Intelligent control method and system for oral surgery robot

Abstract

The application relates to the technical field of medical devices, and discloses an intelligent control method and system for a transoral surgery robot, the system comprising a laryngoscope support module, a lens module and a control module, the laryngoscope support module comprising a support body and a tongue depressor, the support body and the tongue depressor being internally provided with an endoscope channel and a device channel, and the side of the tongue depressor in contact with a tongue body being integrated with a pressure detection unit; the lens module comprising an endoscope, a third field lens and a lens cleaning assembly, the lens cleaning assembly comprising a nozzle for cleaning the endoscope and the third field lens; and the control module being in communication connection with the laryngoscope support module and the lens module. The various functional modules of the application realize integrated transoral surgery auxiliary control with the functions of sensing, control, self-cleaning and intelligent cooperative collision avoidance, and overcome the defects of low automation, single function and easy interruption of operation of the existing transoral surgery auxiliary system.

Description

Technical Field

[0001] This application relates to the field of medical device technology, and in particular to an intelligent control method and system for a transoral surgical robot. Background Technology

[0002] Transoral surgery is a minimally invasive surgical technique that enters the pharynx through the natural oral cavity. In practice, the surgical area is deep and narrow, relying primarily on a laryngoscope stent to hold the tongue in place for exposure. Traditionally, the stent is manually adjusted by the surgeon's experience. Insufficient support or poor positioning can obstruct the surgical field or lead to unstable exposure. Blood, tissue fluid, fumes from electrocoagulation or lasers, and endoscope fogging due to temperature differences can rapidly contaminate the endoscope lens, causing blurred vision. Traditional methods require completely removing the endoscope from the passage for wiping or rinsing, severely disrupting the surgical rhythm and affecting efficiency and safety. Furthermore, instruments and the lens are highly susceptible to collision, entanglement, or mutual obstruction, posing risks of instrument damage, lens damage, or accidental tissue injury.

[0003] Currently, some surgical robots or assistive systems have attempted to solve some of the above problems, but most of them focus on a single function and lack linkage between systems, resulting in a limited degree of automation. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent control method and system for a transoral surgical robot to improve the above-mentioned problems in the prior art.

[0005] For the purposes mentioned above, this application provides the following technical solution:

[0006] The first aspect of this application provides an intelligent control system for a transoral surgical robot, comprising:

[0007] The laryngoscope support module includes a support body and a tongue depressor. The support body and the tongue depressor are connected. An endoscope channel and an instrument channel are provided through the interior of the support body and the tongue depressor. A pressure detection unit is integrated on the side of the tongue depressor that contacts the tongue.

[0008] The lens module includes an endoscope and a lens cleaning assembly. The endoscope is movably disposed inside the endoscope channel, and the lens cleaning assembly is integrated into the endoscope channel outlet side of the tongue depressor.

[0009] The control module is used to communicate with the laryngoscope support module and the lens module respectively.

[0010] Furthermore, the lens module also includes a third field of view lens, which is fixedly mounted on the tongue depressor and has a preset positional relationship with the endoscope.

[0011] Furthermore, the lens cleaning assembly includes a cleaning channel and a nozzle. The cleaning channel is integrated inside the laryngoscope support module. The nozzle is connected to one end of the cleaning channel and fixed to the tongue depressor. The cleaning channel includes a gas channel and a liquid channel. The spray area of ​​the nozzle covers the initial position of the endoscope and the position of the third field of view lens, respectively.

[0012] Furthermore, the tongue depressor includes a pressure plate and a base. The pressure plate is rotatably connected to the base via a connector, and the pressure plate can rotate relative to the base in a vertical or horizontal direction.

[0013] Furthermore, both the endoscope and the third field-of-view lens are flexible lenses.

[0014] The second aspect of this application provides an intelligent control method for a transoral surgical robot, comprising:

[0015] Obtain pressure distribution data between the tongue depressor and the tongue, and obtain the result values ​​of preset support state indicators based on the pressure distribution data. The support state indicators include static support state indicators and dynamic support state indicators.

[0016] The system acquires real-time images from the lens module and performs image recognition on the real-time images to obtain the result values ​​of preset visual state indicators. The lens module includes an endoscope and a third field of view lens, and the real-time images include real-time images from the endoscope and real-time images from the third field of view lens.

[0017] By combining the results of the support status index and the results of the visual status index, a preset adjustment strategy is matched to adjust the tongue depressor and the endoscope, wherein the adjustment priority of the tongue depressor is higher than that of the endoscope.

