Cable tunnel ground path planning method and device and computer equipment

Abstract

The invention relates to a cable tunnel ground path planning method and device and computer equipment. The method comprises the following steps: extracting an initial skeleton line of a passable area in a two-dimensional grid map of a cable tunnel area to be inspected; extracting a guide node for guiding the direction of path exploration from the initial skeleton line; constructing an initial path of the cable tunnel ground in the passable area by adopting a mode of combining random sampling and guiding node guiding sampling; smoothing the initial path to obtain a target path of the cable tunnel ground in the passable area; the target path is a driving path of the tunnel inspection device on the cable tunnel ground. By adopting the method, the number of turning points in the initial path can be reduced, so that the energy consumption and the control difficulty of the tunnel inspection device are reduced.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a method, device and computer equipment for path planning on the ground of a cable tunnel. Background Art

[0002] With the rapid development of unmanned inspection technology, the application of tunnel inspection technology has attracted widespread attention and research. In tunnel inspection technology, tunnel inspection devices can autonomously perform tunnel inspection tasks in complex underground environments. Path planning, a core component of tunnel inspection technology, can be used to plan the travel path of tunnel inspection devices on the ground in cable tunnels. This is crucial for ensuring that tunnel inspection devices can reach their destination safely and efficiently.

[0003] In related technologies, when planning the path of a tunnel inspection device, the A* algorithm, the Rapidly-exploring Random Trees (RRT) algorithm, the ant colony algorithm, or the genetic algorithm are often used to plan the path on the ground of the cable tunnel in the passable area of the cable tunnel area to be inspected.

[0004] However, although the related art can plan the path of the cable tunnel ground, the planned path often has many unnecessary turning points, which increases the energy consumption of the tunnel inspection device and the difficulty of control. Summary of the Invention

[0005] Based on this, the present application provides a path planning method, device and computer equipment for the ground of a cable tunnel, which can reduce the number of turning points in the initial path, thereby reducing the energy consumption and control difficulty of the tunnel inspection device.

[0006] In a first aspect, the present application provides a method for path planning on the ground of a cable tunnel, the method comprising:

[0007] Extracting the initial skeleton line of the passable area in the two-dimensional grid map of the cable tunnel area to be inspected;

[0008] Extracting guide nodes from the initial skeleton line to guide the direction of path exploration;

[0009] The initial path of the cable tunnel ground in the traversable area is constructed by combining random sampling and guided node sampling;

[0010] The initial path is smoothed to obtain a target path on the ground of the cable tunnel in the traversable area; the target path is the driving path of the tunnel inspection device on the ground of the cable tunnel.

[0011] In some embodiments, extracting a guide node for guiding the direction of path exploration from the initial skeleton line includes:

[0012] Sample multiple feature points from the initial skeleton line according to a preset step size and determine the target curvature of each feature point;

[0013] Determine a characteristic point of a target curvature greater than or equal to a preset curvature as a key turning point;

[0014] The redundant turning points among the key turning points are removed to obtain the guiding nodes.

[0015] In some embodiments, removing redundant turning points from key turning points to obtain a guiding node includes:

[0016] Determine the first characteristic point among the key turning points as the first current characteristic point;

[0017] When the distance between the next feature point of the current feature point and the current feature point is greater than a preset distance, the next feature point is determined as a new current feature point;

[0018] If the distance between the next feature point and the current feature point is less than or equal to the preset distance, the next feature point is deleted as a redundant turning point, and the feature point after the redundant turning point is determined as the new next feature point;

[0019] Repeat the above steps until the last feature point in the key turning point is obtained, and determine the retained feature point as the guiding node.

[0020] In some embodiments, a combination of random sampling and guided sampling by a guide node is used to construct an initial path of the cable tunnel ground in the traversable area, including:

[0021] Obtain the starting position point and the ending position point in the cable tunnel area to be inspected, and determine the starting position point as the first current path point;

[0022] When the current path point is in a safe area, the next path point is explored by using a guide node guided sampling method; the safe area is an area where the minimum distance to obstacles is greater than a predetermined distance; obstacles are areas outside the passable area in the two-dimensional grid map;

[0023] If the current path point is not in the safe area, the next path point is explored by random sampling.

[0024] Determine the next waypoint as the new current waypoint;

[0025] Repeat the above steps until the distance between the current path point and the end position point is less than the sampling step size. Based on all the current path points and end position points obtained, the initial path of the cable tunnel ground in the passable area is constructed.

[0026] In some embodiments, exploring the next path point by using a guide node to guide sampling includes:

[0027] If the distance between the current path point obtained last and the corresponding matching feature point in the guide node is greater than or equal to the set distance, the current path point is moved by the sampling step toward the matching feature point to obtain the next path point;

[0028] If the distance between the current path point and the corresponding matching feature point in the guide node is less than the set distance, the current path point is moved by the sampling step toward the next feature point of the matching feature point in the guide node to obtain the next path point;

[0029] The corresponding matching feature point is the feature point with the smallest sequence number among at least one feature point that has been obtained but not passed by the current path point in the guide node.

[0030] In some embodiments, the next path point is explored by random sampling, including:

[0031] A first random point is randomly generated in a two-dimensional grid map, and the current path point obtained is moved by a sampling step toward the first random point to explore the target path point;

[0032] If the angle between the direction of the current path point pointing to the target path point and the preset direction is greater than or equal to the preset angle, obtaining at least one current path point that has been obtained in an area with a preset radius and centered on the target path point, and determining the next path point based on the target path point and the at least one current path point that has been obtained;

[0033] When the angle between the direction of the current path point pointing to the target path point and the preset direction is smaller than the preset angle, the target path point is determined as the next path point.

[0034] In some embodiments, determining a next waypoint based on the target waypoint and at least one acquired current waypoint includes:

[0035] Determine the angles between the directions of the acquired current path points pointing to the target path points and the preset directions;

[0036] If at least one angle among the angles is less than or equal to a preset angle, an acquired current pathpoint corresponding to the minimum angle among the at least one angle is determined as a new parent node of the target pathpoint, or a pathpoint first explored among the at least one acquired current pathpoint corresponding to the at least one angle is determined as a new parent node of the target pathpoint, the pathpoints between the new parent node of the target pathpoint and the target pathpoint are deleted, and the target pathpoint is determined as the next pathpoint;

[0037] When all angles are greater than the preset angle, a second random point is randomly generated in the two-dimensional grid map, and the current path point finally obtained is moved in the direction of the second random point by the sampling step size to explore a new target path point, and the next path point is determined based on the new target path point.

