Path planning system

Abstract

The application relates to a path planning system. The path planning system comprises a surgical robot, a first sensor and a second sensor. The surgical robot comprises a mechanical arm base and a mechanical arm arranged on the mechanical arm base. The surgical robot is provided with a marker, and the relative position of the marker and the mechanical arm base is fixed. The first sensor is used for collecting first point cloud data comprising the marker. The second sensor is used for collecting second point cloud data. The first point cloud data and the second point cloud data jointly cover a surgical operation space of the mechanical arm. The surgical robot is used for constructing a scene model of the mechanical arm according to a first spatial transformation relationship between the first sensor and the mechanical arm base, a second spatial transformation relationship between the second sensor and the mechanical arm base, the first point cloud data and the second point cloud data, and performing path planning on the mechanical arm based on the scene model. The path planning system can accurately avoid obstacles.

Description

Technical Field

[0001] This application relates to the field of surgical robot technology, and in particular to a path planning system. Background Technology

[0002] With the development of surgical robot technology, surgical robots are being used more and more widely in surgical procedures. However, there are some fixed or moving obstacles in surgical procedures. For example, in neurosurgery, there are adjustable linkages or frames used to fix the patient's head, or medical staff in the workspace of the robotic arm. Therefore, obstacle avoidance and path planning for surgical robots are particularly important in their application.

[0003] Current surgical robots typically employ static models to pre-construct scenes for spatial navigation and movement, using these static models for obstacle avoidance and path planning. However, current obstacle avoidance methods are limited in their ability to avoid obstacles outside the static model during movement. Summary of the Invention

[0004] Therefore, it is necessary to provide a path planning system that can accurately and in real-time reconstruct the scene for obstacle avoidance, addressing the aforementioned technical problems.

[0005] A path planning system includes a surgical robot, a first sensor, and a second sensor. The surgical robot includes a robotic arm base and a robotic arm disposed on the robotic arm base. The surgical robot is equipped with a marker, and the relative position of the marker and the robotic arm base is fixed.

[0006] The first sensor is used to collect first point cloud data including the marker;

[0007] The second sensor is used to collect second point cloud data; wherein the first point cloud data and the second point cloud data together cover the surgical operation space of the robotic arm;

[0008] The surgical robot is used to construct a scene model of the robotic arm based on a first spatial transformation relationship between the first sensor and the robotic arm base, a second spatial transformation relationship between the second sensor and the robotic arm base, the first point cloud data, and the second point cloud data, so as to perform path planning for the robotic arm based on the scene model.

[0009] In one embodiment, the first sensor includes at least two sensors, and the second sensor includes at least one sensor.

[0010] In one embodiment, the surgical robot further includes a trolley and a main rod disposed on the trolley, with the first sensor disposed on the main rod;

[0011] The surgical robot is used to obtain a first spatial transformation relationship between the first sensor and the robotic arm base based on the first point cloud data and the spatial transformation relationship between the marker and the robotic arm base.

[0012] In one embodiment, the surgical robot further includes a support frame disposed on the main rod, and the first sensor is disposed on the support frame.

[0013] In one embodiment, the bracket is a retractable arc-shaped bracket.

[0014] In one embodiment, the path planning system further includes a motorized gimbal connected to the first sensor, the motorized gimbal being used to adjust the pose of the first sensor.

[0015] In one embodiment, the second sensor is disposed on the surgical robot, and the relative position of the second sensor and the robotic arm base is fixed;

[0016] The surgical robot is used to obtain a second spatial transformation relationship between the second sensor and the robotic arm base based on the spatial calibration parameters of the second sensor and the robotic arm.

[0017] In one embodiment, the second sensor is positioned in the environment of the surgical robot, and the second point cloud data includes the markers;

[0018] The surgical robot is used to obtain a second spatial transformation relationship between the second sensor and the robotic arm base based on the second point cloud data and the spatial transformation relationship between the marker and the robotic arm base.

[0019] In one embodiment, the surgical robot further includes a support arm, on which the marker is disposed.

[0020] In one embodiment, the surgical robot is configured to obtain the current spatial model of the robotic arm based on a pre-established spatial model of the robotic arm and the current joint values ​​of the robotic arm.

