Path generation method and generation system for electromagnetic navigation, terminal and storage medium

Abstract

The invention relates to an electromagnetic navigation path generation method and system, a terminal and a storage medium, a tiny electromagnetic sensor is placed in the body of a patient through an electromagnetic positioning system, real-time three-dimensional positioning is realized by using an external magnetic field, and efficient and accurate navigation is provided. In an operation, a doctor not only can position the position of the instrument in real time, but also can clearly determine the accurate position of a focus, so that the safety and effectiveness of the operation are greatly improved. The surgical robot shows unique advantages in complex surgical operations due to the characteristics of stability, accuracy and minimally invasive property of the surgical robot. In combination with robot operation and electromagnetic positioning technologies, a doctor can remotely control the surgical robot, and accurate endoscope instrument operation is achieved. The endoscopic surgery is not only limited to a visible area, but also can be used for accurately treating deep and hidden focuses. A program control function enables a doctor to execute a high-difficulty operation at a far place, the geographical limitation is broken, and the problems of difficult positioning of a complex focus, low precision control and the like in an endoscopic operation are solved.

Description

Technical Field

[0001] The present invention relates to a path generation method, and in particular to a path generation method, a generation system, a terminal and a storage medium for electromagnetic navigation. Background Art

[0002] In modern minimally invasive surgery, endoscopic technology has been widely used in a variety of clinical surgeries such as laparoscopy, arthroscopy, and bronchoscopy. However, traditional endoscopic surgery mainly relies on the doctor's experience and intraoperative visual feedback, and the accuracy and safety of the operation are limited when dealing with complex lesions. Faced with the narrow, complex, and visually obstructed surgical environment inside the human body, it is difficult to achieve high-precision lesion positioning relying solely on endoscopic images, which increases the complexity and potential risks of the operation. Summary of the invention

[0003] The technical problem to be solved by the present invention is that traditional endoscopic surgery mainly relies on the doctor's experience and intraoperative visual feedback, and the accuracy and safety of the operation are limited when dealing with complex lesions. Faced with the narrow, complex and visually obstructed surgical environment inside the human body, it is difficult to achieve high-precision lesion positioning relying solely on endoscopic images, which increases the complexity and potential risks of the surgery. In view of the above-mentioned defects of the prior art, a path generation method, generation system, terminal and storage medium for electromagnetic navigation are provided.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] Construct a path generation method for electromagnetic navigation, including the following steps:

[0006] Generate a three-dimensional model of the area to be detected and mark the position of the lesion in the three-dimensional model as the target point, and use the insertion site as the starting point;

[0007] In the space of the three-dimensional model, the starting point is extended as the root node, and child nodes that do not collide with obstacles are randomly generated. The child nodes are added to the random tree to make the random tree grow until the target point is also included in the random tree, and the path connecting the starting point and the target point is obtained by tracing back from the target point to the starting point.

[0008] A path from the starting point to the target point is obtained according to the sub-node, and the endoscope moves from the starting point to the target point according to the path to obtain a target image;

[0009] The actual force generated by the endoscope contacting the inner wall of the cavity when the endoscope moves in the path is collected, and the action state of the endoscope is controlled according to the force.

[0010] Preferably, the process of randomly generating child nodes that do not collide with obstacles also includes:

[0011] The current node position, target position and speed are evaluated, and a force vector is returned to move the extension direction toward the target, so that the random tree grows toward the target point under the action of the gravity function.

[0012] Preferably, in the process of obtaining the path from the starting point to the target point based on the sub-nodes, multiple paths are formed, and the shortest path is selected as the path for the endoscope to move from the starting point to the target point.

[0013] Preferably, in the process of acquiring a path from the starting point to the target point according to the sub-node, and the endoscope moving from the starting point to the target point according to the path to acquire the target image, the process further includes:

[0014] After the path from the starting point to the target point is selected, the force acting on the path during movement is calculated based on the turning angle and the forward direction of the path, and the path is optimized.