[0038] In some embodiments, smoothing the initial path to obtain a target path on the ground of the cable tunnel in the traversable area includes:

[0039] Sampling the initial path at a preset interval to obtain a plurality of control points; wherein the number of the plurality of control points is greater than the number of the plurality of path points used to construct the initial path;

[0040] According to the preset boundary conditions, a spline curve is used to fit multiple control points to obtain the target path of the cable tunnel ground in the passable area; wherein the boundary conditions include: the first-order derivative and the second-order derivative of the starting position point of the target path are both 0, and the first-order derivative and the second-order derivative of the ending position point of the target path are both 0.

[0041] In a second aspect, the present application provides a path planning device for a cable tunnel surface, the device comprising:

[0042] A skeleton line determination unit is used to extract the initial skeleton line of the passable area in the two-dimensional grid map of the cable tunnel area to be inspected;

[0043] A guide node determination unit, configured to extract a guide node for guiding the direction of path exploration from the initial skeleton line;

[0044] An initial path determination unit is used to construct an initial path of the cable tunnel ground in the traversable area by combining random sampling and guided sampling by guide nodes;

[0045] The target path determination unit is used to smooth the initial path to obtain a target path on the cable tunnel ground in the passable area; the target path is the driving path of the tunnel inspection device on the cable tunnel ground.

[0046] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods of the first aspect when executing the computer program.

[0047] In the technical solution provided in the embodiment of the present application, a combination of random sampling and guide node guided sampling is adopted to construct the initial path of the cable tunnel ground in the passable area. This not only avoids the problem of many unnecessary turning points in the initial path when only random sampling is used to construct the initial path, but also avoids the problem of being unable to cross obstacles when only guide node guided sampling is used to construct the initial path. This can reduce the number of turning points in the initial path while avoiding obstacles, thereby reducing the energy consumption and control difficulty of the tunnel inspection device; and, by smoothing the initial path, the target path of the cable tunnel ground in the passable area is obtained, which can further reduce the number of turning points in the initial path. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A schematic flow chart of a cable tunnel ground path planning method provided in the first embodiment;

[0050] Figure 2 A schematic flow chart of a method for planning a path on the ground surface of a cable tunnel provided in the second embodiment;

[0051] Figure 3 A schematic flow chart of a method for planning a path on the ground in a cable tunnel provided in the third embodiment;

[0052] Figure 4 A schematic flow chart of a method for planning a path on the ground of a cable tunnel provided in a fourth embodiment;

[0053] Figure 5 A schematic flow chart of a method for planning a path on the ground of a cable tunnel provided in a fifth embodiment;

[0054] Figure 6 A schematic diagram of a two-dimensional grid map provided for some embodiments;

[0055] Figure 7 A schematic diagram of an initial skeleton line of a traversable area in a two-dimensional grid map provided in some embodiments;

[0056] Figure 8 A schematic diagram of guide nodes extracted from an initial skeleton line provided in some embodiments;

[0057] Figure 9 Schematic diagram of three path points that satisfy angle constraints for some embodiments;

[0058] Figure 10 A schematic diagram of a method for obtaining the next path point when the angle constraint is not satisfied, provided in some embodiments;

[0059] Figure 11 Schematic diagram of the target path obtained by the traditional RRT algorithm;

[0060] Figure 12 Schematic diagram of the target path obtained for the target-biased RRT;

[0061] Figure 13 Schematic diagram of the target path obtained by the RRT connection algorithm;

[0062] Figure 14 This is a schematic diagram of the target path obtained by the Informed RRT* algorithm;

[0063] Figure 15 Schematic diagram of the target path obtained by initial skeleton line extraction and improved RRT algorithm;

[0064] Figure 16 A schematic diagram of the structure of a cable tunnel ground path planning device provided in some embodiments of the present application;

[0065] Figure 17 A schematic structural diagram of a computer device provided in some embodiments. DETAILED DESCRIPTION

[0066] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0068] In the description of the embodiments of the present application, the technical terms "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined. In the description of the embodiments of the present application, "each" means each or each of a plurality, unless otherwise clearly and specifically defined.

[0069] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0070] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0071] The computer device in the embodiments of the present application may include a combination of one or more of the following: a tunnel inspection device, a server, a computer, a mobile phone, a virtual reality (VR) device, an augmented reality (AR) device, a device in industrial control (Industrial Control), a device in self-driving (Self Driving), a device in smart grid (Smart Grid), a device in transportation safety (Transportation Safety), a device in smart city (Smart City), a device in smart home (Smart Home), a vehicle, a vehicle-mounted device, a vehicle-mounted module, and the like.

[0072] Figure 1 A schematic flow chart of a path planning method for a cable tunnel provided in the first embodiment is shown in FIG. Figure 1 As shown, the method is applied to a computer device, and the method includes the following steps:

[0073] S101: extracting an initial skeleton line of a traversable area in a two-dimensional grid map of a cable tunnel area to be inspected.

[0074] In some embodiments, S101 may include: obtaining a two-dimensional grid map of the cable tunnel area to be inspected, extracting a passable area in the two-dimensional grid map using a watershed algorithm, and performing skeleton line extraction on the passable area to obtain an initial skeleton line.

[0075] The cable tunnel area to be inspected may include a cable tunnel area to be inspected. For example, environmental data of the cable tunnel area to be inspected may be collected by at least one device such as a laser radar, a camera, and an ultrasonic sensor in the cable tunnel area to be inspected, and the environmental data may be converted into a two-dimensional grid map.

[0076] For example, the size of each grid cell in a two-dimensional grid map is set based on actual needs. For example, the grid cell size can be determined based on the control accuracy of the tunnel inspection device and the available computing power of the computer equipment. For example, in a two-dimensional grid map, the state of each grid cell can be represented by a binary value, for example, 1 represents an obstacle and 0 represents a passable area.