[0018] Furthermore, the method also includes:

[0019] The system monitors the real-time images, identifies the type and degree of contamination of the lens module based on the real-time images, and determines whether a preset first cleaning trigger condition has been met.

[0020] If the first cleaning trigger condition is met, the lens module is controlled to perform a preset pose compensation movement. During or after the pose compensation movement, the lens cleaning component is controlled to perform a cleaning operation on the lens module, including ventilation pulses and / or water pulses, according to the cleaning strategy corresponding to the type of contamination.

[0021] Furthermore, the method also includes:

[0022] Establish a mapping rule base for each surgical operation and each cleaning trigger condition. The mapping rule base includes multiple mapping relationships between the surgical operations, the cleaning trigger conditions, and the cleaning strategies.

[0023] The current surgical operation is acquired in real time, and a matching search is performed from the mapping rule base based on the current surgical operation to determine whether the second cleaning trigger condition is met.

[0024] If the second cleaning trigger condition is met, the cleaning strategy corresponding to the second cleaning trigger condition is executed, and the lens cleaning component is controlled to perform a cleaning operation on the lens module including ventilation pulses and / or water pulses.

[0025] Furthermore, the method also includes:

[0026] The third field of view image, which includes surgical instruments and the endoscope, is obtained through the third field of view lens. Both the surgical instruments and the endoscope in the third field of view image are marked with visual symbols.

[0027] Identify the visual markers and calculate the first and second poses of the surgical instruments and the endoscope in the coordinate system of the third field of view lens, respectively;

[0028] Based on the pre-defined coordinate transformation relationship, the first pose is converted into the third pose in the global coordinate system and the second pose is converted into the fourth pose in the global coordinate system, respectively.

[0029] Based on the third and fourth poses, the collision risk between the surgical instrument and the endoscope is predicted in real time. If the collision risk exceeds a preset threshold, the surgical instrument and / or the endoscope are controlled to perform an avoidance operation.

[0030] Furthermore, the control of the surgical instruments and / or the endoscope to perform obstacle avoidance operations includes:

[0031] Determine and identify the main moving part of the surgical instrument and the endoscope: when the surgical instrument is the main moving part, adjust the direction of movement of the surgical instrument to bypass the endoscope; when the endoscope is the main moving part, control the endoscope to move in a preset safe direction to avoid the surgical instrument.

[0032] A third aspect of this application provides an electronic device, including: a processor 1102; and a memory 1101 for storing executable instructions of the processor 1102; wherein the processor 1102 is used for the instructions to implement an intelligent control method for a transoral surgical robot as described in the first aspect of this application.

[0033] The fourth aspect of this application provides a storage medium, which is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the intelligent control method for a transoral surgical robot described in the first aspect of this application.

[0034] The fifth aspect of this application provides a computer program product comprising a computer program that, when executed by a processor, implements the steps of an intelligent control method for a transoral surgical robot as described in the first aspect of this application.

[0035] The intelligent control system for the transoral surgical robot described above, as provided in this application, can achieve at least the following technical effects:

[0036] This application provides an auxiliary system that integrates a tongue pressure detection unit, a lens cleaning component, and a third field of view lens. It can automatically sense the support and field of view of the tongue root to achieve intelligent control of tongue pressure and endoscopic field of view during transoral surgery. It realizes integrated transoral surgery auxiliary control with sensing, control, self-cleaning, and intelligent collaborative collision avoidance, overcoming the defects of existing transoral surgery auxiliary systems such as low automation, single function, and easy interruption of operation. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0038] Figure 1 A schematic diagram of the overall structure of an intelligent control system for a transoral surgical robot provided in this application embodiment;

[0039] Figure 2 This is a schematic diagram of the installation structure of the laryngoscope support module provided in the embodiments of this application;

[0040] Figure 3 This is a schematic diagram of the laryngoscope support structure provided in an embodiment of this application;

[0041] Figure 4 This is a side view of the laryngoscope support structure described in an embodiment of this application;

[0042] Figure 5 This is a schematic diagram of the lens module structure described in an embodiment of this application;

[0043] Figure 6 This is a schematic diagram of the lens cleaning assembly structure described in an embodiment of this application;

[0044] Figure 7 This is a schematic diagram of the intelligent control method for a transoral surgical robot according to an embodiment of this application;

[0045] Figure 8 This is a schematic diagram of the fusion decision-making method described in the embodiments of this application;

[0046] Figure 9 This is a schematic diagram of the collision avoidance process described in the embodiments of this application;

[0047] Figure 10 This is a schematic diagram of the functional modules of an intelligent control system for a transoral surgical robot according to an embodiment of this application;

[0048] Figure 11 This is a schematic diagram of a computer device provided in an embodiment of this application.