[0021] The surgical robot is further configured to convert the first point cloud data into first converted point cloud data based on the first spatial transformation relationship, convert the second point cloud data into second converted point cloud data based on the second spatial transformation relationship, fuse the first converted point cloud data and the second converted point cloud data into fused point cloud data, remove the robotic arm point cloud data from the fused point cloud data using the current spatial model of the robotic arm to obtain scene point cloud data, and construct a scene model based on the scene point cloud data.

[0022] The aforementioned path planning system includes: a surgical robot, a first sensor, and a second sensor. The surgical robot includes a robotic arm base and a robotic arm mounted on the robotic arm base. The surgical robot is equipped with markers, and the relative positions of the markers and the robotic arm base are fixed. The first sensor is used to collect first point cloud data including the markers; the second sensor is used to collect second point cloud data; the first point cloud data and the second point cloud data together cover the surgical operation space of the robotic arm; the surgical robot is used to construct a scene model of the robotic arm based on a first spatial transformation relationship between the first sensor and the robotic arm base, a second spatial transformation relationship between the second sensor and the robotic arm base, the first point cloud data, and the second point cloud data, so as to perform path planning for the robotic arm based on the scene model. Since the constructed scene model of the robotic arm is built in real time based on the first spatial transformation relationship between the first sensor and the robotic arm base, the second spatial transformation relationship between the second sensor and the robotic arm base, the first point cloud data, and the second point cloud data, the constructed scene model of the robotic arm includes real-time information of the surgical operation space of the robotic arm. Therefore, the path planning of the robotic arm can be accurately performed based on the real-time information of the surgical operation space of the robotic arm, which improves the accuracy of the path planning of the robotic arm. This allows the surgical robot to be controlled to travel along the planned path and enables the surgical robot to accurately avoid obstacles. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of a path planning system in one embodiment;

[0024] Figure 2 A schematic diagram of the surgical robot in another embodiment;

[0025] Figure 3 A schematic diagram of the surgical robot in another embodiment;

[0026] Explanation of reference numerals in the attached figures:

[0027] Surgical robot: 10; Robotic arm base: 101; Robotic arm: 102;

[0028] Marker: 103; Cart: 104; Main rod: 1041;

[0029] Support frame: 1042; Support arm: 105; First depth camera: 20;

[0030] Second depth camera: 30. Detailed Implementation

[0031] 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.

[0032] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0033] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0034] It should be noted that when an element is referred to as being "fixed to" or "set on" another element, it can be directly on the other element or there may be an intervening element. When an element is considered to be "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0035] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0036] With the widespread application of surgical robots in surgical procedures, obstacle avoidance and path planning have become particularly important. Typically, surgical procedures involve fixed or moving obstacles. For example, in neurosurgery, there are adjustable links or frames used to stabilize the patient's head, or medical personnel within the robotic arm's workspace. Current surgical robots typically use static models to pre-construct the scene for spatial navigation and movement, and then perform obstacle avoidance and path planning based on this static model. Therefore, existing obstacle avoidance methods require prior knowledge of the obstacle's appearance and orientation. However, during surgery, many obstacles exist whose appearance or orientation cannot be known in advance, such as movable links, frames with variable orientations and uncertain appearances, screws used to stabilize the patient, and medical personnel who may accidentally enter the surgical space during the robot's movement. This makes existing obstacle avoidance methods inaccurate. Therefore, this application provides a path planning system capable of accurate obstacle avoidance.

[0037] In one embodiment, a path planning system is provided, comprising a surgical robot, a first sensor, and a second sensor. Both the first and second sensors are devices capable of acquiring point cloud data of an object, such as a depth camera or a lidar. In this embodiment and subsequent embodiments, the example is provided where both the first and second sensors are depth cameras; the first sensor is referred to as the first depth camera, and the second sensor as the second depth camera.

[0038] like Figure 1 As shown, the surgical robot 10 includes a robotic arm base 101 and a robotic arm 102 mounted on the robotic arm base 101. The surgical robot 10 is equipped with a marker 103, and the relative position of the marker 103 and the robotic arm base 101 is fixed. A first depth camera 20 is used to collect first point cloud data including the marker 103. A second depth camera 30 is used to collect second point cloud data. The first point cloud data and the second point cloud data together cover the surgical operation space of the robotic arm 102. The surgical robot 10 is used to construct a scene model of the robotic arm 102 based on the first spatial transformation relationship between the first depth camera 20 and the robotic arm base 101, the second spatial transformation relationship between the second depth camera 30 and the robotic arm base 101, the first point cloud data, and the second point cloud data, so as to perform path planning for the robotic arm 102 based on the scene model.

