Multi-path planning method, surgical robot and related products

Abstract

The application discloses a multi-path planning method, a surgical robot and related products. The method comprises the following steps: acquiring at least two first candidate path sets, wherein the first candidate path set is a set of first candidate paths, the first candidate paths in different first candidate path sets are different, the starting point of the first candidate path is a point in the skin area of a first object, and the ending point of the first candidate path is a point in the first object. A first candidate path is selected from each of the at least two first candidate path sets, and at least two target paths are obtained, wherein the target path corresponds to the first candidate path set one by one, and the distance between any two target paths is greater than a first threshold. The application also discloses corresponding products. Based on the multi-path method provided by the application, the safety of the at least two target paths can be improved.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and in particular to a multi-path planning method, a surgical robot, and related products. Background Technology

[0002] In the medical field, it is often necessary to plan multiple pathways from a patient's skin area into their body. Currently, doctors mainly plan these pathways based on experience; however, the safety of such pathways is low. Summary of the Invention

[0003] This application provides a multi-path planning method, a surgical robot, and related products to improve the safety of at least two target paths. The related products include a multi-path planning device and electronic equipment.

[0004] Firstly, a multi-path planning method is provided, the multi-path planning method comprising:

[0005] Obtain at least two sets of first candidate paths. The first candidate path set is a collection of first candidate paths. The first candidate paths in different first candidate path sets are different. The starting point of the first candidate path is a point in the skin region of the first object, and the ending point of the first candidate path is a point in the body of the first object.

[0006] One first candidate path is selected from each of the at least two first candidate path sets to obtain at least two target paths. The target paths correspond one-to-one with the first candidate path sets, and the distance between any two target paths is greater than a first threshold.

[0007] In conjunction with any embodiment of this application, the step of selecting one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths includes:

[0008] Based on the at least two first candidate path sets, at least two first candidate path combinations are obtained. The first candidate path combination includes at least two second candidate paths. The second candidate paths are paths in the first candidate path sets, and the second candidate paths correspond one-to-one with the first candidate path sets.

[0009] At least two first quality parameters of the at least two first candidate path combinations are obtained by performing the following steps on each of the at least two first candidate path combinations: determining the distance between any two of the at least two second candidate paths to obtain at least one first distance;

[0010] Based on the at least one first distance, the first quality parameter of the first candidate path combination is obtained. The first quality parameter is positively correlated with the number of conflicts, where the number of conflicts is the number of distances in the at least one first distance that are less than or equal to the first threshold.

[0011] Based on the at least two first quality parameters, a second candidate path combination is determined from the at least two first candidate path combinations;

[0012] Based on the at least two second candidate paths in the second candidate path combination, the at least two target paths are obtained.

[0013] In conjunction with any embodiment of this application, before obtaining the first quality parameter of the first candidate path combination based on the at least one first distance, the method further includes:

[0014] Determine the degree of dispersion of the starting points of the at least two second candidate paths;

[0015] The process of obtaining the first quality parameter of the first candidate path combination based on the at least one first distance includes:

[0016] Based on the degree of dispersion and the at least one first distance, the first quality parameter of the first candidate path combination is obtained, and the first quality parameter is positively correlated with the degree of dispersion.

[0017] In conjunction with any embodiment of this application, before obtaining the first quality parameter of the first candidate path combination based on the at least one first distance, the method further includes:

[0018] Based on at least one of the following pieces of information for each of the at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the critical tissue, the first angle between the second candidate path and the direction of gravity, and the second angle between the second candidate path and the first normal vector, at least two second mass parameters are obtained.

[0019] Wherein, the first normal vector is the normal vector of the starting point of the second candidate path, the second quality parameter corresponds one-to-one with the second candidate path, the second quality parameter is negatively correlated with the length of the second candidate path, the first included angle, and the second included angle, the second quality parameter is positively correlated with the second distance, and the key tissue is the tissue in the first object body that is expected not to be collided with.

[0020] The process of obtaining the first quality parameter of the first candidate path combination based on the at least one first distance includes:

[0021] The first mass parameter is obtained based on the at least one first distance and the at least two second mass parameters, and the first mass parameter is positively correlated with the sum of the at least two second mass parameters.

[0022] In conjunction with any embodiment of this application, before obtaining at least two second mass parameters based on at least one of the following information for each of the at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the critical tissue, the first angle between the second candidate path and the direction of gravity, and the second angle between the second candidate path and the first normal vector, the method further includes:

[0023] Determine the distance between the starting points of any two of the at least two second candidate paths to obtain at least one third distance;

[0024] If a fourth distance exists in at least one of the third distances, the normal vector of the first starting point is determined based on the first three-dimensional information of the skin region, wherein the fourth distance is less than or equal to a second threshold, and the first starting point is the starting point of the second candidate path corresponding to the fourth distance;

[0025] Obtain the deformation of the skin region, the deformation being generated by the contact between the second object and the first starting point;

[0026] Based on the deformation, the first three-dimensional information is adjusted to obtain the second three-dimensional information;

[0027] The normal vector of the second starting point is determined based on the second three-dimensional information. The second starting point is the starting point of the second candidate path corresponding to the fourth distance, and the second starting point is different from the first starting point.

[0028] In conjunction with any embodiment of this application, obtaining the deformation of the skin region includes:

[0029] Obtain a simulated force, which is used to simulate the force exerted on the first starting point when the second object comes into contact with the first starting point;

[0030] Based on the simulated force and target relationship, the deformation of the skin region is determined, where the target relationship is the relationship between the force acting on the skin region and the deformation of the skin region.

[0031] In conjunction with any embodiment of this application, obtaining at least two first candidate path sets includes:

[0032] Obtain a 3D image of the first object;

[0033] Determine at least two target points within the first object from the three-dimensional image;

[0034] Based on the at least two target points, at least two nearest points are determined from the skin region, wherein the target point and the nearest point correspond one-to-one, and the nearest point is the point in the skin region that is closest to the target point;

[0035] Based on the at least two nearest points, at least two sets of starting points are obtained, wherein the nearest point corresponds one-to-one with the set of starting points, and the set of starting points is the set of starting points of the first candidate path, wherein the distance between any point in the set of starting points and the nearest point is less than or equal to a third threshold.

[0036] Based on the at least two target points and the at least two sets of starting points, at least two sets of first candidate paths are obtained.