[0049] Reference numerals: 100, Intelligent control system of a transoral surgical robot; 110, Laryngoscope support module; 111, Support body; 112, Tongue depressor; 113, Endoscope channel; 114, Instrument channel; 115, Pressure detection unit; 116, Pressure plate; 117, Base; 118, Rotating shaft; 119, Adjusting wire; 1191, Adjusting adapter; 120, Lens module; 121, Endoscope; 122, Lens cleaning assembly; 123, Nozzle; 124, Cleaning channel; 125, Valve; 126, Third field of view lens; 130, Endoscope support; 140, Robotic arm; 150, Endoscope holder; 160, Control module; 1101, Memory; 1102, Processor. Detailed Implementation

[0050] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] This application provides an intelligent control system 100 for a transoral surgical robot capable of automatically sensing tongue base support and visual field status, intelligently cleaning the lens, and achieving global collaborative collision avoidance of multiple instruments. Figure 1 and Figure 2 , Figure 3 and Figure 10 As shown, the intelligent control system 100 of the transoral surgical robot specifically includes:

[0052] The laryngoscope support module 110 includes a support body 111 and a tongue depressor 112. According to... Figure 1 ,Figure 3 and Figure 5 The support body 111 and the tongue depressor 112 are detachably connected, together forming a channel structure for entering the oral cavity. An endoscope channel 113 for the endoscope 121 and an instrument channel 114 for surgical instruments are internally connected to the support body 111 and the tongue depressor 112. A pressure detection unit 115 is integrated on the side of the tongue depressor 112 that contacts the tongue (i.e., the lower surface), used to sense the magnitude and distribution of contact pressure between the tongue depressor 112 and the tongue tissue in real time. This allows for automatic acquisition and maintenance of the optimal surgical field of view while ensuring a safe pressure threshold for the tissue, thus improving the visibility of key anatomical structures during transoral surgery.

[0053] Lens module 120 includes endoscope 121, third-view lens 126, and lens cleaning assembly 122, according to Figure 5 As shown. The endoscope 121 is movably disposed inside the endoscope channel 113 to provide the main field of view of the surgical area. The third field of view lens 126 is fixedly disposed on the tongue depressor 112 and maintains a preset positional relationship with the lens of the endoscope 121, so that the third field of view lens 126 can provide a global field of view including the outer section of the endoscope 121 and the outer section of the surgical instruments, realizing coordinated control during the surgical process. The lens cleaning assembly 122 is integrated on the endoscope channel 113 outlet side of the tongue depressor 112, and is used to clean the endoscope 121 and the third field of view lens 126 according to the controller instructions.

[0054] The control module 160 is communicatively connected to the laryngoscope support module 110 and the lens module 120, respectively, and is used to receive sensor data and image signals, perform analysis and decision-making, and output control commands.

[0055] Specifically, according to Figure 2 As shown, during transoral surgery, the endoscope 121 is first fixed inside the endoscope support 130. The laryngoscope support module 110 is mounted on the robotic arm 140, and the tongue depressor 112 is mounted on the support body 111. The endoscope 121 passes through the endoscope channel 113 that runs through the support body 111 and the tongue depressor 112, and is inserted into the patient's oral cavity to perform the surgery. The tongue depressor 112 is detachably connected to the support body 111 for easy replacement after use.

[0056] Furthermore, according to Figure 5 and Figure 6As shown, the lens cleaning assembly 122 includes a cleaning channel 124 and a nozzle 123. The cleaning channel 124 is integrated inside the laryngoscope support module 110. The nozzle 123 is connected to one end of the cleaning channel 124 and fixed to the tongue depressor 112. The cleaning channel 124 includes a gas channel and a liquid channel, and each cleaning channel 124 is provided with a valve 125 for adjusting the pulse volume. The spray area of ​​the nozzle 123 covers the initial position of the endoscope 121 and the position of the third field of view lens 126, respectively, so that the lens cleaning assembly 122 can clean both lenses simultaneously.

[0057] Furthermore, the tongue depressor 112 includes a pressure plate 116 and a base 117. The pressure plate 116 is rotatably connected to the base 117 via a connector, and the pressure plate 116 can rotate relative to the base 117 in a vertical or horizontal direction.