[0039] In this embodiment, the marker 103 set on the surgical robot 10 is a non-planar marker. Optionally, the number of markers 103 can be one or more, but it is necessary to ensure that the first depth camera 20 can acquire first point cloud data including at least one marker 103. In this embodiment, the number of markers 103 is one as an example. Optionally, the spatial transformation relationship between the marker 103 and the robotic arm base 101 can be pre-calibrated, and the relative position of the marker 103 and the robotic arm base 101 can be determined according to the spatial transformation relationship between the marker 103 and the robotic arm base 101.

[0040] Optionally, the first depth camera 20 and the second depth camera 30 include, but are not limited to, cameras that generate point cloud information using active infrared light, binocular vision, or TOF (Time of Flight) technology. Optionally, the first depth camera 20 and the second depth camera 30 can both be mounted on the surgical robot 10, or they can be placed on an independent bracket at a location where the observable marker 103 can be seen, or they can be suspended above the surgical workspace, as long as the first depth camera 20 can collect first point cloud data including the aforementioned marker 103, and the second depth camera 30 can collect second point cloud data, and the first and second point cloud data together cover the surgical operating space of the robotic arm 102 of the surgical robot 10.

[0041] Optionally, the surgical robot 10 can spatially transform the first point cloud data and the second point cloud data according to the first spatial transformation relationship between the first depth camera 20 and the robotic arm base 101, and the second spatial transformation relationship between the second depth camera 30 and the robotic arm base 101. The transformed first point cloud data and the transformed second point cloud data are then fused, and a scene model of the robotic arm 102 is constructed using the fused point cloud data. Optionally, the scene model of the robotic arm 102 can be constructed using a triangulation algorithm or an octree algorithm, etc. Optionally, path planning can be performed on the robotic arm 102 of the surgical robot 10 based on the constructed scene model and existing path planning algorithms, such as random forest algorithms.

[0042] The aforementioned path planning system constructs a scene model of the robotic arm in real time based on the first spatial transformation relationship between the first depth camera and the robotic arm base, the second spatial transformation relationship between the second depth camera and the robotic arm base, and the first and second point cloud data. The constructed scene model of the robotic arm includes real-time information on the surgical operation space of the robotic arm. Therefore, the system can accurately plan the path of the robotic arm based on the real-time information on the surgical operation space of the robotic arm, thereby improving the accuracy of the path planning and controlling the surgical robot to travel along the planned path, enabling the surgical robot to accurately avoid obstacles.

[0043] Based on the above embodiments, in one embodiment, the first depth camera 20 includes at least two depth cameras, and the second depth camera 30 includes at least one depth camera.

[0044] Optionally, in this embodiment, the first depth camera 20 may include two depth cameras, or three depth cameras, four depth cameras, etc. Taking two depth cameras as an example, the requirement for the placement of these two depth cameras is that they can collect point cloud data including the marker 103. Optionally, the number of second depth cameras 30 can be determined according to actual needs, as long as the collected first and second point cloud data together cover the surgical operating space of the robotic arm 102.

[0045] In this embodiment, the first depth camera includes at least two depth cameras, and the second depth camera includes at least one depth camera. This ensures that the first point cloud data collected by the first depth camera and the second point cloud data collected by the second depth camera together cover the surgical operation space of the robotic arm, thus ensuring the integrity of the collected first and second point cloud data.

[0046] In some scenarios, such as Figure 2 As shown, the surgical robot 10 also includes a carriage 104 and a main rod 1041 mounted on the carriage 104. The first depth camera 20 is mounted on the main rod 1041 (not in the main rod 1041). Figure 2 (as shown in the figure); surgical robot 10 is used to obtain the first spatial transformation relationship between the first depth camera 20 and the robotic arm base 101 based on the first point cloud data and the spatial transformation relationship between the marker 103 and the robotic arm base 101.