[0037] In any embodiment of this application, obtaining at least two first candidate path sets based on the at least two target points and the at least two starting point sets includes:

[0038] Based on the at least two target points and the at least two sets of starting points, at least two sets of second candidate paths are obtained, and the sets of second candidate paths correspond one-to-one with the target points.

[0039] Remove the paths that intersect with the key organization from the at least two second candidate path sets to obtain the at least two first candidate path sets, where the key organization is the organization within the first object that is expected not to be collided with.

[0040] Secondly, a multi-path planning device is provided, the multi-path planning device comprising:

[0041] The acquisition unit is used to acquire at least two first candidate path sets. The first candidate path set is a collection of first candidate paths. The first candidate paths in different first candidate path sets are different. The starting point of the first candidate path is a point in the skin region of the first object, and the ending point of the first candidate path is a point in the body of the first object.

[0042] The processing unit is configured to select one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths, wherein the target paths correspond one-to-one with the first candidate path sets, and the distance between any two target paths is greater than a first threshold.

[0043] In conjunction with any embodiment of this application, the processing unit is further configured to:

[0044] Based on the at least two first candidate path sets, at least two first candidate path combinations are obtained. The first candidate path combination includes at least two second candidate paths. The second candidate paths are paths in the first candidate path sets, and the second candidate paths correspond one-to-one with the first candidate path sets.

[0045] At least two first quality parameters of the at least two first candidate path combinations are obtained by performing the following steps on each of the at least two first candidate path combinations: determining the distance between any two of the at least two second candidate paths to obtain at least one first distance;

[0046] Based on the at least one first distance, the first quality parameter of the first candidate path combination is obtained. The first quality parameter is positively correlated with the number of conflicts, where the number of conflicts is the number of distances in the at least one first distance that are less than or equal to the first threshold.

[0047] Based on the at least two first quality parameters, a second candidate path combination is determined from the at least two first candidate path combinations;

[0048] Based on the at least two second candidate paths in the second candidate path combination, the at least two target paths are obtained.

[0049] In conjunction with any embodiment of this application, the processing unit is further configured to:

[0050] Determine the degree of dispersion of the starting points of the at least two second candidate paths;

[0051] Based on the degree of dispersion and the at least one first distance, the first quality parameter of the first candidate path combination is obtained, and the first quality parameter is positively correlated with the degree of dispersion.

[0052] In conjunction with any embodiment of this application, the processing unit is further configured to:

[0053] Based on at least one of the following pieces of information for each of the at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the critical tissue, the first angle between the second candidate path and the direction of gravity, and the second angle between the second candidate path and the first normal vector, at least two second mass parameters are obtained.

[0054] Wherein, the first normal vector is the normal vector of the starting point of the second candidate path, the second quality parameter corresponds one-to-one with the second candidate path, the second quality parameter is negatively correlated with the length of the second candidate path, the first included angle, and the second included angle, the second quality parameter is positively correlated with the second distance, and the key tissue is the tissue in the first object body that is expected not to be collided with.

[0055] The first mass parameter is obtained based on the at least one first distance and the at least two second mass parameters, and the first mass parameter is positively correlated with the sum of the at least two second mass parameters.

[0056] In conjunction with any embodiment of this application, the processing unit is further configured to determine the distance between the starting points of any two of the at least two second candidate paths, to obtain at least one third distance;

[0057] The processing unit is further configured to, in the case that a fourth distance exists in the at least one third distance, determine the normal vector of a first starting point based on the first three-dimensional information of the skin region, wherein the fourth distance is less than or equal to a second threshold, and the first starting point is the starting point of the second candidate path corresponding to the fourth distance;

[0058] The acquisition unit is further configured to acquire the deformation of the skin region, the deformation being generated by the contact between the second object and the first starting point;

[0059] The processing unit is further configured to adjust the first three-dimensional information based on the deformation to obtain the second three-dimensional information;

[0060] The processing unit is further configured to determine the normal vector of the second starting point based on the second three-dimensional information, wherein the second starting point is the starting point of the second candidate path corresponding to the fourth distance, and the second starting point is different from the first starting point.

[0061] In conjunction with any embodiment of this application, the acquisition unit is further configured to:

[0062] Obtain a simulated force, which is used to simulate the force exerted on the first starting point when the second object comes into contact with the first starting point;

[0063] Based on the simulated force and target relationship, the deformation of the skin region is determined, where the target relationship is the relationship between the force acting on the skin region and the deformation of the skin region.

[0064] In conjunction with any embodiment of this application, the acquisition unit is further configured to:

[0065] Obtain a 3D image of the first object;

[0066] Determine at least two target points within the first object from the three-dimensional image;

[0067] Based on the at least two target points, at least two nearest points are determined from the skin region, wherein the target point and the nearest point correspond one-to-one, and the nearest point is the point in the skin region that is closest to the target point;

[0068] Based on the at least two nearest points, at least two sets of starting points are obtained, wherein the nearest point corresponds one-to-one with the set of starting points, and the set of starting points is the set of starting points of the first candidate path, wherein the distance between any point in the set of starting points and the nearest point is less than or equal to a third threshold.

[0069] Based on the at least two target points and the at least two sets of starting points, at least two sets of first candidate paths are obtained.

[0070] In conjunction with any embodiment of this application, the acquisition unit is further configured to:

[0071] Based on the at least two target points and the at least two sets of starting points, at least two sets of second candidate paths are obtained, and the sets of second candidate paths correspond one-to-one with the target points.

[0072] Remove the paths that intersect with the key organization from the at least two second candidate path sets to obtain the at least two first candidate path sets, where the key organization is the organization within the first object that is expected not to be collided with.

[0073] Thirdly, a surgical robot is provided, including the multi-path planning device as described in the second aspect. In this third aspect, the surgical robot can perform a multi-path planning method through the multi-path planning device, achieving the following effect: improving the safety of at least two target paths obtained.

[0074] Fourthly, an electronic device is provided, comprising: a processor and a memory, the memory for storing computer program code, the computer program code including computer instructions, wherein, when the processor executes the computer instructions, the electronic device performs a method as described in the first aspect above and any possible implementation thereof.

[0075] Fifthly, another electronic device is provided, comprising: a processor, a transmitting device, an input device, an output device, and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein, when the processor executes the computer instructions, the electronic device performs a method as described in the first aspect above and any possible implementation thereof.

[0076] In a sixth aspect, a computer-readable storage medium is provided, wherein a computer program is stored therein, the computer program including program instructions that, when executed by a processor, cause the processor to perform a method as described in the first aspect above and any possible implementation thereof.

