simultaneously sends a bed moving instruction to the CT scanning device;

[0126] Step 116: The CT scanning device controls the adult to move from a preset position to a different target position according to the movement instruction;

[0127] Step 117: The structured light camera captures a plurality of initial images of the bed at a preset position and at each target position according to the shooting instruction;

[0128] Step 118, the structured light camera sends a plurality of initial images to a workstation;

[0129] Step 119: The workstation performs splicing processing on the multiple initial images to obtain a structured light model; crops the area corresponding to the first model in the second model, and splices the cropped second model and the first model to obtain an obstacle avoidance model;

[0130] Step 120: Send the obstacle avoidance model to the surgical robot, so that the surgical robot determines the phantom according to the obstacle avoidance model.

[0131] See also Fig.12 The present application provides an obstacle avoidance method, the steps of which include:

[0132] Step 121, the user sorts the needle tracks according to the needle locator of the surgical robot;

[0133] Step 122, sending the sorting result to the workstation;

[0134] Step 123, the workstation plans the planning path of each needle channel according to the obstacle avoidance model and the sorting result;

[0135] Step 124, sending the planned path of each needle track to the surgical robot;

[0136] Step 125: the surgical robot controls the mechanical arm to move to the target needle track position according to the planned path of the needle track, determines that it does not contact the first obstacle during the movement, and performs a simulated puncture operation at the target needle track position; the first obstacle is a phantom;

[0137] Step 126: After the simulated puncture operation is completed, the robot arm is controlled to move to the next target needle track position according to the sorting rule and the planned path of the next target needle track; if it is determined that there is no contact with the second obstacle during the movement process, it is determined that the planned path of the needle track meets the preset requirements;

[0138] Step 127: if it is determined that the needle contacts the second obstacle during the moving process, it is determined that the planned path of the needle track does not meet the preset requirements;

[0139] Step 128, returning a prompt message to the workstation, which means that the workstation adjusts the planned path of the needle track according to the obstacle avoidance model, and sends the adjusted planned path of the needle track to the surgical robot.

[0140] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0141] See also Fig.13 An embodiment of the present application provides an obstacle avoidance system 20, which includes a workstation 13 and a surgical robot 14, and the workstation 13 is communicatively connected with the surgical robot 14; the workstation 13 is used to execute the steps of the above-mentioned obstacle avoidance model generation method, and the surgical robot 14 is used to execute the steps of the above-mentioned obstacle avoidance method.

[0142] The workstation 13 in the obstacle avoidance system 20 provided in this embodiment is used to execute the steps of the above-mentioned obstacle avoidance model generation method, and has all the beneficial effects of the obstacle avoidance model generation method; the surgical robot is used to execute the steps of the above-mentioned obstacle avoidance method, and has all the beneficial effects of the obstacle avoidance method, which will not be repeated here.

[0143] Based on the same inventive concept, the embodiment of the present application also provides an obstacle avoidance model device for implementing the obstacle avoidance model method involved above, and an obstacle avoidance device for the obstacle avoidance method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more obstacle avoidance model devices and obstacle avoidance device embodiments provided below can refer to the limitations of the obstacle avoidance model method and obstacle avoidance method above, and will not be repeated here.

[0144] In one embodiment, Fig.14 As shown, an obstacle avoidance model generating device 30 is provided, comprising: an acquisition module 31, a control module 32 and a generating module 33, wherein:

[0145] The acquisition module 31 is used to acquire a medical image of a region of interest of the object to be avoided when the bed carrying the object to be avoided moves to a preset position.

[0146] The control module 32 is used to control the bed to move from a preset position to different target positions, and control the photographing device to photograph a plurality of initial images of the obstacle avoidance object at the preset position and corresponding to each target position.

[0147] The generating module 33 is used to generate an obstacle avoidance model according to the medical image and the multiple initial images.

[0148] In one embodiment, the generation module 33 includes a construction unit and a generation unit. The construction unit is used to construct a first model of the region of interest based on the medical image; the plurality of initial images are spliced ​​to obtain a second model of the object to be avoided; and the generation unit is used to generate an obstacle avoidance model based on the first model and the second model.

[0149] In one embodiment, the generating unit is specifically used to crop the area corresponding to the first model in the second model to obtain a cropped second model; and splice the cropped second model and the first model to obtain an obstacle avoidance model.

[0150] In one embodiment, Fig.15 As shown, an obstacle avoidance device 40 is provided, comprising a receiving module 41 and a determining module 42.

[0151] The receiving module 41 is used to receive the planned path of the needle path corresponding to the surgical robot sent by the workstation; the planned path is generated by the workstation according to the obstacle avoidance model;

[0152] The determination module 42 is used to determine whether the planned path of the needle tract meets the preset requirements. If the planned path of the needle tract does not meet the preset requirements, a new planned path is received and it is determined whether the new planned path meets the preset requirements until the planned path of the needle tract meets the preset requirements.