[0047] Optionally, the main rod 1041 can be a cylindrical main rod 1041, a cuboid main rod 1041, etc. Optionally, the first depth camera 20 can be fixed to the main rod 1041 by a clip or by screws. Optionally, such as Figure 3 As shown, the surgical robot 10 also includes a support 1042, which can be mounted on the main rod 1041. The first depth camera 20 can be mounted on the support 1042. Optionally, the support 1042 can be a telescopic arc-shaped support. Optionally, the telescopic arc-shaped support can be electrically rotated around the main rod 1041. Optionally, the telescopic arc-shaped support can have a built-in geared rail and slide rail motor to achieve electric telescopic movement.

[0048] It is understandable that, since the first point cloud data includes the point cloud data of marker 103, and the relative position of marker 103 and robotic arm base 101 is fixed, the surgical robot 10 can determine the first spatial transformation relationship between the first depth camera 20 and robotic arm base 101 based on the spatial transformation relationship between marker 103 and robotic arm base 101 and the aforementioned first point cloud data. It should be noted that the aforementioned spatial transformation relationship between marker 103 and robotic arm base 101 can be obtained in advance based on the spatial calibration parameters of marker 103 and robotic arm base 101.

[0049] In this embodiment, the surgical robot also includes a trolley and a main rod set on the trolley. A first depth camera is set on the main rod. The first depth camera can collect first point cloud data including markers, so that the surgical robot can accurately obtain the first spatial transformation relationship between the first depth camera and the robotic arm base based on the first point cloud data and the spatial transformation relationship between the markers and the robotic arm base.

[0050] In some scenarios, it is also necessary to adjust the pose of the first depth camera 20. In one embodiment, the above-mentioned path planning system further includes a motorized gimbal connected to the first depth camera 20. The motorized gimbal is used to adjust the pose of the first depth camera 20.

[0051] The motorized pan-tilt head is used to mount and connect to the first depth camera 20. Under the control of the voltage (output by the pan-tilt controller), the motorized pan-tilt head rotates horizontally and vertically, allowing the first depth camera 20 to be aligned with and capture the desired observation target over a wide range. Optionally, the motorized pan-tilt head in this embodiment can be a limiting type or a continuously rotating type. It is understood that in this embodiment, the motorized pan-tilt head can adjust the pose of the first depth camera 20 until the first depth camera 20 can acquire the first point cloud data including the aforementioned marker 103. Optionally, in this embodiment, the number of motorized pan-tilt heads is the same as the number of first depth cameras 20.

[0052] In this embodiment, the path planning system also includes a motorized gimbal connected to the first depth camera, which can adjust the pose of the first depth camera so that the first depth camera can acquire first point cloud data including markers set on the surgical robot.

[0053] In the scenario described above where the second depth camera 30 acquires the second point cloud data, the second depth camera 30 can be set up on the surgical robot 10 or in the environment where the surgical robot 10 is located. The following will explain these two scenarios respectively:

[0054] For the first type, please continue reading. Figure 3The second depth camera 30 is mounted on the surgical robot 10, and the relative position of the second depth camera 30 and the robotic arm base 101 is fixed. The surgical robot 10 is used to obtain the second spatial transformation relationship between the second depth camera 30 and the robotic arm base 101 based on the spatial calibration parameters of the second depth camera 30 and the robotic arm 102.

[0055] Optionally, in this embodiment, the second depth camera 30 may be disposed below the robotic arm base 101 of the surgical robot 10, and the relative position of the second depth camera 30 and the robotic arm base 101 is fixed. Optionally, in this embodiment, the surgical robot 10 may obtain the relative position and relative posture between the second depth camera 30 and the robotic arm 102 based on the spatial calibration parameters between the second depth camera 30 and the robotic arm 102, and determine the second spatial transformation relationship between the second depth camera 30 and the robotic arm base 101 based on the relative position and relative posture between the second depth camera 30 and the robotic arm 102.

[0056] In this embodiment, the second depth camera is mounted on the surgical robot, and the relative position of the second depth camera and the robotic arm base is fixed. This allows the surgical robot to quickly obtain the second spatial transformation relationship between the second depth camera and the robotic arm base based on the spatial calibration parameters of the second depth camera and the robotic arm, thereby improving the efficiency of the surgical robot in obtaining the second spatial transformation relationship between the second depth camera and the robotic arm base.

[0057] The second method involves setting the second depth camera 30 in the environment where the surgical robot 10 is located, and the second point cloud data includes the marker 103. The surgical robot 10 is used to obtain the second spatial transformation relationship between the second depth camera 30 and the robotic arm base 101 based on the second point cloud data and the spatial transformation relationship between the marker 103 and the robotic arm base 101.

