An intelligent assisted positioning and navigation method and system for a surgical manipulator

Abstract

This application relates to the technical field of manipulator positioning and navigation processing, and specifically relates to an intelligent auxiliary positioning and navigation method and system for a surgical manipulator. It obtains the search space for manipulator positioning and navigation; obtains the selection probability of moving from the current discrete point to the next discrete point according to the change in the movement path parameters between the current discrete point and the previous discrete point; uses the roulette wheel algorithm to obtain the selection result of the next discrete point based on the selection probability of moving from the current discrete point to the next discrete point; updates the pheromone concentration of the next discrete point; obtains the neighborhood concentration difference degree of the next discrete point; and optimizes the ant colony algorithm iteration process according to the neighborhood concentration difference degree of the next discrete point by updating the pheromone concentration of the next discrete point, thereby completing the positioning and navigation of the manipulator path. This application aims to improve the reliability of using intelligent auxiliary positioning and navigation of surgical manipulators.

Description

Technical Field

[0001] This application relates to the technical field of robotic positioning and navigation processing, and particularly to an intelligent assisted positioning and navigation method and system for a surgical robot. Background Art

[0002] Surgical operations are complex and precise medical procedures that place very high demands on doctors. In traditional surgical operations, doctors mainly rely on experience and intuition for surgical navigation and positioning, but this often poses certain risks and errors. The intelligent assisted positioning and navigation technology of robotic arms can help surgeons with different levels of experience perform precise surgeries, provide more accurate surgical navigation and positioning, reduce the influence of human factors during surgeries, improve surgical accuracy and safety, reduce the risks of errors and complications during surgeries, and lower the surgical accident rate. At the same time, it can also provide doctors with real-time intraoperative guidance and feedback to help doctors make better decisions.

[0003] The intelligent assisted positioning and navigation system of robotic arms is an important technological innovation in the field of surgical operations. It provides powerful tools and support for surgeons, enabling them to better complete complex surgical operations and improve the surgical outcome and the patient's treatment experience. When using the ant colony algorithm to handle path planning problems, since existing path planning algorithms are all for handling two-dimensional path planning problems, due to the complexity of three-dimensional path planning, there is no relatively unified, suitable, and specific algorithm for the intelligent assisted positioning and navigation of robotic arms when dealing with three-dimensional path planning problems. Therefore, this application uses an improved two-dimensional ant colony algorithm to complete path planning for the above problems. Summary of the Invention

[0004] To solve the above technical problems, this application provides an intelligent assisted positioning and navigation method and system for a surgical robot, and the specific technical solutions adopted are as follows:

[0005] In the first aspect, an embodiment of this application provides an intelligent assisted positioning and navigation method for a surgical robot, and this method includes the following steps:

[0006] Obtain the search space for robotic positioning and navigation;

[0007] Obtain the security factors of each discrete point in the search space; for the current discrete point in the iterative process of the ant colony algorithm, obtain the fitness value of the current discrete point moving to the next discrete point according to the change in the movement path parameters between the current discrete point and the previous discrete point; obtain the heuristic function of the current discrete point moving to the next discrete point according to the fitness value of the current discrete point moving to the next discrete point and the security factor of the current discrete point moving to the next discrete point; obtain the selection probability of the current discrete point moving to the next discrete point according to the heuristic function of the current discrete point moving to the next discrete point; use the roulette wheel algorithm to obtain the selection result of the next discrete point for the selection probability of the current discrete point moving to the next discrete point;

[0008] Update the pheromone concentration of the next discrete point according to the heuristic function of the current discrete point moving to the next discrete point; use the clustering algorithm to cluster the pheromone concentrations of all discrete points in the search space to obtain each clustering cluster; obtain the neighborhood concentration difference degree of the next discrete point; obtain the concentration dilution coefficient of the next discrete point according to the neighborhood concentration difference degree of the next discrete point; update the pheromone concentration of the next discrete point according to the concentration dilution coefficient of the next discrete point to complete the optimization of the iterative process of the ant colony algorithm; use the ant colony algorithm to complete the positioning and navigation of the manipulator path.

