A dressing change navigation system and a dressing change robot

Abstract

The present invention discloses a dressing change navigation system and a dressing change robot, comprising: an information calibration module, which is used to obtain imaging data of a wound, generate and rigidly calibrate feature points, and calculate the surface treatment range and depth treatment range of the dressing change area according to the feature points; a navigation module, which generates a navigation path according to the feature points and the surface treatment range and depth treatment range of the wound; real-time monitoring of the dressing change area, non-rigid calibration through triangulation positioning, dynamic adjustment of the navigation path, and generation of navigation data. The present invention reduces the workload of medical staff, improves the efficiency and accuracy of the dressing change operation, and reduces the risk of wound infection by controlling a robot device that fully automatically performs wound dressing change operations.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical treatment, and in particular to a dressing change navigation system and a dressing change robot. Background Art

[0002] Currently, wound dressing changes after surgical operations usually rely on manual operations by medical staff. The surgical wound dressing change operation process is relatively simple, mainly including disinfection of the wound surface, removal of old dressings, wound treatment and covering with new dressings. Although these operation steps are not highly technical, they are highly repetitive and require a lot of time and energy from medical staff. Especially in the postoperative care stage of surgery, this type of repetitive labor occupies most of the time of surgeons and nurses.

[0003] Although existing technical means can help doctors change dressings through certain mechanical equipment or simple auxiliary tools, these devices are mainly manually operated and cannot be automated or intelligent. They still need to rely on the experience of doctors or nurses to make judgments and handle them. In addition, there are still certain errors and instabilities in the manual dressing change process, such as improper operation force, incomplete disinfection, untimely dressing change, etc., which may increase the risk of wound infection and prolong the patient's recovery time and hospitalization period.

[0004] Therefore, how to design a robotic device that can fully automatically perform wound dressing changes to reduce the workload of medical staff, improve the efficiency and accuracy of dressing changes, and reduce the risk of wound infection has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to overcome the above-mentioned technical problems, the present application provides a dressing change navigation system and a dressing change robot. By using robotic equipment that fully automatically performs wound dressing changes, the workload of medical staff can be reduced, the efficiency and accuracy of dressing changes can be improved, and the risk of wound infection can be reduced.

[0006] In a first aspect, the present invention provides a dressing change navigation system, comprising:

[0007] An information calibration module, used to obtain imaging data of the wound, generate and rigidly calibrate feature points, and calculate the surface treatment range and depth treatment range of the dressing change area according to the feature points;

[0008] The navigation module generates a navigation path according to the feature points and the wound surface treatment range and depth treatment range; monitors the dressing change area in real time, performs non-rigid calibration through triangulation positioning method, dynamically adjusts the navigation path, and generates navigation data.

[0009] In some embodiments, the information calibration module includes a depth processing unit, which determines the two-dimensional contour of the dressing change area based on the imaging data and the feature points; obtains the laser ranging depth of the dressing change area, and determines the depth range of the dressing change area.

[0010] In some embodiments, the navigation module includes a path adjustment unit, and the path adjustment unit performs non-rigid calibration by triangulation positioning to dynamically adjust the navigation path, including:

[0011] Construct a triangular model in the dressing change area; the triangular model includes a marking point, a target point, an entry point and a planned angle; the marking point and the entry point are located on the curved surface where the incision of the dressing change area is located, and the distance between the target point and the marking point is the laser ranging depth;

[0012] Acquire the first real-time positioning data, the second real-time positioning data and the third real-time positioning data to form triangulated positioning data; the first real-time positioning data is the real-time entry distance of the end-effector in the dressing change area; the second real-time positioning data is the positioning data of the entry point; the third real-time positioning data is the positioning data of the marking point;

[0013] Determine the real-time angle through triangulation data;

[0014] The navigation path is dynamically adjusted according to the real-time angle, the planned angle and the first real-time positioning data.

[0015] In some embodiments, the information calibration module includes a feature point recognition unit, which processes the imaging data of the dressing change area through an AI feature point recognition model in combination with medical dressing change pictures to identify feature points of the imaging data, wherein the feature points include one or more of the following: the boundary, depth, and suture range of the dressing change area.

[0016] In some embodiments, the information calibration module includes a surface processing unit, which identifies a boundary of the dressing change area according to the feature point recognition unit, and calculates the area of ​​the curved surface where the dressing change area is located by using a curved surface area calculation formula.