[0077] In a seventh aspect, a computer program product is provided, the computer program product comprising a computer program or instructions, wherein, when the computer program or instructions are executed on a computer, the computer performs the method described in the first aspect and any possible implementation thereof.

[0078] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application.

[0079] In this embodiment, the first candidate path set is a collection of first candidate paths, where the starting point of each first candidate path is a point in the skin region of the first object, and the ending point is a point within the body of the first object. After acquiring at least two first candidate path sets, the multi-path planning device selects one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths. Each target path corresponds one-to-one with a set of first candidate paths, and the distance between any two target paths is greater than a first threshold. This ensures a large distance between any two target paths, thereby improving the security of the at least two target paths. Attached Figure Description

[0080] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments of this application will be described below.

[0081] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0082] Figure 1 A flowchart illustrating a multi-path planning method provided in an embodiment of this application;

[0083] Figure 2 This is a schematic diagram illustrating the display of candidate path combinations in a three-dimensional image, as provided in an embodiment of this application.

[0084] Figure 3 Another schematic diagram illustrating the display of candidate path combinations in a three-dimensional image, provided as an embodiment of this application;

[0085] Figure 4This is a schematic diagram of the structure of a multi-path planning device provided in an embodiment of this application;

[0086] Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0087] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0088] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different first objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0089] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. It should be understood that in this application, "at least one" means one or more, "more" means two or more, and "at least two" means two or three or more.

[0090] The execution subject of this application embodiment is a multi-path planning device (hereinafter referred to as the planning device), wherein the planning device can be any electronic device capable of executing the technical solutions disclosed in the method embodiments of this application. Optionally, the planning device can be one of the following: a computer, a server.

[0091] It should be understood that the method embodiments of this application can also be implemented by a processor executing computer program code. The embodiments of this application are described below with reference to the accompanying drawings. Please refer to... Figure 1 , Figure 1 This is a flowchart illustrating a multi-path planning method provided in an embodiment of this application.

[0092] 101. Obtain at least two sets of first candidate paths, wherein the first candidate path set is a set of first candidate paths, and the first candidate paths in different first candidate path sets are different. The starting point of the first candidate path is a point in the skin region of the first object, and the ending point of the first candidate path is a point in the body of the first object.

[0093] In this embodiment, the first object can be a human being. The starting point of the first candidate path is a point in the skin region of the first object, and the ending point of the first candidate path is a point inside the body of the first object. For example, the ending point of the first candidate path is a target point inside the human body. That is, the first candidate path is a path from the skin region of the first object to a point inside the body of the first object.

[0094] In some schemes, the first candidate paths in at least two sets of first candidate paths have the same endpoint, in which case the starting points of any two first candidate paths in at least two sets of first candidate paths are different. For example, the lung of the first subject includes target point t1, and the endpoint of the first candidate paths in at least two sets of first candidate paths is target point t1. The starting points of different sets of first candidate paths belong to different sub-regions of the skin region.

[0095] In other schemes, the endpoints of the first candidate paths in different sets of first candidate paths are different, while the first candidate paths in the same set of first candidate paths have the same endpoint. For example, the lung of the first object includes target t1 and target t2. At least two sets of first candidate paths include first candidate path set s1 and first candidate path set s2. The endpoint of the first candidate path in first candidate path set s1 is target t1, and the endpoint of the first candidate path in first candidate path set s2 is target t2.

[0096] 102. Select one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths, wherein the target paths correspond one-to-one with the first candidate path sets, and the distance between any two target paths is greater than a first threshold.

[0097] In this embodiment, at least two target paths are at least two paths for moving from the skin region of the first object into the body of the first object. Optionally, each of the at least two target paths is a path for the second object to move from the skin region of the first object into the body of the first object. For example, the second object is a needle.

[0098] In step 102, the planning device selects one first candidate path from each first candidate path set as the target path, and the distance between any two target paths is large. In this embodiment, the planning device uses a first threshold as a basis to determine whether the distance between two paths is large or small. Specifically, a distance between two paths greater than the first threshold indicates a large distance between the two paths, and a distance less than or equal to the first threshold indicates a small distance between the two paths. Therefore, the distance between any two target paths selected by the planning device is greater than the first threshold.

[0099] Optionally, the distance between two target paths is the minimum distance between the two target paths.

[0100] exist Figure 1 In the multi-path planning method, the first candidate path set is a collection of first candidate paths, where the starting point of each first candidate path is a point in the skin region of the first object, and the ending point is a point within the body of the first object. After acquiring at least two first candidate path sets, the planning device selects one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths. Each target path corresponds one-to-one with a set of first candidate paths, and the distance between any two target paths is greater than a first threshold. This ensures a large distance between any two target paths, thereby improving the security of the at least two target paths.

[0101] Optionally, the at least two target paths are paths through which at least two second objects move from the skin region of the first object to the body of the first object, wherein each target path corresponds one-to-one with a second object. Therefore, if the distance between any two target paths is large, the probability of collision between the at least two second objects during movement can be reduced.

[0102] As an optional implementation, step 102 includes: obtaining at least two combinations of first candidate paths based on at least two sets of first candidate paths, wherein each combination of first candidate paths includes at least two second candidate paths, and the second candidate paths are paths in the sets of first candidate paths, with each second candidate path corresponding one-to-one with a set of first candidate paths. At least two first quality parameters of the at least two first candidate path combinations are obtained by performing the following steps on each of the at least two combinations of first candidate paths: determining the distance between any two second candidate paths in the at least two combinations of second candidate paths to obtain at least one first distance; obtaining a first quality parameter of the first candidate path combination based on the at least one first distance, wherein the first quality parameter is positively correlated with the number of conflicts, and the number of conflicts is the number of distances in the at least one first distance that are less than or equal to a first threshold. Based on the at least two first quality parameters, a second path combination is determined from the at least two combinations of first candidate paths. Based on the at least two second candidate paths in the second candidate path combination, at least two target paths are obtained.

[0103] In this implementation, the planning device first obtains at least two combinations of first candidate paths based on at least two sets of first candidate paths. Then, it determines a quality score (i.e., a first quality score) for each combination of first candidate paths. Next, based on at least two first quality scores from the at least two combinations of first candidate paths, it determines second path combinations. Finally, based on at least two second candidate paths from the second path combinations, it obtains at least two target paths.