[0058] In this embodiment, preferably, according to Figure 3 and Figure 4 As shown, the pressure plate 116 is connected to the rotating shaft 118 fixed on the base 117 via an adjusting adapter 1191. Four sets of adjusting wires 119 are connected to the adjusting adapter 1191, including an upper adjusting wire 119, a lower adjusting wire 119, a left adjusting wire 119, and a right adjusting wire 119. One end of each of these four adjusting wires 119 is connected to the adjusting adapter 1191, and the other end is connected to a remote drive unit. The drive unit drives each adjusting wire 119 to achieve dual-degree-of-freedom rotation of the pressure plate 116 around the rotating shaft 118 of the base 117 in either the vertical or horizontal direction. The design of the adjusting wires 119 and the adjusting adapter 1191 allows the system to fine-tune the contact angle and area between the pressure plate 116 and the tongue without moving the entire laryngoscope support, thus optimizing the support effect.

[0059] Preferably, both the endoscope 121 and the third field of view lens 126 can be flexible lenses. Flexible lenses can better adapt to the curved paths inside the oral cavity, reduce pressure on tissues, and provide a more flexible field of view.

[0060] Preferably, the surgical instrument is movably disposed inside the instrument channel 114, and the surgical instrument is preferably a flexible instrument.

[0061] Based on the same inventive concept, this invention also provides an intelligent control method for a transoral surgical robot, as described in the following embodiments. Since the principle behind the problem-solving approach of the intelligent control method for a transoral surgical robot is similar to that of the intelligent control system 100 for a transoral surgical robot, the implementation of the intelligent control method for a transoral surgical robot can refer to the implementation of the intelligent control system 100 for a transoral surgical robot; repeated details will not be elaborated further.

[0062] Figure 7 This is a flowchart illustrating an implementation of an intelligent control method for a transoral surgical robot according to an embodiment of this application. The method specifically includes:

[0063] Step S100: Obtain pressure distribution data between the tongue depressor 112 and the tongue, and obtain the result values ​​of each preset support state index based on the pressure distribution data. The support state index includes static support state index and dynamic support state index.

[0064] Specifically, the surface of the tongue depressor 112 that contacts the tongue integrates a pressure detection unit 115, used to acquire pressure distribution data between the tongue depressor 112 and the tongue in real time. Multiple static and dynamic support state indicators are preset: static support state indicators reflect the instantaneous state, including average pressure, peak pressure, pressure distribution uniformity, and effective contact area; dynamic support state indicators reflect the state trend, including pressure change rate and slippage trend index. The result values ​​of each support state indicator are calculated based on the real-time acquired pressure distribution data.

[0065] Optionally, the pressure detection unit 115 includes a thin-film pressure array, strain gauge, FSR, micro force sensor, etc.

[0066] Step S200: Obtain the real-time image of the lens module 120, and perform image recognition on the real-time image to obtain the result values ​​of preset visual state indicators. The lens module 120 includes an endoscope 121 and a third field of view lens 126. The real-time image includes the real-time image of the endoscope 121 and the real-time image of the third field of view lens 126.

[0067] Specifically, according to Figure 8As shown, real-time images from endoscope 121 and third field of view lens 126 are acquired respectively. Real-time image recognition and analysis are performed by combining the real-time images to calculate the result values ​​of preset visual state indicators. For example, the visibility of target anatomical structures (such as the confidence level of target area recognition or key point detection, such as epiglottis / glottis / pharyngeal wall), the proportion of visual field occlusion (such as soft tissue occlusion area), image clarity (such as edge density, contrast, blur, etc.), and visual field stability (image jitter, drift) are evaluated for the images from endoscope 121; the relative position of the instrument and endoscope 121, the distance to the entrance boundary, etc. are evaluated for the real-time images from third field of view lens 126.

[0068] Step S300: Combining the result values ​​of the support state index and the visual state index, a preset adjustment strategy is matched to adjust the tongue depressor 112 and the endoscope 121, wherein the adjustment priority of the tongue depressor 112 is higher than that of the endoscope 121.

[0069] Specifically, by combining the results of various support status indicators and visual status indicators, a neural network model is used to make fusion decisions and generate posture adjustment commands for the tongue depressor 112 or the endoscope 121 to optimize the surgical field of view while ensuring tissue pressure safety. When executing the adjustment strategy, the adjustment priority of the tongue depressor 112 is higher than that of the endoscope 121. This means that when the field of view is poor, the system prioritizes improving exposure by fine-tuning the tongue depressor 112 (changing tongue root support) rather than directly moving the endoscope 121 to find a field of view. Only when the adjustment of the tongue depressor 112 has reached its limit or poses a risk (such as excessive pressure) is the posture adjustment of the endoscope 121 initiated. This avoids the risks that may arise from blind movement of the endoscope.