[0017] In some embodiments, the information calibration module also includes an optical imaging unit for acquiring imaging data and laser ranging data; the imaging data includes multiple marking points, each of which is set at the boundary of the dressing change area to form a marking surface; the surface processing unit calculates the area of ​​the marking surface where the dressing change area is located through the marking points.

[0018] In a second aspect, the present invention provides a dressing change robot, comprising a dressing change navigation system and a robotic arm operation module as described above, wherein the robotic arm operation module outputs a robotic arm control instruction based on the navigation data output by the navigation module, and the robotic arm operation module comprises a robotic arm and an end effector tool, and controls the robotic arm and the end effector tool to perform dressing change operations according to the robotic arm control instruction.

[0019] In some embodiments, it also includes a dressing change transport module, which includes a dressing change unit and a transport component; the robotic arm operation module is mounted on the platform of the dressing change unit, and the dressing change unit is provided with a clean area for placing unused tools and a contaminated area for placing used tools; the transport component is used to move the robotic arm to a designated dressing change position.

[0020] In some embodiments, the robotic arm includes a scanning detection device, which is used to detect the working range of the robotic arm operation module, determine the operation area, and monitor the dressing change process of the end-effector tool in real time.

[0021] In some embodiments, the end effector tool includes a switching assembly and one or more of the following instruments: forceps, tweezers, scissors; and the instrument of the end effector tool has a built-in sensor.

[0022] The present invention provides a dressing change navigation system and a dressing change robot. By constructing a triangular model and combining rigid and non-rigid registration, the dressing change path is adjusted in real time to ensure that even if the organ is displaced and deformed during the dressing change process, the dressing change robot can accurately operate along the optimal path, avoid the uncontrollable factors randomly generated during the operation, significantly improve the accuracy and safety of the dressing change path, reduce damage to healthy tissues, reduce the risk of dressing change, improve surgical efficiency, and improve the patient's postoperative recovery effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of the dressing change navigation system provided by the present invention;

[0024] Figure 2 A schematic diagram of a triangular model in the dressing change navigation system provided by the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of the dressing changing robot provided by the present invention;

[0026] In the figure: 1. Robotic arm; 2. End effector; 3. Dressing change and transportation module. DETAILED DESCRIPTION

[0027] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0028] like Figure 1As shown, the present application provides a dressing change navigation system and a dressing change robot, which are robotic devices that fully automatically perform wound dressing change operations, thereby reducing the workload of medical staff, improving the efficiency and accuracy of dressing change operations, and reducing the risk of wound infection.

[0029] The dressing change navigation system includes an information calibration module, which is used to obtain imaging data of the wound, generate and rigidly calibrate feature points, and calculate the surface treatment range and depth treatment range of the dressing change area according to the feature points; a navigation module, which generates a navigation path according to the feature points and the surface treatment range and depth treatment range of the wound; and real-time monitoring of the dressing change area, performing non-rigid calibration through triangulation positioning method, dynamically adjusting the navigation path, and generating navigation data.

[0030] The information calibration module includes an optical imaging unit, a multimodal fusion unit, a feature point recognition unit, a surface processing unit and a depth processing unit. The optical imaging unit is used to obtain imaging data and laser ranging data; the imaging data includes a plurality of marking points, each of which is set at the boundary of the dressing change area to form a marking surface. Specifically, the optical imaging unit images the surface of the dressing change area by emitting infrared light, structured light or laser and other optical signals, receives and obtains the reflected light signal, and generates preliminary imaging data. On the basis of optical imaging, other detection imaging methods can also be used, such as ordinary video, electromagnetic field imaging, X-ray, ultrasound, magnetic resonance and holographic imaging, etc., to obtain more comprehensive three-dimensional information of the dressing change area.

[0031] The multimodal fusion unit receives positioning data from different imaging methods, calibrates and fuses these positioning data into a unified working coordinate system. To this end, a calibration point is set outside the dressing area to uniformly adjust the working coordinates of different imaging data to ensure that all data are aligned in the same working coordinate system.

[0032] After obtaining the imaging data, the feature point recognition unit of the information calibration module processes the imaging data of the dressing area through the AI ​​feature point recognition model combined with the medical dressing change picture to identify the feature points of the imaging data, which include one or more of the following: the boundary, depth, and suture range of the dressing area. In addition, the identified feature points are compared and calibrated with the corresponding feature points in the standard medical image library to ensure that the dressing robot can accurately locate and operate, and improve the high precision and consistency in the wound treatment process.