[0058] In this embodiment, the second depth camera 30 is set in the environment where the surgical robot 10 is located. At this time, the second point cloud data collected by the second depth camera 30 includes the marker 103 set on the surgical robot 10. The surgical robot 10 can obtain the second spatial transformation relationship between the second depth camera 30 and the robotic arm base 101 based on the information of the marker 103 included in the second point cloud data and the spatial transformation relationship between the marker 103 and the robotic arm base 101 obtained in advance.

[0059] In this embodiment, the second depth camera is set in the environment where the surgical robot is located. The second depth camera can collect second point cloud data including markers. Since the markers are set on the surgical robot, the surgical robot can quickly obtain the second spatial transformation relationship between the second depth camera and the robotic arm base based on the information of the markers included in the second point cloud data and the spatial transformation relationship between the markers and the robotic arm base of the surgical robot. This improves the efficiency of the surgical robot in obtaining the second spatial transformation relationship between the second depth camera and the robotic arm base.

[0060] In one embodiment, please see [link to previous article]. Figure 3 The surgical robot 10 also includes a support arm 105, and a marker 103 is disposed on the support arm 105.

[0061] In this embodiment, the surgical robot 10 further includes a support arm 105, and the aforementioned marker 103 is disposed on the support arm 105. Optionally, the marker 103 may be recessed in the support arm 105 or disposed on the surface of the support arm 105.

[0062] In this embodiment, the surgical robot also includes a support arm. Setting the marker on the support arm eliminates the need for additional components on the surgical robot, reducing the space occupied by the surgical robot. The marker can be set using the existing components of the surgical robot.

[0063] In one embodiment, the surgical robot 10 is used to obtain the current spatial model of the robotic arm based on a pre-established robotic arm spatial model and the current joint values ​​of the robotic arm 102; the surgical robot 10 is also used to convert the first point cloud data to obtain the first converted point cloud data based on the first spatial transformation relationship, convert the second point cloud data to obtain the second converted point cloud data based on the second spatial transformation relationship, fuse the first converted point cloud data and the second converted point cloud data to obtain the fused point cloud data, use the current spatial model of the robotic arm to remove the robotic arm point cloud data in the fused point cloud data to obtain the scene point cloud data, and construct a scene model based on the scene point cloud data.

[0064] In this embodiment, the surgical robot 10 can determine the current space of the robotic arm 102 based on its current joint values, and determine the current spatial model of the robotic arm based on a pre-established spatial model of the robotic arm and its current joint values. It is understood that the first spatial transformation relationship is the spatial transformation relationship between the first depth camera 20 and the robotic arm base 101. The surgical robot 10 can transform the first point cloud data into the space where the robotic arm base 101 is located based on the first spatial transformation relationship to obtain the first transformed point cloud data. The second spatial transformation relationship is the spatial transformation relationship between the second depth camera 30 and the robotic arm base 101. The surgical robot 10 can transform the second point cloud data into the space where the robotic arm base 101 is located based on the second spatial transformation relationship to obtain the second transformed point cloud data. The first and second transformed point cloud data are then fused to obtain fused point cloud data. The current spatial model of the robotic arm obtained above is used to remove the robotic arm point cloud data from the fused point cloud data to obtain scene point cloud data. Optionally, the surgical robot 10 can construct a scene model from the scene point cloud data using a triangular meshing algorithm or an octree algorithm.

[0065] In this embodiment, the surgical robot can accurately obtain the current spatial model of the robotic arm based on the pre-established spatial model of the robotic arm and the current joint values ​​of the robotic arm. The surgical robot can also accurately convert the first point cloud data into first transformed point cloud data based on the first spatial transformation relationship between the first depth camera and the robotic arm base, and accurately convert the second point cloud data into second transformed point cloud data based on the second spatial transformation relationship between the second depth camera and the robotic arm base. Thus, the first transformed point cloud data and the second transformed point cloud data can be fused to accurately obtain fused point cloud data. The robotic arm point cloud data in the fused point cloud data is removed using the current spatial model of the robotic arm to accurately obtain scene point cloud data. Based on the obtained scene point cloud data, the scene model is accurately constructed, which improves the accuracy of the constructed scene model.