[0077] The watershed algorithm is an image processing algorithm based on region segmentation. It classifies objects by simulating geographical structures (such as mountains, ravines, and basins). By simulating the flow of water from high to low, the watershed algorithm distributes image pixels into different "basins," thereby achieving segmentation. The watershed algorithm effectively processes images with complex textures and boundaries and is particularly effective for segmenting objects with distinct boundaries.

[0078] The skeleton line is the central axis of an image, derived through image thinning techniques. It reflects the image's primary structure and shape characteristics. The skeleton line is a thin curve obtained through thinning that maintains the connectivity and topology of the original shape. For complex shapes such as polygons, the skeleton line is an abstract description of their geometric features, reflecting the shape's primary structure and outline. This skeleton line can be obtained by iteratively removing pixels from the image's edges until a single-pixel-wide line remains.

[0079] Exemplarily, extracting the skeleton line of the passable area to obtain the initial skeleton line may include: using a morphological thinning method, such as the Zhang-Suen algorithm or the Guo-Hall algorithm, to extract the initial skeleton line of the passable area.

[0080] For another example, extracting a skeleton line from the drivable area to obtain an initial skeleton line may include: determining areas outside the drivable area in a two-dimensional grid map as obstacles, obtaining the distance between each grid cell in the drivable area and the nearest obstacle, and determining a line formed by local maximum values in the distance as the initial skeleton line. The local maximum value is the maximum distance within a local area.

[0081] As another example, extracting the skeleton line of the passable area to obtain the initial skeleton line may include: determining the center of the largest inscribed circle in the passable area, and using these center points to form the skeleton line.

[0082] S102: Extracting a guide node for guiding the direction of path exploration from the initial skeleton line.

[0083] In some embodiments, S102 may include: extracting key turning points from the initial skeleton line; and removing redundant turning points from the key turning points to obtain guiding nodes.

[0084] In other embodiments, S102 may include: extracting key turning points from the initial skeleton line, and determining the key turning points as guiding nodes.

[0085] Exemplarily, the initial skeleton line can be traversed to identify all turning points, which are points where the direction of the initial skeleton line changes significantly, such as points where the angle change exceeds a preset threshold (e.g., 10 degrees). All identified turning points are marked as key turning points.

[0086] Exemplarily, a redundant turning point may be a turning point whose distance from other turning points is less than or equal to a predetermined threshold.

[0087] S103: Construct an initial path of the cable tunnel ground in the traversable area by combining random sampling and guided node guided sampling.

[0088] Exemplarily, S103 may include: generating a plurality of path points by combining random sampling and guided sampling by a guide node, and constructing an initial path on the ground of the cable tunnel through the plurality of path points.

[0089] In some embodiments, generating multiple path points by combining random sampling and guide node guided sampling may include: when the i-th path point is in a safe area, exploring the i+1-th path point by using guide node guided sampling; when the i-th path point is not in a safe area, exploring the i+1-th path point by using random sampling; determining the i+1-th path point as the new i-th path point; and repeating the above steps until the exploration is completed and multiple path points are obtained. i is an integer greater than or equal to 1, and the first path point is the starting position point in the cable tunnel area to be inspected.

[0090] In other embodiments, a combination of random sampling and guide node guided sampling is used to generate multiple path points, which may include: exploring path points using random sampling with a first probability, and exploring path points using guide node guided sampling with a second probability, thereby exploring multiple path points; the sum of the first probability and the second probability is 1.

[0091] In some embodiments, constructing an initial path on the ground of a cable tunnel through a plurality of path points may include: sequentially connecting the plurality of path points in the order in which the plurality of path points are generated to obtain the initial path.

[0092] S104: Smoothing the initial path to obtain a target path on the ground of the cable tunnel in the traversable area.

[0093] The target path is the travel path of the tunnel inspection device on the ground of the cable tunnel.

[0094] For example, a spline interpolation algorithm (such as B-spline or cubic spline interpolation) may be used to smooth the initial path to generate a smooth target path.

[0095] For example, the target path may be mapped to a two-dimensional grid map to verify whether it is completely within the traversable area. If the target path collides with an obstacle, smoothing is performed again until the target path is completely within the traversable area.

[0096] In the technical solution provided in the embodiment of the present application, a combination of random sampling and guide node guided sampling is adopted to construct the initial path of the cable tunnel ground in the passable area. This not only avoids the problem of many unnecessary turning points in the initial path when only random sampling is used to construct the initial path, but also avoids the problem of being unable to cross obstacles when only guide node guided sampling is used to construct the initial path. This can reduce the number of turning points in the initial path while avoiding obstacles, thereby reducing the energy consumption and control difficulty of the tunnel inspection device; and, by smoothing the initial path, the target path of the cable tunnel ground in the passable area is obtained, which can further reduce the number of turning points in the initial path.

[0097] Figure 2 A schematic flow chart of a path planning method for a cable tunnel ground provided in the second embodiment is shown as follows: Figure 2 As shown, the method is applied to a computer device, Figure 2 Example compared to Figure 1 The difference between the embodiments is that S102 includes S1021 to S1023.

[0098] S1021 : Sample multiple feature points from the initial skeleton line according to a preset step size, and determine the target curvature of each feature point.

[0099] For example, the preset step size is set according to actual needs. The smaller the step size, the denser the sampling points, the higher the calculation accuracy, but the greater the amount of calculation. For example, the multiple feature points sampled can be numbered according to the sampling order from the initial skeleton line to facilitate subsequent processing. In this way, each feature point has a sequence number.

[0100] For example, the curvature of the first and last feature points among the multiple feature points may be 0. The curvature of each feature point other than the first and last feature points among the multiple feature points may be determined based on the coordinates of the feature point, a feature point before the feature point, and a feature point after the feature point.

[0101] S1022: Determine a feature point of a target curvature that is greater than or equal to a preset curvature as a key turning point.

[0102] The preset curvature threshold can be set according to actual needs. For example, the smaller the preset curvature threshold, the more feature points there are in the key turning point, and thus the more accurate the initial path construction is, and the higher the computing power required by the computer equipment.

[0103] S1023. Remove redundant turning points from key turning points to obtain guiding nodes.