[0033] After the calibration is completed, the surface processing unit identifies the boundary of the dressing change area according to the feature point recognition unit, and calculates the area of ​​the curved surface where the dressing change area is located by the curved surface area calculation formula. A plurality of marking points are set in the imaging data, each of which is set at the boundary of the dressing change area to form a marking curved surface; the surface processing unit recognizes the boundary of the dressing change area through the marking points, thereby calculating the area of ​​the marking curved surface where the dressing change area is located.

[0034] Exemplarily, the marking point is realized by an optical marking ball. The optical imaging unit identifies the four corners of the curved surface where the dressing change area is located, and determines the area of ​​the marked curved surface where the dressing change area is located according to the range set by the optical marking ball. The marked curved surface can be regarded as a three-dimensional smooth curved surface S, and the surface area calculation formula is used to calculate:

[0035]

[0036] Where S is the marked surface, Dxy is the projection area of ​​the marked surface S on the xy plane, and the area of ​​each small piece on the surface is calculated by integration to finally get the area of ​​the entire marked surface.

[0037] The depth processing unit determines the two-dimensional contour of the dressing change area based on the imaging data and feature points obtained by the optical imaging unit; obtains the laser ranging depth of the dressing change area to determine the depth range of the dressing change area. The laser ranging depth is measured by a laser ranging device, which includes a transmitting end, a receiving end, and an information processing end. The transmitting end sends a laser beam in the dressing change area, the receiving end receives the returned laser beam, and the information processing end measures the time difference of the laser beam returning to calculate the depth of the dressing change area.

[0038] Furthermore, the feature point recognition unit, surface processing unit and depth processing unit of the information calibration module can be implemented by the AI ​​model. The input imaging data is processed by the training model using an artificial intelligence (AI) algorithm to automatically identify the feature points of the wound, such as the boundary, depth and position of the wound sutures. The AI ​​model is trained using medical dressing images and can accurately identify and capture these feature points. Medical dressing images are already labeled imaging data, which mark the dressing area, incision depth, skin, fat, muscle range, and contour features of the dressing instrument. The AI ​​model automatically identifies the feature points of the dressing area, the surface processing range and the depth processing range, thereby improving the processing efficiency and accuracy of the dressing robot.

[0039] Since the wound, i.e. the dressing area, has a certain deformation during the dressing process, it is necessary to perform non-rigid registration on the area and depth where the dressing robot needs to operate, so as to improve the accuracy of the dressing robot's operation. The navigation module can use image segmentation algorithm, feature extraction algorithm, target detection algorithm, face recognition algorithm, stereo vision algorithm, motion tracking algorithm, convolutional neural network (CNN), support vector machine (SVM), principal component analysis (PCA), Kalman filter (KalmanFilter), Gaussian mixture model (GMM), recursive neural network (RNN), feature point detection and description (SIFT), and histogram equalization to identify the pixel difference and tissue absorbance of different tissues such as skin, fat, muscle, scar, suture, etc. in the dressing area, so as to adjust the navigation data.

[0040] In this application, in order to improve the accuracy of the operation, the navigation module generates a navigation path based on the feature points and the wound surface treatment range and depth treatment range; monitors the dressing area in real time, performs non-rigid calibration through triangulation positioning, dynamically adjusts the navigation path, and generates navigation data. The navigation module includes a path adjustment unit and a path conversion unit. The path adjustment unit performs non-rigid calibration through triangulation positioning and dynamically adjusts the navigation path, including:

[0041] A triangular model is constructed in the dressing change area; the triangular model includes a marking point, a target point, an entry point and an entry angle; the marking point and the entry point are located on the curved surface where the incision of the dressing change area is located, and the distance between the target point and the marking point is the laser ranging depth;

[0042] Acquire the first real-time positioning data, the second real-time positioning data and the third real-time positioning data to form triangulated positioning data; the first real-time positioning data is the real-time entry distance of the end-effector in the dressing change area; the second real-time positioning data is the positioning data of the entry point; the third real-time positioning data is the positioning data of the marking point;

[0043] Determine the real-time angle through triangulation data;

[0044] The navigation path is dynamically adjusted according to the real-time angle, the planned angle and the first real-time positioning data.

[0045] Specifically, Figure 2 As shown in the figure, after the electromagnetic field completes the rigid registration, the section of the dressing area is determined by ultrasound or other preoperative imaging data to determine the position of the marking point a. The entry point b corresponding to the preset section and the deepest target point c of the section are calculated according to the preoperative imaging data, and the planned angle is calculated by the inverse trigonometric function to construct a triangular model in the dressing area. The triangular model reflects the depth and three-dimensional shape of the wound and is used to guide the dressing robot to perform precise operations in the wound.