[0009] Preferably, the obtaining of the security factors of each discrete point in the search space includes:

[0010] For each discrete point in the search space, take any discrete point as the current discrete point, construct the neighborhood matrix of the current discrete point as the security factor of the current discrete point, mark the discrete points with the same gray value as the current discrete point in the security factor of the current discrete point as 1, and the rest as 0.

[0011] Preferably, the obtaining of the fitness value of the current discrete point moving to the next discrete point according to the change in the movement path parameters between the current discrete point and the previous discrete point includes:

[0012] Obtain the angular value of the angle formed by the movement paths of the previous discrete point moving to the current discrete point and the current discrete point moving to the next discrete point and the origin of the coordinate system in the clockwise direction;

[0013] Calculate the difference between the angular value of the previous discrete point moving to the current discrete point and the current discrete point moving to the next discrete point, calculate the absolute value of the ratio of the difference to the moving speed when the movement conversion direction occurs when the current discrete point moves to the next discrete point, take the opposite of the product of the absolute value of the ratio and the vibration amplitude when the current discrete point moves to the next discrete point as the exponent of the exponential function with the natural constant as the base, and take the calculation result of the exponential function as the fitness value of the current discrete point moving to the next discrete point.

[0014] Preferably, the heuristic function for moving from the current discrete point to the next discrete point, which is obtained based on the fitness value for moving from the current discrete point to the next discrete point and the safety factor for moving from the current discrete point to the next discrete point, includes:

[0015] Obtain the Euclidean distance from the next discrete point to the target discrete point and the fitness value for moving from the current discrete point to the next discrete point;

[0016] Calculate the product of the fitness value for moving from the current discrete point to the next discrete point and the safety factor for moving from the current discrete point to the next discrete point, and use the ratio of the product to the Euclidean distance as the heuristic function for moving from the current discrete point to the next discrete point.

[0017] Preferably, the selection probability for moving from the current discrete point to the next discrete point, which is obtained based on the heuristic function for moving from the current discrete point to the next discrete point, includes:

[0018] Obtain the pheromone concentration and marking value of the next discrete point;

[0019] Calculate the product of the heuristic function for moving from the current discrete point to the next discrete point and the pheromone concentration, and use the ratio of the product to the marking value as the selection probability for moving from the current discrete point to the next discrete point.

[0020] Preferably, the pheromone concentration of the next discrete point is updated based on the heuristic function for moving from the current discrete point to the next discrete point, including:

[0021] Update the sum value of the heuristic function for moving from the current discrete point to the next discrete point and the pheromone concentration of the next discrete point to obtain the pheromone concentration of the next discrete point.

[0022] Preferably, obtaining the neighborhood concentration difference degree of the next discrete point includes:

[0023] Use the mean value of the difference in pheromone concentration between the next discrete point and all discrete points in the neighborhood of the next discrete point as the neighborhood concentration difference degree of the next discrete point.

[0024] Preferably, obtaining the concentration dilution coefficient of the next discrete point based on the neighborhood concentration difference degree of the next discrete point includes:

[0025] Obtain the mean value of the pheromone concentration of all discrete points in the search space;

[0026] Calculate the difference between the pheromone concentration of the next discrete point and the mean value, and use the ratio of the product of the difference and the neighborhood concentration difference degree of the next discrete point to the product of the iteration number and the iteration number importance coefficient as the exponent of the exponential function with the natural constant as the base, and use the normalized value of the exponential function calculation result as the concentration dilution coefficient of the next discrete point.

[0027] Preferably, updating the pheromone concentration of the next discrete point according to the concentration dilution coefficient of the next discrete point includes:

[0028] Taking the product of the result of subtracting the concentration dilution coefficient of the next discrete point from 1 and the pheromone concentration of the next discrete point as the updated value of the pheromone concentration of the next discrete point, and realizing the update of the pheromone concentration of the next discrete point.