[0104] Exemplarily, the characteristic points in the key turning points can be traversed to identify redundant turning points. Exemplarily, if the distance between two characteristic points with adjacent numbers in the key turning points is less than or equal to a preset distance, one of the turning points is marked as a redundant turning point. Exemplarily, if the curvature trends of multiple characteristic points with adjacent numbers in the key turning points are similar, the turning point with the largest curvature is retained, and the remaining turning points are marked as redundant turning points. The starting and ending points in the cable tunnel area to be inspected cannot be redundant turning points.

[0105] By removing redundant turning points from the multiple feature points included in the key turning point, all remaining feature points are determined as guide nodes. For example, each feature point in the guide node can be numbered to facilitate subsequent processing. For example, each feature point in the guide node can be numbered in ascending order of the feature point retention order.

[0106] In the technical solution provided in the embodiment of the present application, by determining the target curvature of each feature point, the local shape change of the initial skeleton line can be quantified, providing an accurate basis for the identification of key turning points. By screening feature points with preset curvature, the points where the direction of the initial skeleton line changes significantly can be accurately identified, avoiding missing important turning points, and ensuring the integrity and accuracy of the determined key turning points; and by removing redundant turning points, the number of guide nodes can be reduced, and the computational complexity of path planning can be reduced; after removing redundant turning points, the generated path is smoother, unnecessary direction changes are reduced, and the number of turning points in the initial path can be reduced.

[0107] In some embodiments, redundant turning points in key turning points are removed to obtain a guiding node, including: determining the first feature point in the key turning points as the first current feature point; when the distance between the next feature point of the current feature point and the current feature point is greater than a preset distance, determining the next feature point as the new current feature point; when the distance between the next feature point and the current feature point is less than or equal to a preset distance, deleting the next feature point as a redundant turning point, and determining the next feature point after the redundant turning point as the new next feature point; repeating the above steps until the last feature point in the key turning points is obtained, and determining the retained feature point as the guiding node.

[0108] For example, the key turning point includes N feature points, each of the N turning points has its own serial number, N is an integer greater than or equal to 2, the first feature point among the key turning points is determined as the current feature point, when the distance between the second feature point and the current feature point (the current feature point at this time is the first feature point) is greater than the preset distance, the second feature point is determined as the new current feature point, when the distance between the third feature point and the current feature point (the current feature point at this time is the second feature point) is less than or equal to the preset distance, the third feature point is deleted as a redundant turning point, and then when the distance between the fourth feature point and the current feature point (the current feature point at this time is the second feature point) is less than or equal to the preset distance, the fourth feature point is deleted as a redundant turning point, and then when the distance between the fifth feature point and the current feature point (the current feature point at this time is the second feature point) is greater than the preset distance, the fifth feature point is determined as the new current feature point, and so on, until the Nth feature point is obtained, the retained feature points are determined as guide nodes.

[0109] In the technical solution provided in the embodiment of the present application, by determining whether the next feature point of the current feature point is a redundant turning point based on a preset distance, redundant turning points can be removed quickly and efficiently, the number of guiding nodes can be reduced, and the efficiency of removing redundant turning points can be improved.

[0110] Figure 3 A schematic flow chart of a method for planning a path on the ground of a cable tunnel provided in the third embodiment is shown in FIG. Figure 3 As shown, the method is applied to a computer device, Figure 3 Example compared to Figure 1 The difference between the embodiments is that S103 includes S1031 to S1035.

[0111] S1031. Obtain a starting position point and an ending position point in the cable tunnel area to be inspected, and determine the starting position point as the first current path point.

[0112] For example, the starting point and the ending point in the cable tunnel area to be inspected can be determined by user input, sensor data or map analysis, and the starting point and the ending point represent the starting point and the end point of the inspection task respectively.

[0113] In this embodiment of the present application, the first current path point is used as the starting point of path planning.

[0114] S1032: When the current path point finally obtained is in a safe area, the next path point is explored by using a guide node guided sampling method.

[0115] The safe area is an area where the minimum distance to obstacles is greater than a predetermined distance; the obstacle is an area outside the passable area in the two-dimensional grid map.

[0116] For example, the minimum distance between the current path point and the obstacle may be determined, and when the minimum distance is greater than a predetermined distance, it is determined that the current path point is in a safe area.

[0117] S1033. When the current path point finally obtained is not in a safe area, a random sampling method is used to explore the next path point.

[0118] In some embodiments, exploring the next path point by random sampling may include randomly selecting an exploration direction, moving the current path point toward the exploration direction by a sampling step, and exploring the next path point.

[0119] S1034. Determine the next path point as the new current path point.

[0120] In this way, the next path point explored is marked as the new current path point, which serves as the basis for the next path planning.

[0121] After S1034 , S1032 or S1033 may be executed.

[0122] S1035. Until the distance between the current path point and the terminal position point is less than the sampling step, an initial path of the cable tunnel ground in the passable area is constructed based on all the current path points and terminal position points that have been obtained.

[0123] In some embodiments, all the acquired current path points and the end position point may be connected in sequence according to the sequence of each current path point and the end path point to obtain an initial path.

[0124] For example, the starting position point in the cable tunnel area to be inspected is taken as the first current path point. When the latest current path point is in a safe area, the next path point is explored by guiding the sampling of the guide node, and the next path point is determined as the new current path point. When the latest current path point is not in a safe area, the next path point is explored by random sampling, and the next path point is determined as the new current path point. In this way, each time a current path point is obtained, it is determined whether the current path point is in a safe area to explore the next path point, until the distance between the last current path point and the end position point is less than the sampling step size, and the exploration is stopped.

[0125] In the technical solution provided by the embodiment of the present application, when the current path point obtained at the end is in a safe area, the next path point is explored by using a guide node guided sampling method, thereby reducing the risk of collision with obstacles, reducing the blindness of random exploration, improving the efficiency and accuracy of path planning, and being able to reduce the number of turning points in the initial path. When the current path point obtained at the end is not in a safe area, the next path point is explored by using a random sampling method, thereby exploring path points in a wider area, increasing the possibility of finding a feasible path, and improving the effectiveness of path planning.