[0015] Preferably, in the process of calculating the force during the movement in the path according to the turning angle and the forward direction of the path and optimizing the path, the process includes:

[0016] The lateral angular rotation is adjusted by the lateral adjustment part, and the longitudinal angular rotation is adjusted by the longitudinal adjustment part.

[0017] Preferably, the process of collecting the actual force generated when the endoscope moves in the path and contacts the inner wall of the cavity, and controlling the action state of the endoscope according to the force, includes:

[0018] If the force generated is greater than the set value, the endoscope is stopped from continuing to move or a new path is changed to continue the movement;

[0019] If the generated force is not greater than the set value, the vehicle continues to move until it reaches the target point.

[0020] Construct a path generation system for electromagnetic navigation, including:

[0021] Operation module: used to distribute and receive instructions within the system;

[0022] Coordinate processing module: used to process electromagnetic positioning information to establish a three-dimensional model and generate a distance path from the initial point to the target point of the endoscope. The coordinate processing module randomly generates nodes in the three-dimensional model to grow a random tree. The vector of the return force should be used to guide the node to move toward the target point according to the current position of the node, the target position and the moving speed until the target point is included in the random tree, and the path connecting the starting point and the target point is obtained by tracing back from the target point to the starting point.

[0023] Data acquisition module: collects the force exerted on the endoscope when it moves in contact with the inner wall of the cavity, and sends the force to the operation module for corresponding action.

[0024] Preferably, the path generation system further comprises a torque conversion module for calculating the direction of movement and the angle of rotation within the path and adjusting the angle and direction to optimize the path.

[0025] A smart terminal is constructed, characterized in that the smart terminal includes at least one memory, at least one processor, and an electromagnetic navigation path generation program stored in the memory and executable on the processor, and the electromagnetic navigation path generation program implements the steps of the electromagnetic navigation path generation method as described above when executed by the processor.

[0026] A computer-readable storage medium is constructed, characterized in that a path generation program for electromagnetic navigation is stored on the computer-readable storage medium, and the path generation program for electromagnetic navigation, when executed by a processor, implements the steps of the path generation method for electromagnetic navigation as described above.

[0027] The beneficial effects of the present invention are: first, a tiny electromagnetic sensor is placed in the patient's body through an electromagnetic positioning system, and an external magnetic field is used to achieve real-time three-dimensional positioning, without the use of radioactive radiation, and can provide efficient and accurate navigation in soft tissues. Compared with optical or X-ray positioning technology, electromagnetic positioning has the advantages of no radiation, penetrating tissues, and real-time dynamic tracking, and is particularly suitable for endoscopic minimally invasive surgery. Through electromagnetic positioning technology, doctors can not only locate the position of the instrument in real time during surgery, but also clearly determine the exact position of the lesion, greatly improving the safety and effectiveness of the surgery. The surgical robot, with its stable, precise and minimally invasive characteristics, shows unique advantages in complex surgical operations. Combining robot operation with electromagnetic positioning technology, doctors can remotely control the surgical robot to achieve precise endoscopic instrument operation. This combination makes endoscopic surgery not only limited to the visible area, but also can accurately treat deep and hidden lesions. At the same time, the remote control function enables doctors to perform difficult operations at a distance, breaking the geographical restrictions. Through the combination of electromagnetic positioning navigation and robotic operation, we can solve the problems of difficult localization of complex lesions and low precision control in endoscopic surgery, promote the development of remote precision minimally invasive surgery, and provide high-level surgical treatment for patients in areas with insufficient medical resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be further described below in conjunction with the accompanying drawings and embodiments. The drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work:

[0029] Figure 1A schematic diagram of a flow chart of a path generation method according to a preferred embodiment of the present invention;

[0030] Figure 2 A schematic diagram of the system structure of a path generation system according to a preferred embodiment of the present invention;

[0031] Figure 3 Schematic diagram of the structure of a smart terminal according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the following will be described clearly and completely in combination with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are partial embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0033] A method for generating a path for electromagnetic navigation according to a preferred embodiment of the present invention; Figure 1 As shown, it is a flow chart of a method for generating a path of electromagnetic navigation provided by an embodiment of the present invention. The method can be executed by a device, and the device can be implemented by software and / or hardware.