[0029] In a second aspect, an intelligent auxiliary positioning and navigation system for a surgical manipulator provided by this application further includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the method described in any one of the above.

[0030] This application has at least the following beneficial effects:

[0031] Based on the surgical three-dimensional model collected by the existing device, this application analyzes and constructs a three-dimensional search space according to this three-dimensional model, constructs the selection probability of discrete points according to the search logic of the ant colony algorithm in the two-dimensional space, and jointly analyzes the probability of the next discrete point being selected from the local and overall perspectives, so that the selection of each discrete point in the search space is combined with many factors in the surgical process of the surgical manipulator, making the selection result more accurate; according to the characteristics of the release of the next discrete point during the movement of the manipulator and the influence on the movement path of the discrete point in the subsequent iteration process, and considering the dilution of the pheromone of each discrete point at the same time, the pheromone of the discrete point is updated, optimizing each iteration process of the ant colony algorithm, enabling the ant colony algorithm to obtain a more accurate movement path of the manipulator, greatly increasing the global search ability of the ant colony algorithm, and considering the movement characteristics of the manipulator at the same time, making the final path obtained enable the manipulator to move faster and generate less vibration during the movement, reducing the surgical risk. This application improves the reliability of using the intelligent auxiliary positioning and navigation of the surgical manipulator. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a flowchart of an intelligent auxiliary positioning and navigation method for a surgical manipulator provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] To further elaborate on the technical means and effects adopted by this application to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a method and system for intelligent assisted positioning and navigation of a surgical manipulator proposed according to this application, including its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0036] The following specifically describes, in conjunction with the accompanying drawings, the specific solution of a method and system for intelligent assisted positioning and navigation of a surgical manipulator provided by this application.

[0037] A method and system for intelligent assisted positioning and navigation of a surgical manipulator provided by an embodiment of this application.

[0038] Specifically, the following provides a method for intelligent assisted positioning and navigation of a surgical manipulator. Please refer to Figure 1 , and this method includes the following steps:

[0039] Step S001, obtain the search space for positioning and navigation of the manipulator during a surgical operation.

[0040] In this embodiment, intelligent positioning and navigation of the surgical manipulator is performed through manipulator processing technology. Since the manipulator and the operating table are in a three-dimensional space, three-dimensional reconstruction technology is used to obtain the three-dimensional models of the manipulator and the corresponding surgical space.

[0041] Since the manipulator only moves within the surgical space, that is, it has the most basic movement space during the surgical operation of the manipulator, therefore, the search space will be obtained based on the position of the manipulator and the surgical space. Next, the movement path of the manipulator for the surgical operation will be calculated for the search space.

[0042] A surgical operation has a fixed target surgical position, that is, the starting position of the manipulator is determined, and at the same time, the target position that the manipulator finally needs to move to is determined.

[0043] Thus far, the search space for positioning and navigation of the manipulator during a surgical operation can be obtained through this method, which is convenient for analyzing the distribution characteristics in its search space.

[0044] Step S002, optimize the iterative process of the ant colony algorithm according to the analysis of the distribution characteristics of each discrete point in the search space.

[0045] The entire search space is discretized into a series of three-dimensional discrete points. In this embodiment, the search space, i.e., the space where the manipulator and the corresponding three-dimensional model are located, is equally divided into a size of w * d * h. These discrete points are the nodes that the ant colony algorithm needs to search. Among them, the discrete point is represented as (x, y, z, p), where x, y, and z respectively represent the coordinates of the discrete point in the search space. P represents the pixel value of the discrete point. Where the pixel value of 0 indicates that the discrete point actually does not exist.