[0070] In step S300, the fusion decision results output by the model and their corresponding adjustment strategies mainly include the following types:

[0071] "Pressure Risk": At this point, the support status indicators show that the peak pressure exceeds the limit or the pressure distribution entropy is extremely low. The adjustment strategy is to control the pressure tongue plate 112 to quickly retract or rotate along the direction of pressure gradient descent to reduce the peak pressure. The field of view will be reassessed after the model evaluates the pressure safety.

[0072] "Insufficient support, limited field of vision": At this time, the support status indicator shows that the effective contact area is too small or the overall pressure is too low, and the visual indicator also shows that the target is lost or severely obstructed. The corresponding adjustment strategy is to control the tongue depressor 112 to compensate for the displacement, so as to increase the contact area and support with the tongue; while or after the tongue depressor 112 is adjusted, the endoscope 121 is controlled to search or refocus to regain the target field of vision.

[0073] "Stable support, field of view shifted": At this point, all support status indicators are within a safe and good range, but the visual status indicators show that the target anatomical structure is not in the center of the image (there is a shift). The corresponding adjustment strategy is to control the endoscope 121 to translate or rotate, adjusting the target to the optimal field of view area (such as the center).

[0074] "Support uneven load, field of view acceptable": At this point, the support status indicators show a significant uneven pressure distribution (high degree of uneven load), but key field of view indicators (such as target visibility and clarity) are still acceptable. The adjustment strategy is to control the tongue depressor 112 to rotate finely around its axis to make the pressure distribution more even. Since the rotation of the tongue depressor 112 may cause slight changes in the field of view, the endoscope 121 is simultaneously controlled to make reverse fine adjustments to maintain the target's position in the image.

[0075] "Slippage risk, visual shaky": At this time, the support status indicator shows that the pressure center is continuously moving (high slippage trend), and the visual status indicator shows that the image is shaking or drifting. The corresponding adjustment strategy is to control the tongue depressor 112 to make a slight displacement in the opposite direction of slippage, while controlling the endoscope posture to make active reverse movement compensation to counteract the remaining shaking.

[0076] "Ideal state, dynamically maintained": At this point, all key support and visual status indicators are within the preset ideal range. Control the tongue depressor 112 and endoscope 121 to enter the position maintenance state and maintain real-time monitoring.

[0077] Furthermore, step S200 also includes:

[0078] Step S210: Monitor the real-time image in real time, identify the type and degree of contamination of the lens module 120 based on the real-time image, and determine whether the preset first cleaning trigger condition has been met;

[0079] Step S220: If the first cleaning trigger condition is met, the lens module 120 is controlled to perform a preset pose compensation movement. During or after the pose compensation movement, the lens cleaning component 122 is controlled to perform a cleaning operation on the lens module 120, including ventilation pulses and / or water pulses, according to the cleaning strategy corresponding to the type of contamination.

[0080] Specifically, the lens cleaning assembly 122 includes a nozzle 123 and a cleaning channel 124 (including a gas channel and a liquid channel) connected to the nozzle 123. The spray area of ​​the nozzle 123 covers the initial position of the endoscope 121 and the position of the third field of view lens 126, respectively. Based on the real-time image, image analysis (such as sharpness calculation, edge detection, and color analysis) is performed to identify the type (such as blood, tissue fluid, smoke, and condensation) and degree of lens contamination. If the first cleaning trigger condition, i.e., the degree of contamination, exceeds a preset threshold, the corresponding cleaning strategy is activated according to the type of contamination. Each cleaning strategy controls the lens cleaning assembly 122 to perform ventilation pulses and / or water pulses, and the corresponding pulse durations, based on different contamination types. Optionally, the cleaning operation includes: brief ventilation pulses to disperse smoke or dry droplets, water pulses to rinse blood stains, and a combination sequence of "ventilation-water-ventilation," etc. Before performing the cleaning operation, the system first controls the endoscope 121 to perform a preset pose compensation movement so that the position of the endoscope lens is within the spraying range of the nozzle 123 in the lens cleaning assembly 122. Since the third field of view lens 126 is fixed to one side of the endoscope 121 on the tongue depressor 112, cleaning can be performed without movement. This embodiment achieves "cleaning without interrupting observation" through the above self-cleaning process, greatly improving the smoothness of the surgery.

[0081] Furthermore, in step S210 above, after identifying the type and degree of contamination of the lens module 120 based on the real-time image, the method further includes:

[0082] Step S211: Establish a mapping rule base for each surgical operation and each cleaning trigger condition. The mapping rule base includes multiple mapping relationships between the surgical operations, the cleaning trigger conditions, and the cleaning strategies.