[0126] In some embodiments, a guide node-guided sampling method is used to explore the next path point, including: when the distance between the last obtained current path point and the corresponding matching feature point in the guide node is greater than or equal to the set distance, the current path point is moved by the sampling step toward the matching feature point to obtain the next path point; when the distance between the last obtained current path point and the corresponding matching feature point in the guide node is less than the set distance, the current path point is moved by the sampling step toward the next feature point of the matching feature point in the guide node to obtain the next path point; wherein the corresponding matching feature point is the feature point with the smallest sequence number among at least one feature point in the guide node that has been obtained but not passed by the current path point.

[0127] Here, the process of determining the matching feature points corresponding to the last obtained current path point is exemplarily described: exemplarily, when the last obtained current path point is the starting position point, the last obtained current path point will not pass through any feature point in the guide node, then the first feature point in the guide node is determined as the matching feature point of the last obtained current path point. As another example, when the last obtained current path point is not the starting position point, the obtained current path point has multiple path points, then when it is determined that the distance between the obtained current path point and the first part of the feature points in the guide node is less than or equal to the specified distance threshold, it is determined that the obtained current path point passes through these first part of the feature points, and when it is determined that the distance between the obtained current path point and the second part of the feature points in the guide node is greater than the specified distance threshold, it is determined that the obtained current path point does not pass through these second part of the feature points, wherein the feature point with the smallest sequence number in the second part of the feature points is determined as the matching feature point of the last obtained current path point.

[0128] In some embodiments, the sampling step size may be fixed. In other embodiments, the sampling step size may be an extended step size (or a dynamically adjustable step size). If the current path point is determined to be within a safe area multiple times in a row, the sampling step size may be increased. If the current path point is determined to be outside a safe area multiple times in a row, the sampling step size may be decreased.

[0129] In the technical solution provided in the embodiment of the present application, the moving direction is dynamically adjusted according to the distance between the current path point and the matching feature point, so as to adapt to different situations in complex environments and improve the adaptability of path planning.

[0130] In some embodiments, random sampling is used to explore the next path point, including: randomly generating a first random point in a two-dimensional grid map, and moving the final current path point toward the first random point by a sampling step to explore the target path point; when the angle between the direction of the final current path point pointing to the target path point and a preset direction is greater than or equal to the preset angle, obtaining at least one acquired current path point in an area with a preset radius with the target path point as the center, and determining the next path point based on the target path point and the at least one acquired current path point; when the angle between the direction of the final current path point pointing to the target path point and the preset direction is less than the preset angle, determining the target path point as the next path point.

[0131] In some embodiments, moving the final current path point by the sampling step size toward the direction of the first random point to explore the target path point can include: moving the final current path point by the sampling step size toward the direction of the first random point to obtain a first designated path point, and when the first designated path point is in a passable area, determining the first designated path point as the target path point; when the first designated path point is not in the passable area, randomly generating a third random point in the two-dimensional grid map, and moving the final current path point by the sampling step size toward the direction of the third random point to obtain a second designated path point, and when the second designated path point is in the passable area, determining the second designated path point as the target path point.

[0132] For example, the preset direction may be the direction of the X-axis or the Y-axis in a two-dimensional grid map.

[0133] In some embodiments, determining the next path point based on the target path point and at least one acquired current path point may include: determining the angles between the direction of each acquired current path point pointing to the target path point and a preset direction, determining an acquired current path point corresponding to the minimum angle as the new parent node of the target path point, deleting the path points between the new parent node of the target path point and the target path point, and determining the target path point as the next path point.

[0134] In some embodiments, the preset radius may be the closest distance between the target path point and the obstacle. In some embodiments, the preset radius may be K times the sampling step size. For example, K is an integer greater than or equal to 1. For example, K is 1, 2, 3, or 5.

[0135] In the technical solution provided in the embodiment of the present application, by comparing the angle between the direction of the current path point pointing to the target path point and the preset direction with the preset angle, the next path point is determined in different ways based on different comparison results, thereby making the determination of the next path point more effective.

[0136] In some embodiments, the next path point is determined based on the target path point and at least one acquired current path point, including: determining each angle between the direction of each acquired current path point pointing to the target path point and a preset direction; in the case where there is at least one angle less than or equal to the preset angle among the angles, determining an acquired current path point corresponding to the minimum angle of the at least one angle as the new parent node of the target path point, or determining the first explored path point among the at least one acquired current path point corresponding to the at least one angle as the new parent node of the target path point, deleting the path points between the new parent node of the target path point and the target path point, and determining the target path point as the next path point; in the case where all angles are greater than the preset angle, randomly generating a second random point in the two-dimensional grid map, moving the last obtained current path point by a sampling step in the direction of the second random point, exploring a new target path point, and determining the next path point based on the new target path point.

[0137] Exemplarily, the method of moving the final current path point toward the second random point by the sampling step to explore a new target path point, and determining the next path point based on the new target path point can be similar to the method of moving the final current path point toward the first random point by the sampling step to explore the target path point, and determining the next path point based on the target path point, which will not be described in detail.

[0138] In the technical solution provided by the embodiments of the present application, by determining an acquired current path point corresponding to the minimum angle among at least one angle as the new parent node of the target path point, or determining the first explored path point among at least one acquired current path point corresponding to at least one angle as the new parent node of the target path point, deleting the path points between the new parent node of the target path point and the target path point, and determining the target path point as the next path point, unnecessary path points between the new parent node of the target path point and the target path point can be deleted, thereby improving the effectiveness of path planning.

[0139] Figure 4 A schematic flow chart of a method for planning a path on the ground of a cable tunnel provided in the fourth embodiment is shown in FIG. Figure 4 As shown, the method is applied to a computer device, Figure 4 Example compared to Figure 1 The difference between the embodiments is that S104 includes S1041 to S1042.

[0140] S1041. Sampling is performed on the initial path at preset intervals to obtain multiple control points.

[0141] The number of the multiple control points is greater than the number of the multiple path points used to construct the initial path.

[0142] The preset interval may be a fixed interval. Two adjacent control points sampled successively between multiple control points.

[0143] S1042. According to preset boundary conditions, a spline curve is used to fit multiple control points to obtain a target path of the cable tunnel ground in the passable area.