[0153] In one embodiment, the determination module 42 is specifically used to move to the target needle track position according to the planned path of the needle track. If it does not contact the first obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if it contacts the first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0154] In one embodiment, the determination module 42 is also used to, when there is a second obstacle at the target needle track position, move to the next target needle track position according to the planned path of the next target needle track, and if it does not contact the second obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if it contacts the second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0155] In one embodiment, the obstacle avoidance device 40 further includes a sending module, which is used to return prompt information to the workstation to instruct the workstation to adjust the planned path of the needle channel according to the obstacle avoidance model, and send the adjusted planned path of the needle channel to the surgical robot.

[0156] Each module in the above obstacle avoidance model generation device and obstacle avoidance device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can 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 each module above.

[0157] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.16 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an obstacle avoidance model generation method and an obstacle avoidance method are implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0158] Those skilled in the art will understand that Fig.16 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0160] When the bed carrying the object to be avoided moves to a preset position, a medical image of a region of interest of the object to be avoided is obtained;

[0161] Controlling the bed to move from a preset position to different target positions, and controlling the photographing device to photograph a plurality of initial images corresponding to the obstacle avoidance object at the preset position and each target position;

[0162] An obstacle avoidance model is generated based on the medical image and multiple initial images.

[0163] In one embodiment, when the processor executes the computer program, the following steps are also implemented: constructing a first model of the region of interest based on the medical image; splicing multiple initial images to obtain a second model of the object to be avoided; and generating an obstacle avoidance model based on the first model and the second model.

[0164] In one embodiment, when the processor executes the computer program, the following steps are also implemented: cropping the area corresponding to the first model in the second model to obtain a cropped second model; and splicing the cropped second model and the first model to obtain an obstacle avoidance model.

[0165] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0166] The planned path of the needle path corresponding to the surgical robot sent by the receiving workstation is generated by the workstation according to the obstacle avoidance model;

[0167] Determine whether the planned path of the needle track meets the preset requirements. If the planned path of the needle track does not meet the preset requirements, receive a new planned path and determine whether the new planned path meets the preset requirements until the planned path of the needle track meets the preset requirements.

[0168] In one embodiment, when the processor executes the computer program, the following steps are also implemented: if the needle track is moved to the target needle track position according to the planned path of the needle track, and if it does not contact the first obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if it contacts the first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0169] In one embodiment, when the processor executes the computer program, the following steps are also implemented: when there is a second obstacle at the target needle track position, the needle track is moved to the next target needle track position according to the planned path of the next target needle track, and if the needle track does not contact the second obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if the needle track contacts the second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0170] In one embodiment, when the processor executes the computer program, it also implements the following steps: returning prompt information to the workstation to instruct the workstation to adjust the planned path of the needle track according to the obstacle avoidance model, and sending the adjusted planned path of the needle track to the surgical robot.

[0171] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0172] When the bed carrying the object to be avoided moves to a preset position, a medical image of a region of interest of the object to be avoided is obtained;

[0173] Controlling the bed to move from a preset position to different target positions, and controlling the photographing device to photograph a plurality of initial images corresponding to the obstacle avoidance object at the preset position and each target position;

[0174] An obstacle avoidance model is generated based on the medical image and multiple initial images.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: constructing a first model of the region of interest based on the medical image; splicing multiple initial images to obtain a second model of the object to be avoided; and generating an obstacle avoidance model based on the first model and the second model.

[0176] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: cropping the area corresponding to the first model in the second model to obtain a cropped second model; and splicing the cropped second model and the first model to obtain an obstacle avoidance model.

[0177] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0178] The planned path of the needle path corresponding to the surgical robot sent by the receiving workstation is generated by the workstation according to the obstacle avoidance model;

[0179] Determine whether the planned path of the needle track meets the preset requirements. If the planned path of the needle track does not meet the preset requirements, receive a new planned path and determine whether the new planned path meets the preset requirements until the planned path of the needle track meets the preset requirements.

[0180] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if the needle track is moved to the target needle track position according to the planned path of the needle track, and if it does not contact the first obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if it contacts the first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0181] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when there is a second obstacle at the target needle track position, move to the next target needle track position according to the planned path of the next target needle track, and if there is no contact with the second obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if there is contact with the second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0182] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a prompt message is returned to the workstation to instruct the workstation to adjust the planned path of the needle track according to the obstacle avoidance model, and the adjusted planned path of the needle track is sent to the surgical robot.

[0183] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0184] When the bed carrying the object to be avoided moves to a preset position, a medical image of a region of interest of the object to be avoided is obtained;

[0185] Controlling the bed to move from a preset position to different target positions, and controlling the photographing device to photograph a plurality of initial images corresponding to the obstacle avoidance object at the preset position and each target position;

[0186] An obstacle avoidance model is generated based on the medical image and multiple initial images.

[0187] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: constructing a first model of the region of interest based on the medical image; splicing multiple initial images to obtain a second model of the object to be avoided; and generating an obstacle avoidance model based on the first model and the second model.