[0046] Real-time non-rigid registration is performed by electromagnetic tracking to assist the positioning of the triangular model and update the triangular model. An in vitro electromagnetic field is constructed in the dressing change area to form a 3D coordinate system in the dressing change area. After calibration with the working coordinate system of the information calibration module, non-rigid registration is performed through the electromagnetic field.

[0047] Cut in at point b, the entry point of the cross-section of the dressing area, and obtain the first real-time positioning data, the second real-time positioning data, and the third real-time positioning data through the first target, the second target, and the third target to form triangulated positioning data; the first real-time positioning data is the real-time entry distance of the end-effector tool in the dressing area; the second real-time positioning data is the positioning data of the entry point; the third real-time positioning data is the positioning data of the marking point. The first target, that is, the base point target, is used to determine the positioning information of the fixed point in the dressing area, that is, point a; the second target, that is, the operating target, is installed in the working part of the dressing change instrument such as the ultrasonic knife, CUSA, etc., and is used to determine the real-time moving position information of the dressing change instrument in the dressing change area; the third target, that is, the detection target, is used for the position of the entry point b, so as to determine the real-time angle of triangulated positioning in the surgical area to be navigated.

[0048] Determine the first side length L using triangulation data ab , the second side length L bc’ and the length of the third side L ac’。 On this basis, the real-time angle is calculated by the arc cosine function:

[0049] cosα=(L ab 2 +L bc’ 2 -L ac’ 2 ) / 2L ab L bc’

[0050] Compare the real-time angle with the planned angle, and adjust the depth and real-time angle at the entry point b to make the real-time angle the same as the planned angle α. Multiple adjacent entry points in the dressing change area form the imaging channel of the triangular model, and multiple imaging channels constitute the planned channel entry surface. In the actual dressing change operation, the relative measurement value of the distance between the entry point b on the preset section and the end-effector, i.e., the real-time entry distance c' of the dressing change instrument, is limited by the influence of displacement deformation, and the measurement process is controllable, with little impact on the surgical process. Therefore, the second side length L bc’ It can be used as a relatively constant determining factor in the navigation module, is not affected by deformation, and calculates the second side length L in real time bc’ Then the real-time angle is obtained.

[0051] Exemplarily, a sensor is provided in the blade head of a dressing changing instrument such as an ultrasonic scalpel, and the sensor is movably provided in the splint of the blade head. The sensor is located on a rotatable splint and can cater to the positioning area. At the same time, the surface of the first splint is covered with an insulating layer. It is used to protect the sensor from interference from heat and current. An in vitro adjustment device is provided at the handle of the ultrasonic scalpel, and the doctor can control the adjustment device in vitro to adjust the position of the sensor on the blade head. The power cord of the sensor and the linkage line for adjusting the position of the sensor are arranged in the blade body and connected to the handle and the host. The sensor is connected to the sensor receiving unit, which transmits the signal to the ultrasonic scalpel control unit and then to the host. During the operation of the blade head in the electromagnetic field, the sensor sends a signal to capture the position information of the blade head in the magnetic field generated by the magnetic field generator, thereby presenting a visual position of the blade head.

[0052] During the operation, the laser distance measuring device simultaneously measures the first real-time positioning data, and L1 and L2 represent the distance between the marked point and the entry point in the triangular model and the distance between the entry point and the target point respectively. c' is defined as the deepest point where the end execution tool enters the dressing area, that is, any point from the entry point b to the target point c. The measured value of L1 is the first side length L ab , the measurement value of L2 is the second side length L bc’ The base point positioning target is fixed at the entry point b, and the operation tracking target is used to track the movement of the liver cutting instrument such as the ultrasonic knife in the L2 direction, so as to determine the real-time entry depth distance L bc’ .

[0053] The laser ranging device used can be fixed on the skin, but always keep it consistent with the section, avoid mutual interference during the positioning and data measurement of multiple feature points at the same time, reduce the influence of heat sources on magnetic positioning and magnetic fields on surgical instruments, use wireless source targets as much as possible, and merge wired source elements with instrument line sources, which is convenient for real-time measurement and not affected by deformation in three-dimensional space.