[0144] The boundary conditions include: the first-order derivative and the second-order derivative of the starting point of the target path are both 0, and the first-order derivative and the second-order derivative of the ending point of the target path are both 0.

[0145] In other embodiments, the boundary conditions may include: P0=2P1-P2, P n+1 =2P n -P n-1 , where P0, P1, and P2 represent the coordinates of the first, second, and third feature points, respectively. n+1 、P n 、P n-1 They represent the coordinates of the last feature point, the second to last feature point, and the third to last feature point respectively.

[0146] In the technical solution provided in the embodiment of the present application, the number of multiple control points is greater than the number of multiple path points used to construct the initial path, so that the number of control points can be increased, which is conducive to improving the accuracy of fitting; and, by setting the first-order derivative and the second-order derivative of the starting position point of the target path to 0, the first-order derivative and the second-order derivative of the ending position point of the target path are both 0, thereby meeting the starting operation angle and the ending operation angle of the tunnel inspection device, and improving the adaptability of the target path to the actual operation of the tunnel inspection device.

[0147] Figure 5 A schematic flow chart of a method for planning a path on the ground of a cable tunnel provided in the fifth embodiment is shown in FIG. Figure 5 As shown, the method is applied to a computer device, and the method includes the following steps:

[0148] S501: extracting an initial skeleton line of a traversable area in a two-dimensional grid map of a cable tunnel area to be inspected.

[0149] S502: Extracting a guide node for guiding the direction of path exploration from the initial skeleton line.

[0150] S503: Determine the starting point as the first current path point.

[0151] S504: Determine whether the distance between the current path point and the end position point is less than the sampling step size.

[0152] If the distance between the current path point and the end position point is less than the sampling step, S515 is executed.

[0153] If the distance between the current path point and the final location point is greater than or equal to the sampling step length, then S505 is executed.

[0154] S505: Determine whether the current path point finally obtained is in a safe area.

[0155] When the current path point finally obtained is in the safe area, S506 and S507 are executed. When the current path point finally obtained is not in the safe area, S508 to S514 and S507 are executed.

[0156] S506: Use the guide node to guide the sampling method to explore the next path point.

[0157] S507: Determine the next path point as the new current path point.

[0158] After S507 , the process goes to S504 .

[0159] S508: Select random sampling to explore the target path point.

[0160] S509: Determine whether the target path point is within the passable area.

[0161] If the target path point is within the passable area, execute S510 ; if the target path point is not within the passable area, go to execute S508 .

[0162] S510: Determine whether the target path point meets the angle restriction.

[0163] Among them, when the angle between the direction of the current path point pointing to the target path point and the preset direction is less than the preset angle, it is determined that the angle restriction is met; otherwise, when the angle between the direction of the current path point pointing to the target path point and the preset direction is greater than or equal to the preset angle, it is determined that the angle restriction is not met.

[0164] If the target path point satisfies the angle restriction, S507 is executed. If the target path point does not satisfy the angle restriction, S512 is executed.

[0165] S511: Acquire at least one current path point in an area with a preset radius and a target path point as the center.

[0166] S512: Determine whether at least one acquired current path point meets the angle restriction.

[0167] When there is at least one angle among the angles that is less than or equal to the preset angle, it is determined that at least one acquired current path point meets the angle restriction; when all the angles are greater than the preset angle, it is determined that at least one acquired current path point does not meet the angle restriction.

[0168] If the current path point that has been obtained meets the angle restriction, S513 is executed. If the current path point that has been obtained does not meet the angle restriction, S508 is executed.

[0169] S513. Determine a new parent node of the target path point based on at least one acquired current path point, delete the path points between the new parent node of the target path point and the target path point, and determine the target path point as the next path point.

[0170] S504 is executed after S513.

[0171] S514: Construct an initial path of the cable tunnel ground in the traversable area based on all the acquired current path points and end position points.

[0172] S515: Smoothing the initial path to obtain a target path on the ground of the cable tunnel in the traversable area.

[0173] The algorithm corresponding to the above steps S504 to S514 may be an improved RRT algorithm (an improved method of the RRT algorithm).

[0174] In some embodiments, a watershed algorithm is used to obtain a skeleton of the map using a known grid map and the location information of the starting and target points. This skeleton is then processed to generate guide nodes. These guide nodes are used as segmentation points, dividing the path planning process into multiple sub-stages. These guide nodes are then used sequentially to guide the sampling points toward the target area. The guide nodes extracted from the map can accurately reflect the location information and directional characteristics of the traversable area between the starting and target points.

[0175] In some embodiments, the use of guidance nodes in this strategy demonstrates significant advantages when tunnel inspection devices navigate narrow roads or face complex obstacles. They effectively guide the algorithm to avoid ineffective areas, reducing search and sampling waste in these areas, significantly improving path planning efficiency.

[0176] Figure 6 A schematic diagram of a two-dimensional grid map provided for some embodiments, Figure 7 A schematic diagram of an initial skeleton line of a traversable area in a two-dimensional grid map provided in some embodiments, Figure 8 A schematic diagram of a guide node extracted from an initial skeleton line provided in some embodiments. The guide node is Figure 8 Points A1, A2, A3 and A4.

[0177] Figure 9 A schematic diagram of three path points that meet the angle constraint is provided for some embodiments, such as Figure 9 As shown, the path points B1, B2, and B3 are generated successively. The angle θ1 between the direction of the path point B1 pointing to the path point B2 and the preset direction is less than or equal to the preset angle. The angle θ2 between the direction of the path point B2 pointing to the path point B3 and the preset direction is less than or equal to the preset angle.

[0178] Figure 10 A schematic diagram of a method for obtaining the next path point when the angle restriction is not satisfied provided in some embodiments, such as Figure 10 As shown, the current path points obtained include D, E, F, and G, and the target path point is H. When the angle θ3 between the direction of G pointing to H and the preset direction is greater than or equal to the preset angle, there is at least one current path point E and G obtained in the area with H as the center and the preset radius, and the angle θ4 between the direction of E pointing to H and the preset direction is less than the preset angle. At this time, E is used as the previous node (parent node) of H, and F and G between E and H are deleted, and node H is used as the next path point.