[0083] Step S212: Obtain the current surgical operation in real time, and perform a matching search from the mapping rule base based on the current surgical operation to determine whether the second cleaning trigger condition is met;

[0084] Step S213: If the second cleaning trigger condition is met, the cleaning strategy corresponding to the second cleaning trigger condition is executed, and the lens cleaning component 122 is controlled to perform a cleaning operation on the lens module 120 including ventilation pulses and / or water pulses.

[0085] Furthermore, the self-cleaning process provided in this embodiment also includes predictive cleaning based on different surgical operations. That is, a mapping relationship is pre-built and stored between different surgical operations (such as "initiation of electrocoagulation hemostasis," "tissue cutting in progress," and "high smoke generation") and corresponding second cleaning trigger conditions and cleaning strategies. The system acquires the currently planned surgical operation in real time; based on the current operation, it searches for a matching item in the mapping rule base to determine whether it is a specific surgical operation corresponding to the second cleaning trigger condition. If so, the corresponding cleaning strategy is executed to ensure that each lens is in optimal visual condition. The cleaning strategies include different combinations of sequences such as ventilation pulses, water pulses, and "ventilation-water-ventilation."

[0086] For example, if the current surgical procedure is a hemostasis or cutting operation, the corresponding cleaning strategy is executed. The cleaning strategy also includes dosage control, namely water volume, gas volume, pulse frequency, and duration, and can be adaptive according to the type of contamination (different strategies are adopted for mist / blood / fume).

[0087] Furthermore, according to Figure 9 As shown, the method further includes:

[0088] Step S400: Obtain a third field of view image with surgical instruments and endoscope 121 through the third field of view lens 126. In the third field of view image, both the surgical instruments and endoscope 121 are marked with visual markers.

[0089] Step S500: Identify the visual markers and calculate the first pose and second pose of the surgical instruments and the endoscope 121 in the coordinate system of the third field of view lens 126 respectively;

[0090] Step S600: Based on the pre-calibrated coordinate transformation relationship, the first pose is converted into the third pose in the global coordinate system and the second pose is converted into the fourth pose in the global coordinate system, respectively.

[0091] Step S700: Based on the third pose and the fourth pose, predict the collision risk between the surgical instrument and the endoscope 121 in real time. If the collision risk exceeds a preset threshold, control the surgical instrument and / or the endoscope 121 to perform an avoidance operation.

[0092] Specifically, a third field of view image containing the surgical instruments and the outer segment of the endoscope 121 is continuously acquired via a third field of view lens 126 fixed to the tongue depressor 112. The surgical instruments are movably disposed within the instrument channel 114 inside the laryngoscope support. To facilitate tracking, high-contrast visual markers (such as color rings, reflective dots, or specific patterns) are provided at specific locations on the outer segments of the surgical instruments and the endoscope 121 for image recognition to distinguish the endoscope 121 from the surgical instruments. During the synchronous control of the surgical instruments and the endoscope 121, the visual markers in the third field of view image are identified, and computer vision algorithms are used to calculate the first and second poses of the surgical instruments and the endoscope 121 in the coordinate system of the third field of view lens 126, respectively.

[0093] The system determines the coordinate transformation relationship between the global coordinate system and the coordinate system of the third field-of-view lens 126 based on the positional relationship between the coordinate system of the third field-of-view lens 126 and the various structural components of the system. Based on the predetermined coordinate transformation relationship, the first pose is converted into a third pose in the global coordinate system, and the second pose is converted into a fourth pose in the global coordinate system. The third pose represents the position information of the surgical instrument in the global coordinate system, and the fourth pose represents the position information of the endoscope 121 in the global coordinate system. Based on the above third and fourth poses, the minimum distance between the surgical instrument and the endoscope 121 is calculated in real time, and combined with their movement speed and direction, the collision risk in the near future (e.g., 200-500ms) is predicted. If the collision risk exceeds a preset threshold, the surgical instrument and / or the endoscope 121 are controlled to perform an avoidance operation to prevent a collision.

[0094] Further, in step S700, controlling the surgical instrument and / or the endoscope 121 to perform an avoidance operation includes: determining and identifying the main moving body in the surgical instrument and the endoscope 121; when the surgical instrument is the main moving body, adjusting the movement direction of the surgical instrument to bypass the endoscope; when the endoscope 121 is the main moving body, controlling the endoscope 121 to move in a preset safe direction to avoid the surgical instrument.