[0104] Because the distance between two paths is small, objects moving along the paths are more likely to collide. Therefore, the first quality score of the first candidate path combination is negatively correlated with the number of collisions. In other words, the more collisions there are, the lower the quality of the first candidate path combination, and correspondingly, the smaller the first quality score.

[0105] As an optional implementation, in determining the first quality score of the first candidate path combination, the planning device further determines the dispersion of the starting points of at least two second candidate paths before obtaining the first quality parameter of the first candidate path combination based on at least one first distance. Then, in the process of executing the step "obtaining the first quality parameter of the first candidate path combination based on at least one first distance", the following steps are performed: obtaining the first quality parameter of the first candidate path combination based on the dispersion and at least one first distance, wherein the first quality parameter is positively correlated with the dispersion.

[0106] Because the greater the dispersion of the starting points of the second candidate paths, the more dispersed the starting points of the second candidate paths are, which means that the probability of collision between objects moving from the skin region of the first object and the body of the first object along the second candidate paths is low, in this embodiment, the planning device not only determines the first quality score of the first candidate path combination based on at least one first distance, but also determines the first quality score of the first candidate path combination based on the dispersion of the starting points of at least two second candidate paths. Moreover, the first quality parameter is positively correlated with the dispersion.

[0107] In some schemes, the planning device acquires first three-dimensional information of the skin region, wherein the first three-dimensional information includes the three-dimensional information of each point in the skin region. Optionally, the first three-dimensional information includes the three-dimensional coordinates of each point in the skin region in a target coordinate system; for example, the target coordinate system is the world coordinate system. Based on the first three-dimensional information, the three-dimensional information of the starting points of at least two second candidate paths is determined. Based on the three-dimensional information of the starting points of the at least two second candidate paths, the dispersion of the starting points of the at least two second candidate paths is obtained. For example, based on the variance of the three-dimensional information of the starting points of the at least two second candidate paths, the dispersion of the starting points of the at least two second candidate paths is obtained.

[0108] As an alternative implementation, in determining the first mass score of the first candidate path combination, before obtaining the first mass parameter of the first candidate path combination based on at least one first distance, the planning device also obtains at least two second mass parameters based on at least one of the following information for each of at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the critical tissue, the first angle between the second candidate path and the direction of gravity, and the second angle between the second candidate path and the first normal vector. The first normal vector is the normal vector of the starting point of the second candidate path. The second mass parameters correspond one-to-one with the second candidate paths. The second mass parameters are negatively correlated with the length, first angle, and second angle of the second candidate path, and positively correlated with the second distance. The critical tissue is the tissue within the first object that is expected to avoid collision.

[0109] Then, during the execution of step "obtaining the first quality parameter of the first candidate path combination based on at least one first distance", the following steps are performed: obtaining the first quality parameter based on at least one first distance and at least two second quality parameters, wherein the first quality parameter is positively correlated with the sum of at least two second quality parameters. Thus, based on the second quality scores of the second candidate paths in the first candidate path combination, the first quality score of the first candidate path organization can be determined, thereby improving the accuracy of the first quality parameter.

[0110] Optionally, the planning device obtains a length score based on the length of the second candidate path, wherein the length score is negatively correlated with the length of the second candidate path. A first angle score is obtained based on a first included angle, wherein the first angle score is negatively correlated with the first included angle. A second angle score is obtained based on a second included angle, wherein the second angle score is negatively correlated with the second included angle. The length score, the first angle score, and the second angle score are weighted and summed to obtain a second quality score.

[0111] As an optional implementation, in determining the first quality score of the first candidate path combination, before obtaining the first quality parameter of the first candidate path combination based on the degree of dispersion and at least one first distance, the planning device further performs the following steps: obtaining at least two second quality parameters based on at least one of the following information for each of at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the critical organization, the first angle between the second candidate path and the direction of gravity, and the second angle between the second candidate path and the first normal vector. After obtaining at least two second quality parameters, in the process of obtaining the first quality parameter of the first candidate path combination based on the degree of dispersion and at least one first distance, the following steps are performed: obtaining the first quality parameter of the first candidate path combination based on the degree of dispersion, at least one first distance, and at least two second quality parameters. This can improve the accuracy of the first quality score.

[0112] As an optional implementation, in determining the first quality score of the first candidate path combination, before obtaining at least two second quality parameters based on at least one of the following information for each of the at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the critical tissue, the first angle between the second candidate path and the direction of gravity, and the second angle between the second candidate path and the first normal vector, the planning device further determines the normal vector of the starting point of the second candidate path by performing the following steps: determining the distance between the starting points of any two of the at least two second candidate paths to obtain at least one third distance. If a fourth distance exists in at least one third distance, the normal vector of the first starting point is determined based on the first three-dimensional information of the skin region, wherein the fourth distance is less than or equal to a second threshold, and the first starting point is the starting point of the second candidate path corresponding to the fourth distance. The deformation of the skin region is obtained, wherein the deformation is generated by the contact between the second object and the first starting point. Based on the deformation, the first three-dimensional information is adjusted to obtain second three-dimensional information. The normal vector of the second starting point is determined based on the second three-dimensional information, wherein the second starting point is the starting point of the second candidate path corresponding to the fourth distance, and the second starting point is different from the first starting point.

[0113] Considering that if the starting points of the two second candidate paths in the first candidate combination are close to each other, when the second object comes into contact with the starting point of one of the second candidate paths, it will cause deformation of the starting point of the other second candidate path, thus changing the normal vector of the starting point of the other second candidate path. For example, the first candidate tissue includes a second candidate path P1 and a second candidate path P2. When the second object comes into contact with the starting point of the second candidate path P1, the starting point of the second candidate path P1 deforms, causing deformation in the skin area near the starting point of the second candidate path P1. If the starting point of the second candidate path P2 is near the starting point of the second candidate path P1, then the starting point of the second candidate path P2 will deform, thus causing a change in the normal vector of the starting point of the second candidate path P2.

[0114] Therefore, in this embodiment, the planning device first determines the distance between the starting points of any two of the at least two second candidate paths, obtaining at least one third distance. Then, it determines whether the distance between the two starting points is small or large based on a second threshold, that is, whether the third distance is small or large based on the second threshold. Specifically, if the third distance is less than or equal to the second threshold, it indicates that the third distance is small, and thus the two starting points corresponding to the third distance are relatively close. The aforementioned fourth distance is the third distance among at least one third distance that is less than or equal to the second threshold. Conversely, if the third distance is greater than the second threshold, it indicates that the third distance is large, and thus the two starting points corresponding to the third distance are relatively far apart. Therefore, when a fourth distance exists among at least one third distance, the planning device determines the normal vector of one of the two starting points that are relatively close based on the first three-dimensional information of the skin region. Specifically, it determines the normal vector of the first starting point based on the first three-dimensional information, where the first starting point is any one of the two starting points corresponding to the fourth distance.