[0179] When a path only satisfies the continuity of position points but fails to ensure smoothness and satisfy curvature constraints, it will lead to discontinuous motion and poor trajectory tracking. To overcome these difficulties, the embodiment of the present application uses a third-order quasi-uniform B-spline curve to optimize the path, aiming to generate a smooth operating trajectory that meets the robot's maximum curvature constraint.

[0180] The curvature of the target path at both ends must be 0 at the start and end stages.

[0181] The core of the improved RRT algorithm based on the watershed algorithm and the guide node guidance strategy proposed in the embodiment of the present application is to first extract the skeleton points in the grid map and extract the guide nodes to guide the direction of path exploration. For example, when the guide node guidance sampling strategy is adopted, the generation of path points will tend to be towards these preset guide nodes. In the random sampling mode, the algorithm randomly generates path points and immediately performs collision detection and angle constraint verification. For those sampling points that fail to meet the angle constraint conditions, the algorithm will adopt an expansion strategy, that is, explore other potential parent nodes and reapply the angle constraint verification. This process will be iterated until a sampling point that can reach the target position is successfully generated. Finally, the algorithm will backtrack the entire exploration process and construct the initial path. In order to further improve the smoothness of the path, a cubic B-spline curve is used to smooth it, thereby obtaining a path that meets the kinematic constraints of the tunnel inspection device and has a high degree of smoothness.

[0182] The improved RRT algorithm in this application's examples was compared with the traditional RRT algorithm, the goal-bias RRT algorithm, the RRT_connect algorithm, and the Informed RRT* algorithm. To effectively mitigate the impact of randomness in the experimental results, each algorithm was independently run 100 times under each environmental condition. The average number of iterations, average path length, average planning time, and success rate were used as key indicators to evaluate path planning performance.

[0183] Based on the conditions of an underground tunnel, a simplified 50×30 rectangular area was created as a simulation map, and corresponding obstacles were placed on the simulation map for testing. This experiment aimed to further explore and compare the path planning efficiency and effectiveness of existing algorithms and the proposed algorithm in narrow and long spaces. To verify the algorithm's planning performance in narrow and long spaces, a narrow and long space test scenario was designed.

[0184] Figure 11 This is a schematic diagram of the target path obtained by the traditional RRT algorithm. Due to the blind sampling characteristics of the RRT algorithm, the generated path is often tortuous and complex and contains many redundant nodes.

[0185] Figure 12 Schematic diagram of the target path obtained by the goal-biased RRT. The Goal-bias RRT algorithm effectively reduces the generation of redundant nodes by introducing a goal-oriented strategy, but the path quality still needs to be improved.

[0186] Figure 13 This is a schematic diagram of the target path obtained by the RRT connection algorithm. The RRT connection algorithm is effective when there are no obstacles in the middle, but it is still difficult to bypass wider obstacles.

[0187] Figure 14 This is a schematic diagram of the target path obtained by the Informed RRT* algorithm. After generating the initial path, the algorithm further improves the path quality by iteratively optimizing within the elliptical area. However, this optimization process also increases the algorithm's time consumption accordingly.

[0188] Figure 15 This is a schematic diagram of the target path obtained by extracting the initial skeleton line and improving the RRT algorithm. This algorithm combines a guided node-based approach with a region-based sampling strategy to quickly find a path while significantly reducing redundant nodes and iterations. Furthermore, its improved angle constraints ensure smoothness of the planned path, making it an excellent choice for path planning and optimization.

[0189] Table 1 is a performance diagram of various algorithms provided in some embodiments.

[0190] Table 1

[0191]

[0192] Table 1 shows that in the narrow tunnel scenario, the initial skeleton line extraction and improved RRT algorithms demonstrate significant advantages in planning time, number of iterations, and path quality compared to the traditional RRT algorithm, Goal-bias RRT algorithm, RRT_connect algorithm, and Informed RRT* algorithm. Furthermore, the path is close to the centerline of the road, making it very user-friendly for tunnel inspection equipment.

[0193] The initial skeleton line extraction and improved RRT algorithm proposed in the embodiment of the present application have achieved significant improvements in multiple key performance indicators such as planning time, number of iterations and path length. Although its path length is not the shortest, the gap is kept within a smaller range compared with similar algorithms. Therefore, this algorithm has demonstrated more outstanding performance in reducing the number of iterations, shortening the planning cycle and improving path smoothness. Most importantly, when performing path planning, this algorithm always stays in the middle area of the obstacle, avoiding collisions with obstacles to the greatest extent. In summary, the improved RRT algorithm based on the watershed algorithm and the guide node guidance strategy has demonstrated its efficiency, accuracy and reliability in narrow spaces.

[0194] Based on the same inventive concept, an embodiment of the present application further provides a cable tunnel ground path planning device for implementing the cable tunnel ground path planning method involved above. The implementation solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more cable tunnel ground path planning device embodiments provided below can be referred to the limitations of the cable tunnel ground path planning method above, and will not be repeated here.

[0195] In an exemplary embodiment, Figure 16 A schematic diagram of a cable tunnel ground path planning device provided in some embodiments of the present application, such as Figure 16 As shown, the cable tunnel ground path planning device 1600 includes:

[0196] The skeleton line determination unit 1601 is used to extract the initial skeleton line of the passable area in the two-dimensional grid map of the cable tunnel area to be inspected;

[0197] A guide node determining unit 1602 is configured to extract a guide node for guiding the direction of path exploration from the initial skeleton line;

[0198] An initial path determination unit 1603 is configured to construct an initial path of the cable tunnel ground in the traversable area by combining random sampling and guided sampling by a guide node;

[0199] The target path determining unit 1604 is configured to smooth the initial path to obtain a target path on the cable tunnel floor in the traversable area; the target path is the travel path of the tunnel inspection device on the cable tunnel floor.

[0200] The description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0201] Each module in the above-mentioned cable tunnel ground path planning device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0202] In an exemplary embodiment, Figure 17This is a schematic diagram of the structure of a computer device provided in some embodiments. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and computer program stored in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. The wireless communication method can be implemented via wireless fidelity (Wi-Fi), a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for path planning on the ground surface of a cable tunnel. The display unit of the computer device is used to produce a visual image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0203] Those skilled in the art will understand that Figure 17 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0204] For example, a computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method of any of the above embodiments when executing the computer program.