[0046] Mark the discrete points around each discrete point in the search space with a size of 3 * 3 * 3. When the pixel value of the surrounding discrete points is the same as that of the current discrete point, the surrounding discrete points are marked as 1, otherwise marked as 0. Each discrete point has a matrix with a size of 3 * 3 * 3 to record the safety factor of the discrete point for the surrounding path, and this matrix is denoted as the safety matrix of the discrete point. At the same time, the safety factor of the safety matrix can be manually changed to ensure that the manipulator can enter the brain. The safety factor of 1 indicates that the surrounding discrete points of the discrete point are safer, that is, it may be a normal path for the manipulator to operate.

[0047] Obtain the average moving speed of the manipulator in each posture and the corresponding moving speed during different posture conversions according to historical data. According to the scenario of this embodiment, that is, there are a total of 26 moving directions of the manipulator, so the average moving speed of the manipulator corresponding to 26 directions can be obtained.

[0048] At the same time, since the vibration generated by the manipulator is different at different positions, obtain the vibration generated by the manipulator during the movement in different types of discrete points according to historical data, and use a sensor to obtain the vibration amplitude. And normalize it and denote it as B, and its value range is [0, 1].

[0049] First, when using the ant colony algorithm for optimization, initialize the pheromone concentration of each discrete point. The initial data volume of the population is 1000, and the maximum number of iterations is denoted as K = 50.

[0050] For any iteration number, take the current discrete point where the iteration number is located as an example to analyze the selection of the next discrete point m.

[0051] Considering that during a surgical operation, when the manipulator is moving, the fewer the number of changes in the direction of its corresponding moving path and the smaller the angle of direction change, the smoother the robot moves and the faster its moving speed. At the same time, vibrations will occur during the movement of the manipulator, and the degree of vibration may affect the operation. Therefore, by combining the moving speed and direction from the current discrete point to the next discrete point, and considering the magnitude of the vibration during the movement of the manipulator, the adaptation value of the manipulator moving from the current discrete point to the next discrete point in the moving path is obtained. Taking the m-th discrete point in the neighborhood of the current discrete point as the next discrete point of the current discrete point as an example, the adaptation value of the current discrete point moving to the next discrete point is obtained:

[0052]

[0053] In the formula, represents the adaptation value of the current discrete point moving to the next discrete point, is an exponential function with the natural constant e as the base, represents the angular value of the clockwise angle formed by the moving path from the previous discrete point to the current discrete point and the origin of the coordinate system, represents the angular value of the clockwise angle formed by the moving path from the current discrete point to the next discrete point and the origin of the coordinate system, represents the angle of the motion conversion direction when the manipulator moves to the next discrete point corresponding moving speed, represents the vibration amplitude generated when the manipulator moves from the current discrete point to the next discrete point.

[0054] It should be noted that when the difference between the moving direction of the manipulator from the previous discrete point to the current discrete point and the moving direction from the current discrete point to the next discrete point is relatively large, that is, is smaller, and at the same time, according to the historical movement data, the moving speed corresponding to the angle of the motion conversion direction of the manipulator is is larger, and the vibration amplitude from the current discrete point to the next discrete point is smaller, it indicates that the adaptation value of the current discrete point moving to the next discrete point relative to the previous movement is larger, that is, is larger, indicating that at this time, the manipulator can move to the next smaller direction with a faster moving speed and smaller vibration.

[0055] The fitness value for the current discrete point to move to the next discrete point m is considered at the local level of the combination of the current discrete point moving to the next discrete point and the historical movement path. However, at the overall level, not only the distance between the current discrete point and the final target discrete point needs to be considered, but also whether the next discrete point is a movable point, that is, to ensure that the position selection of the next discrete point conforms to the basic operations of the surgical procedure and there will be no large deviation errors when the manipulator is running.

[0056] Accordingly, considering the local and overall factors of the current discrete point moving to the next discrete point, the heuristic function for the current discrete point moving to the next discrete point can be obtained:

[0057]

[0058] In the formula, represents the heuristic function for the current discrete point to move to the next discrete point, represents the Euclidean distance between the current discrete point moving to the next discrete point and the target discrete point, represents the safety factor for the current discrete point to move to the next discrete point, represents the fitness value for the current discrete point to move to the next discrete point.