[0034] Specifically, in this embodiment, the path generation method of electromagnetic navigation includes:

[0035] S1: Generate a three-dimensional model of the area to be detected and mark the position of the lesion in the three-dimensional model as the target point;

[0036] In a preferred embodiment of the present invention, after the patient lies flat, the doctor places the magnetic positioning frame outside the patient's area to be detected, parallel to the body, and then starts the electromagnetic positioning control unit to establish a stable magnetic field. Among them, the magnetic positioning frame is outside the patient's area to be detected, and a stable magnetic field environment is established, and the magnetic field environment can cover all positions within the patient's area to be detected, thereby ensuring that the endoscope is always within the coverage of the magnetic field after entering the human body, and is located in real time with the endoscope. The positioning space size of the magnetic positioning frame is divided into an elliptical area surrounded by R1 and R2, and is connected to the electromagnetic positioning unit. The electromagnetic positioning control unit controls the action of the magnetic positioning frame to change the magnetic field outside the area to be detected. The specific action change can be to control the rotation or movement of the magnetic positioning frame. And during the action, the magnetic field is kept to cover all positions within the patient's area to be detected.

[0037] Furthermore, an endoscope with a magnetic induction device is operated to enter the lesion site of the human body through a natural cavity, and an image of the lesion site is obtained through the endoscope. The magnetic induction device uses a magnetic sensor, which is integrated into the insertion part of the endoscope and enters the human body through the natural cavity with the endoscope. The magnetic sensor detects the magnetic field changes around the lesion site in real time, and transmits the data of the magnetic field changes to the electromagnetic positioning control unit. The magnetic sensor uses the principle of electromagnetic induction to obtain its position and direction in the magnetic field. It can be seen from the Hall effect that when a semiconductor sheet (magnetic sensor) is placed in a magnetic field, when a current passes through, an electromotive force will be generated in a direction perpendicular to the current and the magnetic field. The current in the conductive plate is the directional movement of free electrons in the metal under the action of the electric field. For a conductor with a known Hall coefficient, a current with a known direction and magnitude is passed, and the direction and magnitude of the Hall potential difference on both sides of the conductor are measured at the same time, so that the direction and magnitude of the magnetic field in which the conductor is located can be obtained. By continuously recording the position of the magnetic sensor, the movement path of the magnetic sensor in the human body and the position of the magnetic sensor can be established.

[0038] Furthermore, the magnetic sensor detects the change of magnetic field in real time, the electromagnetic positioning control unit receives the data sent by the magnetic sensor, accurately calculates the position and direction of each magnetic sensor according to the change of magnetic field, and converts it into the specific position information of the endoscope in the human body, and the electromagnetic control unit generates the path of the magnetic sensor in the human body cavity in real time, and establishes a three-dimensional model of the human body according to the specific position information. The endoscope is equipped with a high-definition camera and a light source system, which can provide clear real-time images. Through the precise measurement of the magnetic sensor, the electromagnetic positioning control unit establishes a three-dimensional model of the human body, and the doctor operates the endoscope handle to drive the movement of the magnetic sensor, and adjusts the position and direction of the endoscope through the control button on the endoscope handle, and marks the three-dimensional model according to the image of the lesion site obtained by the endoscope during observation, and records the marked point as the target point, and the insertion point as the initial point.