[0188] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: cropping the area corresponding to the first model in the second model to obtain a cropped second model; and splicing the cropped second model and the first model to obtain an obstacle avoidance model.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0190] The planned path of the needle path corresponding to the surgical robot sent by the receiving workstation is generated by the workstation according to the obstacle avoidance model;

[0191] Determine whether the planned path of the needle track meets the preset requirements. If the planned path of the needle track does not meet the preset requirements, receive a new planned path and determine whether the new planned path meets the preset requirements until the planned path of the needle track meets the preset requirements.

[0192] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if the needle track is moved to the target needle track position according to the planned path of the needle track, and if it does not contact the first obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if it contacts the first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0193] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when there is a second obstacle at the target needle track position, move to the next target needle track position according to the planned path of the next target needle track, and if there is no contact with the second obstacle during the movement, it is determined that the planned path of the needle track meets the preset requirements; if there is contact with the second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirements.

[0194] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a prompt message is returned to the workstation to instruct the workstation to adjust the planned path of the needle track according to the obstacle avoidance model, and the adjusted planned path of the needle track is sent to the surgical robot.

[0195] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the 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-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0196] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0197] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating an obstacle avoidance model, characterized in that: The method comprises: When the bed carrying the object to be avoided moves to a preset position, a medical image of a region of interest of the object to be avoided is acquired; Controlling the bed to move from the preset position to different target positions, and controlling a photographing device to photograph a plurality of initial images of the obstacle-avoiding object at the preset position and corresponding to each of the target positions; An obstacle avoidance model is generated according to the medical image and the multiple initial images.

2. The method according to claim 1, characterized in that: The step of generating an obstacle avoidance model according to the medical image and the plurality of initial images comprises: constructing a first model of the region of interest based on the medical image; Splicing the multiple initial images to obtain a second model of the obstacle avoidance object; The obstacle avoidance model is generated according to the first model and the second model.

3. The method according to claim 2, characterized in that The step of generating the obstacle avoidance model according to the first model and the second model includes: Cropping the area corresponding to the first model in the second model to obtain a cropped second model; The cropped second model and the first model are spliced ​​together to obtain the obstacle avoidance model.

4. An obstacle avoidance method, characterized in that: The method comprises: Receiving a planned path of the needle path corresponding to the surgical robot sent by the workstation; the planned path is generated by the workstation according to the obstacle avoidance model; Determine whether the planned path of the needle tract meets the preset requirements. If the planned path of the needle tract does not meet the preset requirements, receive a new planned path and determine whether the new planned path meets the preset requirements until the planned path of the needle tract meets the preset requirements.

5. The method according to claim 4, characterized in that Determining whether the planned path of the needle track meets preset requirements includes: Moving to the target needle track position according to the planned path of the needle track, and not contacting the first obstacle during the movement, then determining that the planned path of the needle track meets the preset requirement; If the needle contacts the first obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirement.

6. The method according to claim 5, characterized in that In the case where the first obstacle is not in contact with the object during the movement, the method further includes: In the case where there is a second obstacle at the target needle track position, the needle track is moved to the next target needle track position according to the planned path of the next target needle track, and does not contact the second obstacle during the movement, then it is determined that the planned path of the needle track meets the preset requirement; If the needle contacts the second obstacle during the movement, it is determined that the planned path of the needle track does not meet the preset requirement.

7. The method according to claim 5 or 6, characterized in that: In the case where it is determined that the planned path of the needle track does not meet the preset requirement, the method further includes: A prompt message is returned to the workstation to instruct the workstation to adjust the planned path of the needle track according to the obstacle avoidance model, and the adjusted planned path of the needle track is sent to the surgical robot.

8. An obstacle avoidance system, characterized in that: The obstacle avoidance system includes a workstation and a surgical robot, wherein the workstation is communicatively connected to the surgical robot; the workstation is used to execute the steps of the method described in any one of claims 1-3, and the surgical robot is used to execute the steps of the method described in any one of claims 4-7.

9. An obstacle avoidance model generating device, characterized in that: The device comprises: An acquisition module, used for acquiring a medical image of a region of interest of the object to be avoided when the bed carrying the object to be avoided moves to a preset position; A control module, used for controlling the bed to move from the preset position to different target positions, and controlling a photographing device to photograph a plurality of initial images of the obstacle avoidance object at the preset position and corresponding to each of the target positions; A generating module is used to generate an obstacle avoidance model according to the medical image and the multiple initial images.

10. An obstacle avoidance device, characterized in that: The device comprises: A receiving module, used for receiving a planned path of a needle path corresponding to the surgical robot sent by a workstation; the planned path is generated by the workstation according to an obstacle avoidance model; A determination module is used to determine whether the planned path of the needle track meets the preset requirements. If the planned path of the needle track does not meet the preset requirements, a new planned path is received and it is determined whether the new planned path meets the preset requirements until the planned path of the needle track meets the preset requirements.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images