[0059] It should be noted that the closer the Euclidean distance between the next discrete point and the target discrete point is, and the safer the next discrete point is, that is, the safety factor of the next discrete point m of the current discrete point is 1, and the smaller the difference in the movement direction and speed between the previous discrete point and the current discrete point that has passed, the greater the fitness of the current discrete point when moving to the next discrete point, which means the greater the heuristic function of the current discrete point, that is, the next movement of the current discrete point is more likely to be the preferred ant path.

[0060] According to the ant colony algorithm, calculate the selection probability of the current discrete point for other points within its surrounding 3x3x3 neighborhood. The calculation method for the selection probability of the current discrete point moving to the next discrete point m is as follows:

[0061]

[0062] In the formula, represents the selection probability of the current discrete point moving to the next discrete point, represents the marking value of the current discrete point moving to the next discrete point. The value of this is 0 or 1. 0 means no ant has passed through this path, and 1 means an ant has passed through this path, represents the pheromone concentration of the current discrete point moving to the next discrete point. The larger this value is, the greater the possibility of selecting this point, represents the heuristic function of the current discrete point moving to the next discrete point.

[0063] It should be noted that when the marker value for the current discrete point to move to the next discrete point is 0, the selection probability of the next discrete point is indirectly increased, that is, the global search ability of the ant is increased in this way, so that each discrete point may have an ant passing by; at the same time, the higher the pheromone concentration and the heuristic function of the next discrete point, the more likely it is that the next discrete point is the optimal search path of the ant, that is, the greater the selection probability of the current discrete point moving to the next discrete point, and the more likely the next discrete point is to be selected.

[0064] According to the selection probability of the current discrete point moving to the next discrete point obtained above , the ant selection result is obtained using the roulette wheel algorithm. Among them, the roulette wheel algorithm is a well-known technology and will not be elaborated in this embodiment.

[0065] After passing through the next discrete point, the next discrete point also serves as a reference point for the discrete points in the subsequent movement process at the same time, and its reference degree will also change, that is, when the ant passes through the next discrete point, it will release pheromone, so that more ants will be attracted to choose this path on this path. Then, the calculation method of the pheromone concentration of the next discrete point after the ant passes through the next discrete point is as follows:

[0066]

[0067] In the formula, represents the pheromone concentration of the current discrete point moving to the next discrete point. The larger this value, the greater the possibility of selecting this point. represents the heuristic function of the current discrete point moving to the next discrete point. represents the pheromone concentration of the next discrete point after the ant passes through the next discrete point.

[0068] It should be noted that the larger the heuristic function of the next discrete point, the more likely it is that the discrete point is the preferred path, that is, when the heuristic function value of the desired point is larger, the more pheromone is released by the corresponding ant when passing through this point.

[0069] In the process of real ants searching for paths, there are ants releasing pheromones on the passed paths. In order to prevent ants from repeating the same path, that is, to prevent situations where ants keep walking on the same path or other situations, it is necessary to dilute the pheromones released by ants, simulate the process of real ants searching for paths, and ensure that ants do not fall into the local optimal solution when searching for paths.

[0070] According to the analysis of the pheromone concentration of the discrete points around the discrete points, in order to ensure the global search ability of the ant colony in this embodiment, in the initial stage of iteration, the discrete points with pheromone concentration higher than that of the discrete points around them are suppressed, that is, their pheromone concentration dilution coefficient is larger. The specific method is as follows:

[0071] First, perform clustering analysis on the pheromone concentrations of all discrete points. By clustering the pheromone concentrations of all discrete points, discrete points with similar pheromone concentrations are obtained, and the pheromone concentrations of similar discrete points are kept similar. Then, all clustering clusters are reorganized according to the positions in the search space, and the clustering clusters composed of adjacent discrete points are used as new clustering clusters, that is, the discrete points that were originally in the same clustering cluster but far apart are updated according to their position relationships, suppressing the discrete points with lower pheromone concentrations around them, so as to keep the pheromone concentration of the current discrete point at a relatively high level and increase the possibility of the optimal path. Among them, the clustering algorithm in this embodiment uses the DBSCAN clustering algorithm, which is a well-known technology and will not be elaborated in this embodiment. Then, the calculation method of the corresponding discrete point pheromone concentration dilution is as follows:

[0072]

[0073] In the formula, represents the neighborhood concentration difference degree of the next discrete point, represents the pheromone concentration difference between the next discrete point and the corresponding discrete points within the 5*5*5 range around the next discrete point among them.

[0074] It should be noted that the greater the difference in the corresponding pheromone concentrations between the next discrete point and its surrounding discrete points, the more unique the pheromone concentration of the next discrete point is compared to other discrete points, that is, this point may be the intersection of many paths or a point that many paths do not pass through.

[0075] In order to more accurately determine whether the next discrete point is a corner point of many paths or a point that many paths do not pass through, the concentration dilution coefficient of the next discrete point is obtained by combining the pheromone concentration of the next discrete point and the number of iterations:

[0076]

[0077] In the formula, represents the concentration dilution coefficient of the next discrete point, is a normalization function, is an exponential function with the natural constant e as the base, represents the neighborhood concentration difference degree of the next discrete point, represents the pheromone concentration of the next discrete point after the ant passes through it, represents the average value of the pheromone concentrations of all discrete points in the search space, represents the importance coefficient of the number of iterations, represents the number of iterations.

[0078] It should be noted that when the pheromone concentration of the next discrete point to be obtained is greater than the average pheromone concentration, it indicates that the next discrete point may be a discrete point on the intersection path. Therefore, the pheromone dilution coefficient for it is increased to reduce the possibility of ants choosing this path and enhance the possibility of ants choosing other paths. Here, k represents the number of iterations, and n represents the importance coefficient of the number of iterations. In this embodiment, the empirical value of n is taken as 0.05, which can be set by the implementer himself. That is, at the initial stage of the ant colony algorithm iteration, the pheromone concentration of the discrete points with higher inhibitory pheromones is made to increase the possibility of ants going to other paths and enhance its global search ability. When the obtained k is smaller, that is, the number of iterations is less, and the difference between the pheromone concentration of the corresponding discrete point and the pheromones around it is greater, that is, the obtained is larger, and the difference is a positive difference, that is, the obtained is a positive number, it indicates that the pheromone concentration dilution coefficient corresponding to this discrete point is larger.

[0079] By analyzing the dilution degree of the pheromone concentration of the next discrete point, the concentration dilution coefficient of the discrete point is obtained, and then it is brought into each discrete point in the above iteration process. After each iteration is completed, in addition to updating the pheromone concentration of the discrete points on the shortest path among all paths, the pheromone concentration of all discrete points is also diluted and volatilized:

[0080]

[0081] In the formula, represents the pheromone concentration of the next discrete point after the current iteration is completed, that is, the initial pheromone concentration of this discrete point in the next round of iteration , represents the concentration dilution coefficient of the next discrete point, represents the pheromone concentration of the next discrete point after the ant passes through the next discrete point.

[0082] So far, the update of the pheromone concentration in one iteration process can be completed through the above method.

[0083] Step S003, complete the positioning and navigation of the manipulator path during the operation according to the ant colony algorithm.

[0084] Through the optimization of the above iteration process, the iteration process of moving from the current discrete point to the next discrete point is completed. Based on this, the same method is used to complete each iteration of the surgical manipulator in the search space using the ant colony algorithm. Among them, the ant colony algorithm is a well-known technology, which will not be elaborated in this embodiment.

[0085] When the number of iterations is less than the maximum number of iterations K = 50, the iterative process of the ant colony algorithm continues until the iterative process of all data in the population is completed and then stops; when the number of iterations is greater than the maximum number of iterations K = 50, the iterative process of the ant colony algorithm stops, and the final path at this time is used as the final result of the ant colony algorithm.