[0115] Then, by simulating the deformation of the skin region when the second object comes into contact with the first starting point, the normal vector of the second starting point is determined. Specifically, the planning device acquires the deformation of the skin region, and then adjusts the first three-dimensional information based on the deformation to obtain the second three-dimensional information. That is, the second three-dimensional information is obtained by correcting the three-dimensional information of the skin region based on the deformation of the skin region. The second three-dimensional information is the three-dimensional information of the skin region when the second object comes into contact with the first starting point. Finally, the normal vector of the second starting point is determined based on the second three-dimensional information. This improves the accuracy of the normal vector of the second starting point.

[0116] Optionally, at least one of the third distances other than the fourth distance can be referred to as the fifth distance. Then, the normal vector of the starting point of the second candidate path corresponding to the fifth distance can be determined based on the first three-dimensional information.

[0117] Optionally, if a fourth distance does not exist in at least one third distance, the planning device determines the normal vector of the starting point of the second candidate path based on the first three-dimensional information.

[0118] As an optional implementation, obtaining the deformation of the skin region includes: obtaining a simulated force, wherein the simulated force is used to simulate the force exerted on the first starting point when the second object comes into contact with the first starting point. Based on the simulated force and a target relationship, the deformation of the skin region is determined, wherein the target relationship is the relationship between the force exerted on the skin region and the deformation of the skin region.

[0119] Because the second object will come into contact with the first starting point when it moves along the second candidate path with the first starting point as the starting point, and the contact between the second object and the first starting point will cause the first starting point to be subjected to the force of the second object, thereby causing deformation of the skin area. Therefore, in this embodiment, the planning device first obtains the simulated force, and then determines the deformation of the skin area based on the simulated force and the target relationship, which can improve the accuracy of the deformation of the skin area.

[0120] Optionally, the target relationship can be one of the following: linear elastic model, hyperelastic model, or viscoelastic model. Any of these models can be used to simulate the elastic deformation of the skin region under external force.

[0121] As an optional implementation, obtaining at least two first candidate path sets includes: obtaining a three-dimensional image of a first object; determining at least two target points within the first object from the three-dimensional image; determining at least two nearest points in a skin region based on the at least two target points, wherein each target point corresponds to a nearest point, and the nearest point is the point in the skin region closest to the target point; obtaining at least two starting point sets based on the at least two nearest points, wherein each nearest point corresponds to a starting point set, and the starting point set is the set of starting points for the first candidate paths, wherein the distance between any point in the starting point set and the nearest point is less than or equal to a third threshold; and obtaining at least two first candidate path sets based on the at least two target points and the at least two starting point sets.

[0122] In this implementation, the three-dimensional image can be a three-dimensional computed tomography (CT) image. After acquiring the three-dimensional image, the planning device can determine at least two target points within the first object body from the three-dimensional image based on the semantics of the pixels in the 3D CT image. Optionally, the planning device can determine a skin region from the three-dimensional image based on the semantics of the pixels in the 3D CT image. Then, at least two nearest points are determined from the skin region. Specifically, for each target point, a point in the skin region that is closest to it is determined, resulting in at least two nearest points. Based on the at least two nearest points, at least two sets of starting points are obtained. Optionally, for each nearest point, points in the skin region whose distance to the nearest point is less than or equal to a third threshold are determined as adjacent points, resulting in the set of starting points. Finally, based on the at least two target points and the at least two sets of starting points, at least two sets of first candidate paths can be obtained. This enables the determination of at least two sets of first candidate paths based on at least two target points.

[0123] For example, at least two target points include target point B1 and target point B2, at least two first candidate path sets include first candidate path set s3 and first candidate path s4, and at least two starting point sets include starting point set s5 and starting point set s6. Starting point set s5 is determined based on the nearest point z1, and starting point set s6 is determined based on the nearest point z2. The starting point set corresponding to target point B1 is starting point set s5, and the starting point set corresponding to target point B2 is starting point set s6. At this time, the planning device determines the first candidate path set s3 based on target point B1 and the points in the starting point set s5, where the starting point of the first candidate path in the first candidate path set s3 is a point in the starting point set s5, and the ending point of the first candidate path in the first candidate path set s3 is target point B1. Based on target point B2 and the points in the starting point set s6, the first candidate path set s4 is determined, where the starting point of the first candidate path in the first candidate path set s4 is a point in the starting point set s6, and the ending point of the first candidate path in the first candidate path set s4 is target point B2.

[0124] As an optional implementation, based on at least two target points and at least two sets of starting points, at least two first candidate path sets are obtained, including: based on at least two target points and at least two sets of starting points, at least two second candidate path sets are obtained, wherein each second candidate path set corresponds one-to-one with a target point. Paths intersecting with key organizations in the at least two second candidate path sets are removed to obtain at least two first candidate path sets.

[0125] Since the critical organization is the organization within the first object that is expected to avoid collisions, the first candidate path in the first candidate path set should not intersect with the critical organization. Therefore, in this embodiment, the planning device obtains at least two first candidate path sets by removing paths that intersect with the critical organization from at least two second candidate path sets, thereby avoiding the first candidate path in the first candidate path set intersecting with the critical organization and improving the quality of the first candidate path in the first candidate path set.

[0126] To better understand the multi-path planning method provided in this application's embodiments, this application also provides a possible implementation scenario. In this scenario, the planning device first acquires a three-dimensional CT image of a first object. Using a pre-trained deep neural network model (such as U-Net, V-Net, etc.), semantic segmentation is performed on the three-dimensional CT image to obtain segmentation results. Based on the segmentation results, skin regions, bones, organs, blood vessels, trachea, and at least two lesion regions are determined from the three-dimensional CT image, wherein organs, blood vessels, and trachea excluding target points are all critical tissues. Based on the centroids of the at least two lesion regions, at least two target points are obtained. Optionally, after obtaining the at least two target points, the planning device displays the at least two target points in the three-dimensional CT image so that the user can determine the priority of each of the at least two target points. Then, the priority of each of the at least two target points input by the user is received.