[0039] S2: Acquire a path from the starting point to the target point, and the endoscope moves from the starting point to the target point according to the path to acquire a target image;

[0040] In a preferred embodiment of the present invention, an improved RRT algorithm, i.e., a fast expansion random number algorithm, is used to calculate the path from the starting point to the target point. Since the core idea of ​​the traditional RRT algorithm is to use the starting point as the root node of the tree, and then generate new nodes in the space by random sampling, if the new node does not collide with the obstacle, the node is added to the random tree as a child node of the tree. In this way, the random tree is expanded in the space until the end point is found, and then the planned path can be found by tracing back from the end point to the starting point. This method explores the entire space in a random sampling manner, and has the advantage of traversing the entire space at the fastest speed.

[0041] Furthermore, from the principle of the algorithm, we can see that the traditional RRT algorithm is divided into two steps:

[0042] Step 1: Grow the random tree by randomly generating nodes in space until the end point is also included in the random tree;

[0043] Step 2: Trace back from the end point to obtain multiple paths connecting the starting point and the target end point, and use the shortest path among them.

[0044] However, in the standard RRT algorithm, the premise of determining a new node is to generate a random node in space, which makes the growth of the random tree non-directional and the algorithm converges slowly. To address this problem, the target gravity function is introduced into the standard RRT algorithm by combining the concepts of gravitational field and repulsive field in the artificial potential field method. The target gravity function is used to evaluate the current position, target position and generation speed, and a force vector is returned to guide the moving point toward the target, so that the random tree grows toward the end point under the action of the gravity function, so that the improved RRT algorithm corrects the disadvantage of the slow convergence of the random tree.

[0045] When generating new nodes, the original algorithm uses:

[0046]

[0047] In the formula, x r Represents the randomly generated node when a new node is generated, x n represents the child node closest to the random point, S represents the step length, x ne Represents the new node that is finally generated.

[0048] The improved algorithm uses:

[0049]

[0050] Where x e represents the target node, k p Represents the gravity component. The larger the value, the stronger the control of the gravity component. However, too large a value will distort the growth of the random tree. You can adjust it yourself to get the best result.

[0051] Furthermore, the improved algorithm may still generate multiple available paths from the starting point to the target point, and the multiple paths may be sorted by length, and the shortest path may be selected as the preferred path. It should be noted that the paths may also be sorted based on a variety of conditions, and the specific conditions may be set differently according to the different locations of the lesions.

[0052] S3: calculating the steering angle of the acquired path and the acquired path, and adjusting the speed and direction of the endoscope moving within the path;

[0053] In the preferred embodiment of the present invention, since the conditions inside the human body are relatively complex, it is also necessary to calculate the displacement and force of the moving point in order to control the endoscope to move forward in the human body. Since the robot actually operates a four-way endoscope to insert into the human body, after path planning, it is necessary to calculate the actual force acting on the operating part of the endoscope according to the turning angle and the forward direction of the path to obtain the turning angle and the distance between the turning angles at each point in the path. At the same time, the rotation angle and the moving force of the endoscope are adjusted by the operating part. The operating part mainly includes a lateral adjustment part and a longitudinal adjustment part. The lateral adjustment part is used to adjust the lateral angle rotation, and the longitudinal adjustment part is used to adjust the longitudinal angle rotation. When the endoscope moves to the turning angle and the forward direction of the path, the angle and speed will be adjusted according to the aforementioned data to make its movement in the path more precise. Assume that the relationship between the deflection angle and the force of the four-way endoscope is:

[0054] θ h =k h n h ③

[0055] θ v =k n n v ④

[0056] where θ h and θ v Denote the horizontal deflection angle and the vertical deflection angle respectively, k h and k v Denote the horizontal deflection function and the vertical deflection function respectively, n h and n v They respectively represent the magnitude of the force on the horizontal deflection adjustment part and the magnitude of the force on the vertical adjustment part.

[0057] According to the above formula, the path planning data can be converted into the specific force of the robot operating the endoscope. At the same time, when the robot enters the target position along the path, it can directly move in the insertion direction according to the path length. The moving length is:

[0058] L=kl ⑤

[0059] Where L represents the displacement length of the robot arm along the insertion direction, k is a constant, and l is the actual length of the path planning.