[0054] Laser distance measuring equipment can also be used to assist non-rigid registration. A laser distance measuring equipment is fixed at the entry point b. The L1 and L2 laser displacement sensors of the equipment point from point b to ba and bc respectively, and their angles are set to the angle α corresponding to point b before the operation. When the point b is resected to angle α, the laser emitted from this point can be presented on the cut surface. bc’ The laser beam emitted by laser L2 can be projected to the cutting point where the ultrasonic knife is located, and real-time measurement can be performed until L bc’ =L bc .

[0055] Non-rigid registration by electromagnetic field or laser ranging equipment complements and verifies each other. When the section deformation is large, the beam of the laser ranging equipment may be affected to a certain extent, resulting in deviations in measurement accuracy, which requires verification by electromagnetic coordinate measurement. When the patient's position needs to change frequently and the deformation of the dressing area is large, the electromagnetic coordinates may be displaced. At this time, the use of laser ranging can correct the deviation. Therefore, the combination of the two methods can achieve the most accurate measurement and implement precise navigation according to the preoperative plan.

[0056] During the dressing change operation, the optical imaging unit of the information calibration module continues to monitor the changes in the wound and the position of the robotic arm. The path adjustment unit of the navigation module dynamically adjusts the navigation path by comparing the real-time depth data with the triangulated model, thereby outputting navigation data to adjust the operating depth of the robotic arm to ensure the accuracy and safety of the entire operation process.

[0057] The path conversion unit is used to generate navigation data according to the navigation path, so as to control the robot arm operation module to generate robot arm control instructions according to the navigation data, and control the robot arm and the end execution tool to perform predetermined operations.

[0058] Based on the same inventive idea, such as Figure 3 As shown, the present application also provides a dressing change surgical robot equipped with the above-mentioned operating system and a robotic arm operating module. The robotic arm operating module includes a robotic arm 1, an end effector 2, and a scanning detection tool. The robotic arm uses joints with a certain degree of freedom to form the main body of the robot, and controls the joints and the end effector to complete the dressing change operation according to the robotic arm control instructions. The scanning detection tool is used to detect the working range of the robotic arm operating module, determine the dressing change area, and monitor the entire process of the end effector operation in real time to perform quality control of the entire process. When it is found that there is an error between the dressing change area and the operating area of ​​the end effector, or when the end effector is operated improperly, timely feedback is provided.

[0059] When the dressing robot is operating, the deformation of the dressing area, the deviation of the end-effector in the magnetic field, and the magnetic field interference in the external environment will all cause certain interference. The scanning detection tool also monitors the external environment and performs real-time verification when external interference is found, so as to timely detect deviations and calibrate. Real-time scanning can detect these abnormalities in time and provide timely feedback. Manual intervention or the navigation module can update the triangulation model in time and dynamically adjust the navigation data.

[0060] The end effector can be fixed to the end of the robotic arm, including conversion components and dressing instruments such as pliers, forceps, scissors, and closed pipe devices to complete the instruments required for incision, hemostasis, clamping, suturing, and other operations. The switching of instruments is completed by a switching component. The instrument of the end effector has a built-in sensor. After the switching component completes the instrument switching, the instrument is located at the designated working position, and the built-in sensor is turned on. The information calibration module and the navigation module can receive the signal from the built-in sensor of the instrument in real time to determine the location information. In addition, the end effector can also be provided with a trigger feedback component, which builds a feedback mechanism through visual, tactile, pressure, temperature and other measurement sensors, and judges or triggers the simulation of surgical tools through AI models.

[0061] The dressing change robot also includes a dressing change transport module 3, which includes a dressing change unit and a transport component; the robotic arm operation module is mounted on the platform of the dressing change unit, and the dressing change unit is provided with a clean area for placing unused tools and a contaminated area for placing used tools; the transport component is used to move the robotic arm to the designated position for dressing change.

[0062] In some embodiments, the transport component uses a dressing change vehicle, and the vehicle body is provided with a plurality of storage boxes for placing different disinfection instruments, auxiliary materials and different external liquids. After acquiring the navigation data, the robot arm operation module converts it into a robot arm control instruction, controls the robot arm located on the platform to move according to the navigation data, completes the dressing change operations such as switching the end effector, dressing change, disinfection, cutting sutures, and placing the used dressing change tools in the contaminated area.

[0063] The dressing robot determines the imaging data through the information calibration module, calculates the surface area and depth of the dressing area, and outputs the navigation data through the navigation module. The robotic arm takes the corresponding items from the dressing box of the dressing vehicle according to the navigation data, moves to the dressing area, and completes the designated dressing operation. In this process, if the patient moves or shifts, but the marking point remains unchanged, the relative distance between the end effector and the entry point remains unchanged, which does not affect the execution of the navigation data.