[0095] Specifically, the avoidance operation employs the following logic: the component currently performing the main operation and being controlled (endoscope 121 or surgical instrument) is defined as the primary moving part, with higher priority for its movement path. When the surgical instrument is identified as the primary moving part, the avoidance strategy is to adjust the end-effector trajectory of the surgical instrument to "bypass" the stationary or slow-moving endoscope 121 via a more optimized path, minimizing interruption of the main operation. When the endoscope 121 is identified as the primary moving part (e.g., actively adjusting the endoscope's viewing angle), the avoidance strategy is to control the endoscope 121 to make a rapid, small displacement in a preset safe direction (e.g., upward or sideways), actively avoiding the working path of the surgical instrument. Through the global coordination and avoidance mechanism of steps S400~S700, as well as coordinate transformation and collision prediction algorithms, potential collision risks can be warned in advance, and avoidance strategies can be intelligently executed according to the priority of the primary and secondary components, effectively reducing the collision risk between instruments and lenses and improving the safety and smoothness of multi-instrument collaborative operation.

[0096] In some embodiments, the above-mentioned avoidance strategy further includes: applying virtual wall / virtual spring constraints to the instrument and endoscope lens, and limiting, redirecting or scaling the command when there is a risk of collision.

[0097] In some embodiments, the third field-of-view lens 126 can also be used for "optimal coordination," such as the lens automatically maintaining an observation position that does not obstruct the instrument's trajectory, and the instrument maintaining a working posture within the lens's field of view.

[0098] In this embodiment, an electronic device is also provided, such as... Figure 11 As shown, it includes: a processor 1102; a memory 1101 for storing executable instructions of the processor 1102; wherein the processor 1102 is used for the instructions to implement an intelligent control method for a transoral surgical robot as described above in this embodiment.

[0099] Specifically, the computer device can be a computer terminal, a server, or a similar computing device.

[0100] In this embodiment, a storage medium is provided, which is a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by a processor, it implements the intelligent control method of the transoral surgical robot described above in this embodiment.

[0101] In this embodiment, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the intelligent control method for a transoral surgical robot described above in this embodiment.

[0102] In this embodiment, a computer-readable storage medium is provided, which stores a computer program that executes any of the above-described intelligent control methods for a transoral surgical robot.

[0103] Specifically, computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, and optical disc read-only memory (CD-ROM). ROM, digital multifunction optical disc (DVD) or other optical storage, magnetic cassette tape, magnetic disk storage or other magnetic storage devices or any other non-transfer media, may be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0104] The embodiments of the present invention achieve the following technical effects:

[0105] 1. This application monitors the tongue root support status in real time by integrating a pressure detection unit into the tongue depressor. Combined with the visual assessment of the endoscopic field of view, the system can intelligently determine whether the support is good, whether there is a risk of compression or insufficient exposure. Under the premise of ensuring the tissue safety pressure threshold, it can automatically obtain and maintain the best surgical field of view and improve the visibility of key anatomical structures in transoral surgery.

[0106] 2. This application integrates the lens cleaning component into one side of the lens module of the tongue depressor, and combines an image recognition-based contamination detection method with a prediction logic based on the surgical stage to achieve adaptive cleaning of the lens during the operation, ensuring that the cleaning operation does not affect the observation of the surgical area and significantly improving surgical efficiency.

[0107] 3. This application sets up a third field of view lens to monitor the real-time position and pose of the instrument and the outer segment of the endoscope, and predicts the collision risk between the instrument and the endoscope. Based on the magnitude of the collision risk, it executes an intelligent obstacle avoidance strategy, thereby providing a closed-loop collaborative system of "third field of view - position tracking - collaborative constraint - collision prediction / suppression", which further improves surgical efficiency.

[0108] 4. This application provides a transoral surgical auxiliary control system that integrates support adjustment, cleaning triggering, collision avoidance planning and multiple actuators. The functional modules share data and make decisions in a coordinated manner, realizing full-process automation and intelligence from "perception-analysis-decision-execution".