[0127] The planning device obtains at least two sets of first candidate paths based on at least two target points. It determines the distance between any two first candidate paths in the at least two sets of first candidate paths, and based on the distance between any two first candidate paths in the at least two sets of first candidate paths, determines the number of conflicting paths in the at least two sets of first candidate paths, wherein conflicting paths include two paths with a distance less than or equal to a first threshold. The planning device also determines the normal vector of the starting point of the first candidate path in the at least two sets of first candidate paths based on first three-dimensional information of the skin region. Then, based on the second quality score method for determining the second candidate path described above, it determines the quality score of each first candidate path in the at least two sets of first candidate paths.

[0128] Based on at least two sets of first candidate paths, at least two combinations of first candidate paths are obtained. Based on the number of conflicting paths in the at least two sets of first candidate paths, the number of conflicts corresponding to the first candidate path combinations is determined. Based on the quality score of each first candidate path in the at least two sets of first candidate paths, at least two second quality scores are determined for the at least two second candidate paths in the first candidate path combinations. The dispersion of the starting points of the at least two second candidate paths in the first candidate path combinations is determined. Based on the number of conflicts, the at least two second quality scores, and the dispersion, the first quality score of the first candidate path combinations is determined.

[0129] Optionally, the first quality score of the first candidate path combination is determined based on the following formula:

[0130] …Formula (1)

[0131] in, Indicates the first mass fraction. It represents the average of at least two second mass fractions. Indicates the number of conflicts. Indicates the degree of dispersion. , , All are positive numbers. (Optional) , , All are less than 1.

[0132] Optionally, the maximum value of the first quality score is determined based on any of the following methods: simulated annealing, genetic algorithm. The first candidate path combination corresponding to the maximum value of the first quality score is used as the second candidate path combination. Based on at least two second candidate paths in the second candidate path combination, at least two target paths are obtained.

[0133] Optionally, the planning device determines a third candidate path combination and a fourth candidate path combination. The first quality score of both the third and fourth candidate path combinations is greater than or equal to a quality score threshold. The number of conflicts corresponding to both the third and fourth candidate path combinations is less than or equal to a conflict threshold. The dispersion of both the third and fourth candidate path combinations is greater than or equal to a dispersion threshold. Furthermore, the third candidate path combination is the one with the smallest number of conflicts among at least one first candidate path combination, and the fourth candidate path combination is the one with the largest dispersion among at least one first candidate path combination. The planning device outputs the third and fourth candidate path combinations, allowing the user to select one as the second candidate path combination. This improves the matching degree between the second candidate path combination and the user's needs.

[0134] Optionally, the planning device outputs the third and fourth candidate path combinations by: displaying the third and fourth candidate path combinations, the first quality score of the third candidate path combination, the first quality score of the fourth candidate path combination, the number of conflicts corresponding to the third and fourth candidate path combinations, the dispersion of the third and fourth candidate path combinations, and the dispersion of the fourth candidate path combination. This allows users to select one of the third and fourth candidate path combinations as the second candidate path combination based on the relevant information of the third and fourth candidate path combinations.

[0135] Optionally, the planning device displays the third and fourth candidate path combinations in the 3D image. This allows users to more intuitively compare the third and fourth candidate path combinations. For example, Figure 2 This is a schematic diagram illustrating the display of candidate path combinations in a three-dimensional image, as provided in an embodiment of this application. Figure 2 In the 3D image of the first object shown, O1 is the endpoint of the candidate path, and Q1 and Q2 are both starting points of the candidate paths. The line segment between Q1 and O1 represents one candidate path in the candidate path combination, and the line segment between Q2 and O1 represents the other candidate path in the candidate path combination. It should be understood that... Figure 2 Part of the candidate path between Q2 and O1 is obscured by the ribs of the first object, therefore the candidate path between Q2 and O1 is discontinuous. Figure 3 This is another schematic diagram illustrating the display of candidate path combinations in a three-dimensional image, provided as an embodiment of this application. Figure 3 In the 3D image of the first object shown, O2 and O3 are both endpoints of candidate paths, and Q3 and Q4 are both starting points of candidate paths. The line segment between Q2 and O3 is one candidate path in the candidate path combination, and the line segment between Q3 and O4 is another candidate path in the candidate path combination.

[0136] Optionally, the planning device also displays the total length of the second candidate path in the third candidate path combination and the total length of the second candidate path in the fourth candidate path combination. This allows the user to select one of the third and fourth candidate path combinations as the second candidate path combination based on the total length.

[0137] Optionally, the planning device also displays the distance between any two second candidate paths in the third candidate path combination and the distance between any two second candidate paths in the fourth candidate path combination. This allows users to select one of the third or fourth candidate path combinations as the second candidate path combination based on the distance between the second candidate path combinations.

[0138] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0139] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, while using clear signs / information to inform users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, personal information processing may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0140] The methods of the embodiments of this application have been described in detail above, and the apparatus of the embodiments of this application is provided below.

[0141] Please see Figure 4 , Figure 4 This is a schematic diagram of a multi-path planning device provided in an embodiment of this application. The multi-path planning device 1 includes an acquisition unit 11 and a processing unit 12, wherein:

[0142] The acquisition unit 11 is used to acquire at least two first candidate path sets. The first candidate path set is a collection of first candidate paths. The first candidate paths in different first candidate path sets are different. The starting point of the first candidate path is a point in the skin region of the first object, and the ending point of the first candidate path is a point in the body of the first object.

[0143] Processing unit 12 is configured to select one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths, wherein the target paths correspond one-to-one with the first candidate path sets, and the distance between any two target paths is greater than a first threshold.

[0144] In conjunction with any embodiment of this application, the processing unit 12 is further configured to:

[0145] Based on the at least two first candidate path sets, at least two first candidate path combinations are obtained. The first candidate path combination includes at least two second candidate paths. The second candidate paths are paths in the first candidate path sets, and the second candidate paths correspond one-to-one with the first candidate path sets.

[0146] At least two first quality parameters of the at least two first candidate path combinations are obtained by performing the following steps on each of the at least two first candidate path combinations: determining the distance between any two of the at least two second candidate paths to obtain at least one first distance;

[0147] Based on the at least one first distance, the first quality parameter of the first candidate path combination is obtained. The first quality parameter is positively correlated with the number of conflicts, where the number of conflicts is the number of distances in the at least one first distance that are less than or equal to the first threshold.