[0086] Repeat the above process for each iteration to complete the ant colony algorithm, and obtain the moving path of the final manipulator.

[0087] Input the moving path of the manipulator into the manipulator control system, so that the manipulator completes the surgical assistant positioning and navigation function according to the obtained moving path.

[0088] Thus, the intelligent assistant positioning and navigation of the surgical manipulator is completed.

[0089] Based on the same inventive concept as the above method, the embodiment of the present application also provides an intelligent assistant positioning and navigation system for a surgical manipulator, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above methods for an intelligent assistant positioning and navigation method of a surgical manipulator.

[0090] In the embodiment of the present application, based on the surgical three-dimensional model collected by the existing equipment, a three-dimensional stereoscopic search space is analyzed and constructed according to the three-dimensional model. According to the search logic of the ant colony algorithm in the two-dimensional space, the selection probability of discrete points is constructed. The probability of the next discrete point being selected is analyzed from both local and overall perspectives, so that the selection of each discrete point in the search space is combined with many factors in the surgical process of the surgical manipulator, making the selection result more accurate.

[0091] Combined with the influence of the characteristics of the release of the next discrete point on the moving path of discrete points in the subsequent iterative process according to the moving process of the manipulator, and considering the dilution of pheromones of each discrete point, and then updating the pheromones of discrete points, optimizing the iterative process of the ant colony algorithm each time, so that the ant colony algorithm obtains a more accurate moving path of the manipulator, greatly increasing the global search ability of the ant colony algorithm. At the same time, considering the moving characteristics of the manipulator, the obtained final path can make the manipulator move faster and generate less vibration during the moving process, reducing the surgical risk. The embodiment of the present application increases the reliability of using the intelligent assistant positioning and navigation of the surgical manipulator and improves the surgical success rate.

[0092] It should be noted that: the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the specific embodiments of this specification have been described. Moreover, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] The embodiments in this specification are all described in a progressive manner. For the same or similar parts between the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0094] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; any modification to the technical solutions recorded in the foregoing embodiments, or any equivalent replacement of some of the technical features, does not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. An intelligent auxiliary positioning and navigation method for a surgical manipulator, characterized in that: The method comprises the following steps: Obtain the search space for manipulator positioning and navigation; Obtain the safety factor of each discrete point in the search space; for the current discrete point in the iterative process of the ant colony algorithm, obtain the fitness value of the current discrete point moving to the next discrete point according to the change of the moving path parameters of the current discrete point and the previous discrete point; obtain the heuristic function of the current discrete point moving to the next discrete point according to the fitness value of the current discrete point moving to the next discrete point and the safety factor of the current discrete point moving to the next discrete point; obtain the selection probability of the current discrete point moving to the next discrete point according to the heuristic function of the current discrete point moving to the next discrete point; use the turntable algorithm to calculate the selection probability of the current discrete point moving to the next discrete point to obtain the selection result of the next discrete point; Update the pheromone concentration of the next discrete point according to the heuristic function of moving the current discrete point to the next discrete point; use the clustering algorithm to cluster the pheromone concentrations of all discrete points in the search space to obtain clusters; obtain the neighborhood concentration difference of the next discrete point; obtain the concentration dilution coefficient of the next discrete point according to the neighborhood concentration difference of the next discrete point; update the pheromone concentration of the next discrete point according to the concentration dilution coefficient of the next discrete point to complete the optimization of the iterative process of the ant colony algorithm; use the ant colony algorithm to complete the positioning and navigation of the robot path; The step of obtaining the adaptation value of the current discrete point moving to the next discrete point according to the change of the moving path parameters between the current discrete point and the previous discrete point includes: Get the angle value of the clockwise angle formed by the moving path from the previous discrete point to the current discrete point and the moving path from the current discrete point to the next discrete point and the origin of the coordinate system; The difference between the angles of the previous discrete point moving to the current discrete point and the angles of the current discrete point moving to the next discrete point is calculated, the absolute value of the ratio of the difference to the moving speed when the current discrete point moves to the next discrete point and changes direction is calculated, the inverse of the product of the absolute value of the ratio and the vibration amplitude when the current discrete point moves to the next discrete point is used as the exponent of an exponential function with a natural constant as the base, and the calculation result of the exponential function is used as the adaptation value of the current discrete point moving to the next discrete point.