[0064] The present invention provides a dressing change navigation system and a dressing change robot. By constructing a triangular model and combining rigid and non-rigid registration, the dressing change path is adjusted in real time to ensure that even if the organ is displaced and deformed during the dressing change process, the dressing change robot can accurately operate along the optimal path, avoid the uncontrollable factors randomly generated during the operation, significantly improve the accuracy and safety of the dressing change path, reduce damage to healthy tissues, reduce the risk of dressing change, improve surgical efficiency, and improve the patient's postoperative recovery effect.

[0065] The embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without paying creative labor.

[0066] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0067] Finally, it should be noted that the embodiments disclosed in the present invention are only preferred embodiments of the present invention, which are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A dressing change navigation system, characterized in that: include: An information calibration module, used to obtain imaging data of the wound, generate and rigidly calibrate feature points, and calculate the surface treatment range and depth treatment range of the dressing change area according to the feature points; A navigation module generates a navigation path according to the feature points and the wound surface treatment range and depth treatment range; Real-time monitoring of the dressing change area, non-rigid calibration through triangulation, dynamic adjustment of the navigation path, and generation of navigation data.

2. A dressing change navigation system according to claim 1, characterized in that: The information calibration module includes a depth processing unit, which determines the two-dimensional contour of the dressing change area according to the imaging data and the feature points; obtains the laser ranging depth of the dressing change area, and determines the depth range of the dressing change area.

3. A dressing change navigation system according to claim 2, characterized in that: The navigation module includes a path adjustment unit, which performs non-rigid calibration through triangulation and dynamically adjusts the navigation path, including: Construct a triangular model in the dressing change area; the triangular model includes a marking point, a target point, an entry point and a planned angle; the marking point and the entry point are located on the curved surface where the incision of the dressing change area is located, and the distance between the target point and the marking point is the laser ranging depth; Acquire the first real-time positioning data, the second real-time positioning data and the third real-time positioning data to form triangulated positioning data; the first real-time positioning data is the real-time entry distance of the end-effector in the dressing change area; the second real-time positioning data is the positioning data of the entry point; the third real-time positioning data is the positioning data of the marking point; Determine the real-time angle through triangulation data; The navigation path is dynamically adjusted according to the real-time angle, the planned angle and the first real-time positioning data.

4. A dressing change navigation system according to any one of claims 1 to 3, characterized in that: The information calibration module includes a feature point recognition unit, which processes the imaging data of the dressing change area through an AI feature point recognition model in combination with a medical dressing change picture, and identifies feature points of the imaging data, wherein the feature points include one or more of the following: the boundary, depth, and suture range of the dressing change area.

5. A dressing change navigation system according to claim 4, characterized in that: The information calibration module includes a surface processing unit, which identifies a dressing change area boundary according to a feature point recognition unit and calculates the area of ​​the curved surface where the dressing change area is located by using a curved surface area calculation formula.

6. A dressing change navigation system according to claim 5, characterized in that: The information calibration module also includes an optical imaging unit for acquiring imaging data and laser ranging data; the imaging data includes a plurality of marking points, each of which is arranged at the boundary of the dressing change area to form a marking surface; the surface processing unit calculates the area of ​​the marking surface where the dressing change area is located through the marking points.

7. A dressing changing robot, characterized in that: It comprises a dressing change navigation system and a robotic arm operation module as described in any one of claims 1 to 6, wherein the robotic arm operation module outputs a robotic arm control instruction according to the navigation data output by the navigation module, and the robotic arm operation module comprises a robotic arm and an end effector tool, and controls the robotic arm and the end effector tool to perform a dressing change operation according to the robotic arm control instruction.

8. A dressing changing robot as claimed in claim 7, characterized in that: It also includes a dressing change transport module, which includes a dressing change unit and a transport component; the robotic arm operation module is mounted on the platform of the dressing change unit, and the dressing change unit is provided with a clean area for placing unused tools and a contaminated area for placing used tools; the transport component is used to move the robotic arm to the designated position for dressing change.

9. A dressing changing robot as claimed in claim 8, characterized in that: The robotic arm includes a scanning detection device, which is used to detect the working range of the robotic arm operation module, determine the operation area, and monitor the dressing change process of the end-effector tool in real time.

10. The dressing changing robot according to claim 8, characterized in that: The end effector tool comprises a switching assembly and one or more of the following instruments: pliers, tweezers, and scissors; the end effector tool has a built-in sensor in the instrument.

Images