[0060] S4: collecting the actual force generated by the endoscope contacting the inner wall of the cavity when the endoscope moves in the path, and controlling the action state of the endoscope according to the force;

[0061] In a preferred embodiment of the present invention, a miniature force sensor is installed on the top of the endoscope. When the endoscope advances in the human cavity, if the force between the endoscope and the cavity is too large due to misoperation or inaccurate calculation, and even the intestine is damaged, the force signal is promptly transmitted to the robot operating system to stop the current operation in time to avoid damage to the human body, thereby providing safety protection measures for the endoscope during insertion into the human body.

[0062] Through the above method, a three-dimensional model of the area to be detected is first obtained through electromagnetic positioning, and the lesion site is marked as a target point on the three-dimensional model. Then, the path from the starting point to the target point is obtained through the rapid expansion random number method, and the turning angle and the forward direction in the path are calculated to act on the endoscope to adjust the movement of the endoscope and optimize the path. The endoscope reaches the target point from the insertion point according to the optimized path and collects the force during the movement to avoid damage to the cavity caused by excessive force due to misoperation or inaccurate calculation, thereby enabling the endoscope to enter the lesion site of the human body for surgery, while solving the problems of difficult positioning of complex lesions and low precision control, and achieving accurate endoscopic instrument operation.

[0063] Corresponding to an electromagnetic navigation path generation method, the present invention also provides an electromagnetic navigation path generation system, specifically, as Figure 2 As shown, the path generation of the electromagnetic navigation includes: an operation module 100, a coordinate processing module 200, a torque conversion module 300 and a data acquisition module 400.

[0064] The operation module 100 is used to distribute and receive instructions within the system;

[0065] Specifically, the operating system can adopt a robot operating system, which uses the general ROS robot operating system to distribute and receive instructions within the system. The robot automatically controls the four-way endoscope to enter the lesion site of the human body for surgery. Due to the robot's own properties, it can contain a coordinate processing module to generate a specific insertion path for the soft endoscope and specify an exit path. It also calculates the insertion direction and force based on the basic parameters of the manipulator and the endoscope to control the operation.

[0066] A coordinate processing module 200 is used to process electromagnetic positioning information to establish a three-dimensional model and generate a distance path from an initial point to a target point of the endoscope;

[0067] Specifically, a magnetic positioning frame is placed outside the patient's area to be detected, and a stable magnetic field environment is established, and the magnetic field environment can cover all positions within the patient's area to be detected, so as to ensure that the endoscope is always within the coverage of the magnetic field after entering the human body, and is positioned in real time with the endoscope. The endoscope with a magnetic induction device is operated to enter the lesion site of the human body through the natural cavity, and the image of the lesion site is obtained through the endoscope. The magnetic field changes around the lesion site are detected in real time by the magnetic sensor, and the data of the magnetic field changes are transmitted to the electromagnetic positioning control unit. By continuously recording the position of the magnetic sensor, the movement path of the magnetic sensor in the human body and the position of the magnetic sensor can be established. The magnetic sensor detects the magnetic field changes in real time, and the electromagnetic positioning control unit receives the data sent by the magnetic sensor, accurately calculates the position and direction of each magnetic sensor according to the magnetic field changes, and converts it into the specific position information of the endoscope in the human body, and the electromagnetic control unit generates the path of the magnetic sensor in the human body cavity in real time, and establishes a three-dimensional model of the human body according to the specific position information. And when observing, the image of the lesion site obtained by the endoscope is marked on the three-dimensional model, the marked point is recorded as the target point, and the insertion point is recorded as the initial point.

[0068] The improved RRT algorithm, i.e., the rapid expansion random number algorithm, is used to calculate the path from the starting point to the target point. Combining the concepts of gravitational field and repulsive field in the artificial potential field method, the target gravitational function is introduced into the standard RRT algorithm. The target gravitational function is used to evaluate the current position, target position, and generation speed, and a force vector is returned to guide the moving point toward the target, so that the random tree grows toward the end point under the action of the gravitational function, so that the improved RRT algorithm corrects the disadvantage of the slow convergence of the random tree. The improved algorithm may still generate multiple available paths from the starting point to the target point, so the multiple paths can be sorted by length, and the shortest path can be selected as the preferred path. It should be noted that the paths can also be sorted by combining multiple conditions, and the specific conditions can be set according to the different locations of the lesions.