2. The intelligent auxiliary positioning and navigation method of a surgical manipulator according to claim 1, characterized in that: The step of obtaining the security factor of each discrete point in the search space includes: For each discrete point in the search space, any discrete point is taken as the current discrete point, and the neighborhood matrix of the current discrete point is constructed as the security factor of the current discrete point. The discrete points in the security factor of the current discrete point with the same grayscale value as the current discrete point are marked as 1, and the rest are marked as 0.

3. The intelligent auxiliary positioning and navigation method of a surgical manipulator according to claim 1, characterized in that: The heuristic function of moving the current discrete point to the next discrete point is obtained according to the fitness value of the current discrete point moving to the next discrete point and the safety factor of the current discrete point moving to the next discrete point, including: Get the Euclidean distance between the next discrete point and the target discrete point, and the fitness value of the current discrete point moving to the next discrete point; The product of the fitness value of the current discrete point moving to the next discrete point and the safety factor of the current discrete point moving to the next discrete point is calculated, and the ratio of the product to the Euclidean distance is used as the heuristic function of the current discrete point moving to the next discrete point.

4. The intelligent auxiliary positioning and navigation method of a surgical manipulator according to claim 3, characterized in that: The selection probability of moving the current discrete point to the next discrete point is obtained according to the heuristic function of moving the current discrete point to the next discrete point, including: Get the pheromone concentration and marking value of the next discrete point; The product of the heuristic function for the current discrete point to move to the next discrete point and the pheromone concentration is calculated, and the ratio of the product to the mark value is used as the selection probability of the current discrete point to move to the next discrete point.

5. The intelligent auxiliary positioning and navigation method of a surgical manipulator according to claim 1, characterized in that: The updating of the pheromone concentration of the next discrete point according to the heuristic function of moving from the current discrete point to the next discrete point comprises: The heuristic function of moving the current discrete point to the next discrete point and the sum of the pheromone concentration of the next discrete point are updated to obtain the pheromone concentration of the next discrete point.

6. The intelligent auxiliary positioning and navigation method of a surgical manipulator according to claim 1, characterized in that: The step of obtaining the neighborhood concentration difference of the next discrete point includes: The average of the pheromone concentration differences between the next discrete point and all discrete points in the neighborhood of the next discrete point is taken as the neighborhood concentration difference of the next discrete point.

7. The intelligent auxiliary positioning and navigation method of a surgical manipulator according to claim 6, characterized in that: The step of obtaining the concentration dilution coefficient of the next discrete point according to the neighborhood concentration difference of the next discrete point includes: Get the mean value of pheromone concentration of all discrete points in the search space; The difference between the pheromone concentration of the next discrete point and the mean is calculated, and the ratio of the product of the difference and the neighborhood concentration difference of the next discrete point and the product of the number of iterations and the important coefficient of the number of iterations is used as the exponent of an exponential function with a natural constant as the base, and the normalized value of the calculation result of the exponential function is used as the concentration dilution coefficient of the next discrete point.

8. The intelligent auxiliary positioning and navigation method of a surgical manipulator according to claim 7, characterized in that: The step of updating the pheromone concentration of the next discrete point according to the concentration dilution coefficient of the next discrete point includes: The product of the result of subtracting the concentration dilution coefficient of the next discrete point from 1 and the pheromone concentration of the next discrete point is used as the update value of the pheromone concentration of the next discrete point, so as to realize the update of the pheromone concentration of the next discrete point.

9. An intelligent auxiliary positioning and navigation system for a surgical manipulator, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images