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. An intelligent control system for a transoral surgical robot, characterized in that, include: The laryngoscope support module (110) includes a support body (111) and a tongue depressor (112). The support body (111) and the tongue depressor (112) are connected. An endoscope channel (113) and an instrument channel (114) are provided through the interior of the support body (111) and the tongue depressor (112). A pressure detection unit (115) is integrated on the side of the tongue depressor (112) that contacts the tongue. The lens module (120) includes an endoscope (121) and a lens cleaning assembly (122). The endoscope (121) is movably disposed inside the endoscope channel (113). The lens cleaning assembly (122) is integrated on the endoscope channel (113) outlet side of the tongue depressor (112). The lens module (120) also includes a third field of view lens (126). The third field of view lens (126) is fixedly disposed on the tongue depressor (112) and has a preset positional relationship with the endoscope (121). The control module (160) is used to communicate with the laryngoscope support module (110) and the lens module (120) respectively; The system is also used to acquire pressure distribution data between the tongue depressor (112) and the tongue, and to acquire the result values ​​of preset support state indicators based on the pressure distribution data. The support state indicators include static support state indicators and dynamic support state indicators. The real-time image of the lens module (120) is acquired, and the real-time image is subjected to image recognition to obtain the result values ​​of preset visual state indicators. The real-time image includes the real-time image of the endoscope (121) and the real-time image of the third field of view lens (126). By combining the results of the support status index and the results of the visual status index, a preset adjustment strategy is matched to adjust the tongue depressor (112) and the endoscope (121), wherein the adjustment priority of the tongue depressor (112) is higher than the adjustment priority of the endoscope (121). A third field of view image containing surgical instruments and the endoscope (121) is obtained through the third field of view lens (126), wherein the surgical instruments and the endoscope (121) in the third field of view image are both marked with visual markers; Identify the visual markers and calculate the first and second poses of the surgical instruments and the endoscope (121) in the coordinate system of the third field of view lens (126); Based on the pre-defined coordinate transformation relationship, the first pose is converted into the third pose in the global coordinate system and the second pose is converted into the fourth pose in the global coordinate system, respectively. Based on the third and fourth poses, the collision risk between the surgical instrument and the endoscope (121) is predicted in real time. If the collision risk exceeds a preset threshold, the surgical instrument and / or the endoscope (121) are controlled to perform an avoidance operation.

2. The intelligent control system for a transoral surgical robot according to claim 1, characterized in that, The lens cleaning assembly (122) includes a cleaning channel (124) and a nozzle (123). The cleaning channel (124) is integrated inside the laryngoscope support module (110). The nozzle (123) is connected to one end of the cleaning channel (124) and fixed to the tongue depressor (112). The cleaning channel (124) includes a gas channel and a liquid channel. The spray area of ​​the nozzle (123) covers the initial position of the endoscope (121) and the position of the third field of view lens (126), respectively.

3. The intelligent control system for a transoral surgical robot according to claim 1, characterized in that, The tongue depressor (112) includes a pressure plate (116) and a base (117). The pressure plate (116) is connected to the rotating shaft (118) on the base (117) via an adjustment adapter (1191). The adjustment adapter (1191) is connected to an upper adjustment wire, a lower adjustment wire, a left adjustment wire, and a right adjustment wire, respectively. A remote drive unit is connected to drive each adjustment wire so that the pressure plate (116) can rotate around the rotating shaft (118) of the base (117) in a vertical or horizontal direction.

4. The intelligent control system for a transoral surgical robot according to claim 1, characterized in that, Both the endoscope (121) and the third field of view lens (126) are flexible lenses.

5. The intelligent control system for a transoral surgical robot according to claim 1, characterized in that, The system is also used for: The real-time image is monitored in real time, and the type and degree of contamination of the lens module (120) are identified based on the real-time image, and it is determined whether the preset first cleaning trigger condition has been met. If the first cleaning trigger condition is met, the lens module (120) is controlled to perform a preset pose compensation movement. During or after the pose compensation movement, the lens cleaning component (122) is controlled to perform a cleaning operation on the lens module (120) including ventilation pulses and / or water pulses according to the cleaning strategy corresponding to the type of contamination.

6. The intelligent control system for a transoral surgical robot according to claim 5, characterized in that, The method of identifying the type and degree of contamination of the lens module (120) based on the real-time image also includes: Establish a mapping rule base for each surgical operation and each cleaning trigger condition. The mapping rule base includes multiple mapping relationships between the surgical operations, the cleaning trigger conditions, and the cleaning strategies. The current surgical operation is acquired in real time, and a matching search is performed from the mapping rule base based on the current surgical operation to determine whether the second cleaning trigger condition is met. If the second cleaning trigger condition is met, the cleaning strategy corresponding to the second cleaning trigger condition is executed, and the lens cleaning component (122) is controlled to perform a cleaning operation on the lens module (120) including ventilation pulses and / or water pulses.

7. The intelligent control system for a transoral surgical robot according to claim 1, characterized in that, The control of the surgical instruments and / or the endoscope (121) to perform avoidance maneuvers includes: Determine and identify the main moving body in the surgical instrument and the endoscope (121): when the surgical instrument is the main moving body, adjust the movement direction of the surgical instrument to bypass the endoscope (121); when the endoscope (121) is the main moving body, control the endoscope (121) to move in a preset safe direction to avoid the surgical instrument.

Images