[0148] Based on the at least two first quality parameters, a second candidate path combination is determined from the at least two first candidate path combinations;

[0149] Based on the at least two second candidate paths in the second candidate path combination, the at least two target paths are obtained.

[0150] In conjunction with any embodiment of this application, the processing unit 12 is further configured to:

[0151] Determine the degree of dispersion of the starting points of the at least two second candidate paths;

[0152] Based on the degree of dispersion and the at least one first distance, the first quality parameter of the first candidate path combination is obtained, and the first quality parameter is positively correlated with the degree of dispersion.

[0153] In conjunction with any embodiment of this application, the processing unit 12 is further configured to:

[0154] Based on at least one of the following pieces of information for each of the at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the critical tissue, the first angle between the second candidate path and the direction of gravity, and the second angle between the second candidate path and the first normal vector, at least two second mass parameters are obtained.

[0155] Wherein, the first normal vector is the normal vector of the starting point of the second candidate path, the second quality parameter corresponds one-to-one with the second candidate path, the second quality parameter is negatively correlated with the length of the second candidate path, the first included angle, and the second included angle, the second quality parameter is positively correlated with the second distance, and the key tissue is the tissue in the first object body that is expected not to be collided with.

[0156] The first mass parameter is obtained based on the at least one first distance and the at least two second mass parameters, and the first mass parameter is positively correlated with the sum of the at least two second mass parameters.

[0157] In conjunction with any embodiment of this application, the processing unit 12 is further configured to determine the distance between the starting points of any two of the at least two second candidate paths, to obtain at least one third distance;

[0158] The processing unit 12 is further configured to, in the case that a fourth distance exists in the at least one third distance, determine the normal vector of a first starting point based on the first three-dimensional information of the skin region, wherein the fourth distance is less than or equal to a second threshold, and the first starting point is the starting point of the second candidate path corresponding to the fourth distance;

[0159] The acquisition unit 11 is further configured to acquire the deformation of the skin region, the deformation being generated by the contact between the second object and the first starting point;

[0160] The processing unit 12 is further configured to adjust the first three-dimensional information based on the deformation to obtain the second three-dimensional information;

[0161] The processing unit 12 is further configured to determine the normal vector of the second starting point based on the second three-dimensional information, wherein the second starting point is the starting point of the second candidate path corresponding to the fourth distance, and the second starting point is different from the first starting point.

[0162] In conjunction with any embodiment of this application, the acquisition unit 11 is further configured to:

[0163] Obtain a simulated force, which is used to simulate the force exerted on the first starting point when the second object comes into contact with the first starting point;

[0164] Based on the simulated force and target relationship, the deformation of the skin region is determined, where the target relationship is the relationship between the force acting on the skin region and the deformation of the skin region.

[0165] In conjunction with any embodiment of this application, the acquisition unit 11 is further configured to:

[0166] Obtain a 3D image of the first object;

[0167] Determine at least two target points within the first object from the three-dimensional image;

[0168] Based on the at least two target points, at least two nearest points are determined from the skin region, wherein the target point and the nearest point correspond one-to-one, and the nearest point is the point in the skin region that is closest to the target point;

[0169] Based on the at least two nearest points, at least two sets of starting points are obtained, wherein the nearest point corresponds one-to-one with the set of starting points, and the set of starting points is the set of starting points of the first candidate path, wherein the distance between any point in the set of starting points and the nearest point is less than or equal to a third threshold.

[0170] Based on the at least two target points and the at least two sets of starting points, at least two sets of first candidate paths are obtained.

[0171] In conjunction with any embodiment of this application, the acquisition unit 11 is further configured to:

[0172] Based on the at least two target points and the at least two sets of starting points, at least two sets of second candidate paths are obtained, and the sets of second candidate paths correspond one-to-one with the target points.

[0173] Remove the paths that intersect with the key organization from the at least two second candidate path sets to obtain the at least two first candidate path sets, where the key organization is the organization within the first object that is expected not to be collided with.

[0174] In this embodiment, the first candidate path set is a collection of first candidate paths, where the starting point of each first candidate path is a point in the skin region of the first object, and the ending point is a point within the body of the first object. After acquiring at least two first candidate path sets, the multi-path planning device selects one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths. Each target path corresponds one-to-one with a set of first candidate paths, and the distance between any two target paths is greater than a first threshold. This ensures a large distance between any two target paths, thereby improving the security of the at least two target paths.

[0175] In some embodiments, the functions or modules of the apparatus provided in this application can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0176] Figure 5This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device 2 includes a processor 21 and a memory 22. Optionally, the electronic device 2 also includes an input device 23 and an output device 24. The processor 21, memory 22, input device 23, and output device 24 are coupled together via connectors, which include various interfaces, transmission lines, or buses, etc., and are not limited in this embodiment. It should be understood that in the various embodiments of this application, coupling refers to mutual connection in a specific way, including direct connection or indirect connection through other devices, such as through various interfaces, transmission lines, buses, etc.

[0177] The processor 21 can be one or more graphics processing units (GPUs). If the processor 21 is a GPU, the GPU can be a single-core GPU or a multi-core GPU. Optionally, the processor 21 can be a processor group composed of multiple GPUs, with the multiple processors coupled to each other via one or more buses. Optionally, the processor can also be other types of processors, etc., which are not limited in this embodiment.

[0178] The memory 22 can be used to store computer program instructions, as well as various types of computer program code, including program code for executing the scheme of this application. Optionally, the memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), which is used for related instructions and data.

[0179] Input device 23 is used to input data and / or signals, and output device 24 is used to output data and / or signals. Input device 23 and output device 24 can be independent devices or an integrated device.

[0180] It is understood that in this embodiment of the application, the memory 22 can be used not only to store related instructions, but also to store related data. For example, the memory 22 can be used to store at least two first candidate path sets obtained through the input device 23, or the memory 22 can also be used to store at least two target paths obtained through the processor 21, etc. This embodiment of the application does not limit the specific data stored in the memory.

[0181] Understandable Figure 5This is merely a simplified design of an electronic device. In practical applications, the electronic device may also include other necessary components, including, but not limited to, any number of input / output devices, processors, memories, etc., and all electronic devices that can implement the embodiments of this application are within the protection scope of this application.

[0182] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0183] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will also readily understand that the various embodiments of this application have different focuses, and for the sake of convenience and brevity, the same or similar parts may not be repeated in different embodiments. Therefore, parts not described or not described in detail in one embodiment can be referred to the descriptions in other embodiments.