[0066] It should be noted that in some other scenarios, the marker 103 used is a planar marker, and the planar marker has features that can be recognized by the RGB camera, such as color features. In this case, the RGB camera will be integrated on the first depth camera 20, and the spatial transformation relationship between the first depth camera 20 and the RGB camera will be pre-calibrated, so that the first depth camera 20 can obtain the first point cloud data including the planar marker based on the RGB camera.

[0067] In this embodiment, the first depth camera 20 can only obtain the distance information of the planar marker relative to itself, but cannot obtain other feature information of the planar marker. Therefore, the first depth camera 20 cannot obtain the pose information of the planar marker relative to itself. However, the RGB camera can obtain other feature information of the planar marker. The RGB camera can determine the pose information of the planar marker relative to the first depth camera 20 based on the spatial transformation relationship between itself and the first depth camera 20 and the acquired image information, thereby enabling the first depth camera 20 to obtain first point cloud data containing the planar marker.

[0068] It is understandable that when the second depth camera 30 is in the surgical environment, an RGB camera will be integrated on the second depth camera 30, and the spatial transformation relationship between the second depth camera 30 and the RGB camera will be pre-calibrated, so that the second depth camera 30 can obtain second point cloud data including the planar marker based on the RGB camera.

[0069] In this embodiment, when the marker set on the surgical robot is a planar marker, the first depth camera, integrated with an RGB camera, can accurately acquire first point cloud data including the planar marker, thereby improving the accuracy of the first point cloud data acquired by the first depth camera. When the marker set on the surgical robot is a planar marker, the second depth camera, integrated with an RGB camera, can accurately acquire second point cloud data including the planar marker, thereby improving the accuracy of the second point cloud data acquired by the second depth camera.

[0070] 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.

[0071] 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 path planning system, characterized in that, The path planning system includes: a surgical robot, a first sensor, and a second sensor. The surgical robot includes a robotic arm base and a robotic arm mounted on the robotic arm base. The surgical robot is equipped with a marker, and the relative position of the marker and the robotic arm base is fixed. The surgical robot also includes a trolley and a main rod mounted on the trolley. The first sensor is mounted on the main rod. The second sensor is located in the environment in which the surgical robot is located. The first sensor is used to collect first point cloud data including the marker; the first point cloud data includes the marker. The second sensor is used to collect second point cloud data; wherein the first point cloud data and the second point cloud data together cover the surgical operation space of the robotic arm; the second point cloud data includes the markers; The surgical robot is configured to obtain a first spatial transformation relationship between the first sensor and the robotic arm base based on the first point cloud data and the spatial transformation relationship between the marker and the robotic arm base; obtain a second spatial transformation relationship between the second sensor and the robotic arm base based on the second point cloud data and the spatial transformation relationship between the marker and the robotic arm base; and construct a scene model of the robotic arm based on the first spatial transformation relationship between the first sensor and the robotic arm base, the second spatial transformation relationship between the second sensor and the robotic arm base, the first point cloud data, and the second point cloud data, so as to perform path planning for the robotic arm based on the scene model.

2. The path planning system according to claim 1, characterized in that, The first sensor includes at least two sensors, and the second sensor includes at least one sensor.

3. The path planning system according to claim 1, characterized in that, The surgical robot also includes a support frame, which is mounted on the main rod, and the first sensor is mounted on the support frame.

4. The path planning system according to claim 3, characterized in that, The bracket is a retractable arc-shaped bracket.

5. The path planning system according to claim 1, characterized in that, The path planning system also includes a motorized gimbal, which is connected to the first sensor and is used to adjust the pose of the first sensor.

6. The path planning system according to claim 1, characterized in that, The surgical robot also includes a support arm, and the marker is disposed on the support arm.

7. The path planning system according to claim 1, characterized in that, The surgical robot is used to obtain the current spatial model of the robotic arm based on a pre-established spatial model of the robotic arm and the current joint values ​​of the robotic arm. The surgical robot is further configured to convert the first point cloud data into first converted point cloud data based on the first spatial transformation relationship, convert the second point cloud data into second converted point cloud data based on the second spatial transformation relationship, fuse the first converted point cloud data and the second converted point cloud data into fused point cloud data, remove the robotic arm point cloud data from the fused point cloud data using the current spatial model of the robotic arm to obtain scene point cloud data, and construct a scene model based on the scene point cloud data.

Images