[0069] A torque conversion module 300, for calculating the direction of movement and the angle of rotation within the path and adjusting the angle and direction to optimize the path;

[0070] Specifically, due to the complex conditions inside the human body, it is also necessary to calculate the displacement and force of the moving point in order to control the endoscope to move forward in the human body. Since the robot actually operates a four-way endoscope inserted into the human body, after path planning, it is necessary to calculate the actual force acting on the operating part of the endoscope based on the turning angle and forward direction of the path to obtain the turning angle and distance between the corners at each point in the path. At the same time, the rotation angle and moving force of the endoscope are adjusted by the operating part. The operating part mainly includes a lateral adjustment part and a longitudinal adjustment part. The lateral adjustment part is used to adjust the lateral angle rotation, and the longitudinal adjustment part is used to adjust the longitudinal angle rotation. When the endoscope moves to the turning angle and forward direction of the path, the angle and speed will be adjusted according to the aforementioned data to make its movement in the path more precise.

[0071] The data acquisition module 400 collects the force exerted on the endoscope when it moves and contacts the inner wall of the cavity, and sends the force to the operation module for corresponding action;

[0072] Specifically, a miniature force sensor is installed on the top of the endoscope. When the endoscope advances in the human cavity, if the force between the endoscope and the cavity is too large due to misoperation or inaccurate calculation, and even the intestine is damaged, the force signal will be transmitted to the robot operating system in time to stop the current operation in time to avoid harm to the human body, thereby providing safety protection measures for the process of inserting the endoscope into the human body.

[0073] Based on the above embodiments, the present invention further provides an intelligent terminal, whose principle block diagram is as follows: Figure 3 As shown, the above-mentioned intelligent terminal includes a processor, a memory, a network interface and a display screen connected through a system bus. The processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a path generation program for electromagnetic navigation. The memory provides an environment for the operation of the operating system and the path generation program for electromagnetic navigation in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal through a network connection. When the path generation program for electromagnetic navigation is executed by the processor, the steps of any one of the above-mentioned electromagnetic navigation path generation methods are implemented. The display screen of the intelligent terminal can be a liquid crystal display screen or other display screens.

[0074] Those skilled in the art will understand that Figure 3 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the smart terminal to which the scheme of the present invention is applied. The specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0075] In an embodiment of the present invention, a smart terminal is provided. The smart terminal includes a memory, a processor, and an electromagnetic navigation path generation program stored in the memory and executable on the processor. When the electromagnetic navigation path generation program is executed by the processor, the following operation instructions are performed:

[0076] Generate a three-dimensional model of the area to be inspected through an electromagnetic positioning system;

[0077] The corresponding area of ​​the lesion in the three-dimensional model is marked as the target point, and the insertion point is recorded as the starting point;

[0078] Randomly generate nodes in the middle of the three-dimensional model, so that the random tree grows until the end point is also included in the random tree;

[0079] The target gravity function is introduced to evaluate the current position, target position and velocity of the moving point, and return the force vector to guide the moving point to move towards the target point;

[0080] After the moving point moves to the target point, it traces back from the target point to the starting point to obtain the path connecting the starting point and the target point;

[0081] The force applied by the endoscope is calculated based on the steering angle and the heading of the moving point within the path to optimize the path;

[0082] The endoscope moves from the starting point to the target point on the optimized path and collects the force during the movement. If the force is greater than the set value, the movement stops. If the force is less than or equal to the set value, the endoscope continues to move until it reaches the target point.