[0184] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0185] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0186] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0187] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital versatile discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0188] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A multi-path planning method, characterized by, The method comprises: obtaining at least two first candidate path sets, each of the first candidate path sets being a set of first candidate paths, the first candidate paths in different first candidate path sets being different, the first candidate paths having starting points in a skin region of a first object and ending points in the first object; selecting one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths, each of the target paths corresponding to one of the first candidate path sets, and a distance between any two of the target paths being greater than a first threshold; the selecting one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths comprises: obtaining at least two first candidate path combinations based on the at least two first candidate path sets, each of the first candidate path combinations comprising at least two second candidate paths, each of the second candidate paths corresponding to one of the first candidate path sets; determining a distance between any two of the second candidate paths to obtain at least one first distance by performing the following steps on each of the at least two first candidate path combinations; obtaining the first quality parameter of each of the first candidate path combinations based on the at least one first distance, the first quality parameter being positively correlated with a conflict number, the conflict number being a number of distances in the at least one first distance that are less than or equal to the first threshold; determining a second candidate path combination from the at least two first candidate path combinations based on the at least two first quality parameters; and obtaining at least two target paths based on the at least two second candidate paths in the second candidate path combination.

2. The method of claim 1, wherein, Before the obtaining the first quality parameter of each of the first candidate path combinations based on the at least one first distance, the method further comprises: determining a dispersion degree of the starting points of the at least two second candidate paths; the obtaining the first quality parameter of each of the first candidate path combinations based on the at least one first distance comprises: obtaining the first quality parameter of each of the first candidate path combinations based on the dispersion degree and the at least one first distance, the first quality parameter being positively correlated with the dispersion degree.

3. The method of claim 1, wherein, Before the obtaining the first quality parameter of each of the first candidate path combinations based on the at least one first distance, the method further comprises: obtaining at least two second quality parameters based on at least one of the following information of each of the second candidate paths: a length of the second candidate path, a second distance of the second candidate path to a key tissue, a first included angle of the second candidate path to a direction of gravity, and a second included angle of the second candidate path to a first normal vector. The first normal vector is a normal vector of a starting point of the second candidate path, the second quality parameter corresponds to the second candidate path one by one, the second quality parameter is negatively correlated with the length of the second candidate path, the first included angle, the second included angle, and the second quality parameter is positively correlated with the second distance, and the key tissue is a tissue in the first object body which is expected not to be collided; The first quality parameter of the first candidate path combination is obtained based on the at least one first distance, comprising: The first quality parameter is obtained based on the at least one first distance and the at least two second quality parameters, and the first quality parameter is positively correlated with the sum of the at least two second quality parameters.

4. The method of claim 3, wherein, Before the at least two second quality parameters are obtained based on at least one of the following information of each of the at least two second candidate paths: the length of the second candidate path, the second distance between the second candidate path and the key tissue, the first included angle between the second candidate path and the direction of gravity, and the second included angle between the second candidate path and the first normal vector, the method further comprises: Determine the distance between the starting points of any two of the at least two second candidate paths to obtain at least one third distance; In the case that there is a fourth distance in the at least one third distance, the normal vector of the first starting point is determined based on the first three-dimensional information of the skin region, the fourth distance is less than or equal to a second threshold, and the first starting point is the starting point of the second candidate path corresponding to the fourth distance; Obtain the deformation amount of the skin region, the deformation amount being generated by the second object contacting the first starting point; Adjust the first three-dimensional information based on the deformation amount to obtain second three-dimensional information; Determine the normal vector of the second starting point based on the second three-dimensional information, the second starting point being the starting point of the second candidate path corresponding to the fourth distance, and the second starting point being different from the first starting point.

5. The method of claim 4, wherein, The method further comprises: Obtain the simulation force, the simulation force being used to simulate the force received by the first starting point when the second object contacts the first starting point; Determine the deformation amount of the skin region based on the simulation force and a target relationship, the target relationship being the relationship between the force received by the skin region and the deformation of the skin region.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: Obtain a three-dimensional image of the first object; Determine at least two target points in the first object body from the three-dimensional image; Determine at least two nearest points from the skin region based on the at least two target points, the target points and the nearest points corresponding one by one, and the nearest points being the points in the skin region closest to the target points; Based on the at least two nearest points, at least two starting point sets are obtained, the nearest points correspond to the starting point sets one by one, the starting point set is a set of starting points of the first candidate path, and a distance between any point in the starting point set and the nearest point is less than or equal to a third threshold value; Based on the at least two target points and the at least two starting point sets, the at least two first candidate path sets are obtained.

7. A multi-path planning device, characterized by comprising: The multi-path planning device comprises: An acquisition unit is configured to acquire at least two first candidate path sets, the first candidate path sets being sets of first candidate paths, the first candidate paths in different first candidate path sets being different, starting points of the first candidate paths being points in a skin region of a first object, and end points of the first candidate paths being points in the first object. A processing unit is configured to select one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths, the target paths corresponding to the first candidate path sets one by one, and a distance between any two target paths being greater than a first threshold value. The selecting one first candidate path from each of the at least two first candidate path sets to obtain at least two target paths comprises: based on the at least two first candidate path sets, at least two first candidate path combinations are obtained, the first candidate path combination comprising at least two second candidate paths, the second candidate paths being paths in the first candidate path sets, and the second candidate paths corresponding to the first candidate path sets one by one; at least two first quality parameters of the at least two first candidate path combinations are obtained by performing the following steps on each of the at least two first candidate path combinations: a distance between any two second candidate paths in the at least two second candidate paths is determined to obtain at least one first distance; based on the at least one first distance, the first quality parameter of the first candidate path combination is obtained, the first quality parameter being positively correlated with a conflict number, and the conflict number being a number of distances in the at least one first distance that are less than or equal to the first threshold value; based on the at least two first quality parameters, a second candidate path combination is determined from the at least two first candidate path combinations; and based on the at least two second candidate paths in the second candidate path combination, at least two target paths are obtained.

8. A surgical robot, characterized by The multi-path planning device comprises the multi-path planning device as claimed in claim 7.

9. An electronic device, comprising: The multi-path planning device comprises: A processor and a memory, the memory being configured to store computer program code, the computer program code comprising computer instructions, and the electronic device being configured to execute the computer instructions to perform the method as claimed in any one of claims 1 to 6.

Images