[0083] An embodiment of the present invention further provides a computer-readable storage medium, on which a path generation program for electromagnetic navigation is stored. When the path generation program is executed by a processor, the steps of any one of the electromagnetic navigation path generation methods provided in the embodiments of the present invention are implemented.

[0084] It should be understood that the present invention is described by some embodiments, and those skilled in the art will appreciate that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the scope of protection of the present invention.

Claims

1. A method for generating a path for electromagnetic navigation, characterized in that: The steps include: Generate a three-dimensional model of the area to be detected and mark the position of the lesion in the three-dimensional model as the target point, and use the insertion site as the starting point; In the space of the three-dimensional model, the starting point is extended as the root node, and child nodes that do not collide with obstacles are randomly generated. The child nodes are added to the random tree to make the random tree grow until the target point is also included in the random tree, and the path connecting the starting point and the target point is obtained by tracing back from the target point to the starting point. A path from the starting point to the target point is obtained according to the sub-node, and the endoscope moves from the starting point to the target point according to the path to obtain a target image; The actual force generated by the endoscope contacting the inner wall of the cavity when the endoscope moves in the path is collected, and the action state of the endoscope is controlled according to the force.

2. The path generation method according to claim 1, characterized in that: The process of randomly generating child nodes that do not collide with obstacles also includes: The current node position, target position and speed are evaluated, and a force vector is returned to move the extension direction toward the target, so that the random tree grows toward the target point under the action of the gravity function.

3. The path generation method according to claim 2, characterized in that: In the process of acquiring the path from the starting point to the target point according to the sub-nodes, multiple paths are formed, and the shortest path is selected as the path for the endoscope to move from the starting point to the target point.

4. The path generation method according to claim 1, characterized in that: In the process of acquiring a path from the starting point to the target point according to the sub-node, and the endoscope moving from the starting point to the target point according to the path to acquire the target image, the process also includes: After the path from the starting point to the target point is selected, the force acting on the path during movement is calculated based on the turning angle and the forward direction of the path, and the path is optimized.

5. The path generation method according to claim 4, characterized in that: The process of calculating the force during the movement within the path according to the turning angle and the forward direction of the path and optimizing the path includes: The lateral angular rotation is adjusted by the lateral adjustment part, and the longitudinal angular rotation is adjusted by the longitudinal adjustment part.

6. The path generation method according to claim 1, characterized in that: The process of collecting the actual force generated when the endoscope moves in the path and contacts the inner wall of the cavity, and controlling the action state of the endoscope according to the force, includes: If the force generated is greater than the set value, the endoscope is stopped from continuing to move or a new path is changed to continue the movement; If the generated force is not greater than the set value, the vehicle continues to move until it reaches the target point.

7. A path generation system for electromagnetic navigation, characterized in that: include: Operation module: used to distribute and receive instructions within the system; Coordinate processing module: used to process electromagnetic positioning information to establish a three-dimensional model and generate a distance path from the initial point to the target point of the endoscope. The coordinate processing module randomly generates nodes in the three-dimensional model to grow a random tree. The vector of the return force should be used to guide the node to move toward the target point according to the current position of the node, the target position and the moving speed until the target point is included in the random tree, and the target point is traced back to the starting point to obtain a path connecting the starting point and the target point. Data acquisition module: collects the force exerted on the endoscope when it moves in contact with the inner wall of the cavity, and sends the force to the operation module for corresponding action.

8. The path generation system according to claim 1, characterized in that: The path generation system also includes a torque conversion module for calculating the direction of movement and the angle of rotation within the path and adjusting the angle and direction to optimize the path.

9. An intelligent terminal, characterized in that: The intelligent terminal includes at least one memory, at least one processor, and an electromagnetic navigation path generation program stored in the memory and executable on the processor. When the electromagnetic navigation path generation program is executed by the processor, the steps of the electromagnetic navigation path generation method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an electromagnetic navigation path generation program, and when the electromagnetic navigation path generation program is executed by a processor, the steps of the electromagnetic navigation path generation method according to any one of claims 1 to 6 are implemented.

Images