[0205] For example, in an exemplary embodiment, the processor is used to execute a computer program to implement: extracting the initial skeleton line of the passable area in the two-dimensional grid map of the cable tunnel area to be inspected; extracting the guide nodes for guiding the direction of path exploration from the initial skeleton line; constructing the initial path of the cable tunnel ground in the passable area by combining random sampling and guide node guided sampling; smoothing the initial path to obtain the target path of the cable tunnel ground in the passable area; the target path is the driving path of the tunnel inspection device on the cable tunnel ground.

[0206] In one embodiment, a computer-readable storage medium is provided, and when a computer program is executed by a processor, the computer program implements the steps of the method provided in any of the above embodiments.

[0207] For example, in an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: extracting the initial skeleton line of the passable area in the two-dimensional grid map of the cable tunnel area to be inspected; extracting the guide nodes for guiding the direction of path exploration from the initial skeleton line; constructing the initial path of the cable tunnel ground in the passable area by combining random sampling and guide node guided sampling; smoothing the initial path to obtain the target path of the cable tunnel ground in the passable area; the target path is the driving path of the tunnel inspection device on the cable tunnel ground.

[0208] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of the method provided in any of the above embodiments are implemented.

[0209] For example, in an exemplary embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the following steps: extracting an initial skeleton line of a traversable area in a two-dimensional grid map of a cable tunnel area to be inspected; extracting guide nodes for guiding the direction of path exploration from the initial skeleton line; constructing an initial path of the cable tunnel ground in the traversable area by combining random sampling and guide node guided sampling; smoothing the initial path to obtain a target path of the cable tunnel ground in the traversable area; the target path is the driving path of a tunnel inspection device on the cable tunnel ground.

[0210] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0211] The processor, each functional module or each functional unit in any embodiment of the present application may include any one or more of the following integrations: a general-purpose processor, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a graphics processing unit (GPU), an embedded neural network processing unit (NPU), a controller, a microcontroller, a microprocessor, a programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, a data processing logic based on quantum computing, an artificial intelligence (AI) processor, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0212] The memory or computer-readable storage medium in any embodiment of the present application may include at least one of a non-volatile memory and a volatile memory. Non-volatile memory includes the integration of one or more of the following: Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory, Magnetic Surface Storage, Optical Disc, Compact Disc Read-Only Memory (CD-ROM), Magnetic Tape, Floppy Disk, Flash Memory, Optical Storage, High-density Embedded Non-volatile Memory, Resistive Random Access Memory (ReRAM), Magnetoresistive Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), Graphene Memory, Volatile Memory, etc. Volatile memory includes one or more of the following: random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can come in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0213] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0214] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A path planning method for a cable tunnel ground, characterized in that: The method comprises: Extracting the initial skeleton line of the passable area in the two-dimensional grid map of the cable tunnel area to be inspected; Extracting a guide node for guiding the direction of path exploration from the initial skeleton line; Constructing an initial path of the cable tunnel ground in the traversable area by combining random sampling and the guide node guided sampling; The initial path is smoothed to obtain a target path of the cable tunnel ground in the traversable area; the target path is a travel path of a tunnel inspection device on the cable tunnel ground.

2. The method according to claim 1, characterized in that The step of extracting a guide node for guiding the direction of path exploration from the initial skeleton line includes: Sampling a plurality of feature points from the initial skeleton line according to a preset step size, and determining a target curvature of each feature point; Determine a characteristic point of a target curvature greater than or equal to a preset curvature as a key turning point; Redundant turning points in the key turning points are removed to obtain the guiding node.

3. The method according to claim 2, characterized in that The removing of redundant turning points from the key turning points to obtain the guiding node includes: Determine the first feature point among the key turning points as the first current feature point; When the distance between the next feature point of the current feature point and the current feature point is greater than a preset distance, the next feature point is determined as a new current feature point; If the distance between the next feature point and the current feature point is less than or equal to the preset distance, the next feature point is deleted as a redundant turning point, and the feature point after the redundant turning point is determined as the new next feature point; The above steps are repeated until the last feature point in the key turning point is obtained, and the retained feature point is determined as the guiding node.

4. The method according to any one of claims 1 to 3, characterized in that The method of constructing the initial path of the cable tunnel ground in the traversable area by combining random sampling and guided sampling by the guide node includes: Obtaining a starting position point and an ending position point in the cable tunnel area to be inspected, and determining the starting position point as the first current path point; When the current path point finally obtained is in a safe area, the next path point is explored by using the guide node guided sampling method; wherein the safe area is an area where the minimum distance to obstacles is greater than a predetermined distance; and the obstacle is an area outside the passable area in the two-dimensional grid map; When the current path point finally obtained is not in the safe area, the next path point is explored by using the random sampling method; determining the next waypoint as a new current waypoint; Repeat the above steps until the distance between the current path point and the end position point is less than the sampling step size, and construct the initial path of the cable tunnel ground in the passable area based on all the current path points and the end position points that have been obtained.

5. The method according to claim 4, characterized in that The method of exploring the next path point by using the guide node to guide sampling includes: When the distance between the current path point finally obtained and the corresponding matching feature point in the guide node is greater than or equal to the set distance, the current path point is moved by the sampling step length toward the matching feature point to obtain the next path point; When the distance between the current path point finally obtained and the corresponding matching feature point in the guide node is less than the set distance, the current path point is moved by the sampling step length toward the direction of the next feature point of the matching feature point in the guide node to obtain the next path point; The corresponding matching feature point is the feature point with the smallest sequence number among at least one feature point that has been obtained but not passed by the current path point in the guide node.

6. The method according to claim 4, characterized in that The step of exploring the next path point by random sampling includes: Randomly generating a first random point in the two-dimensional grid map, and moving the final current path point toward the first random point by the sampling step length to explore the target path point; If the angle between the direction of the current path point pointing to the target path point and the preset direction is greater than or equal to the preset angle, obtaining at least one current path point that has been obtained in an area with a preset radius and centered on the target path point, and determining the next path point based on the target path point and the at least one current path point that has been obtained; When the angle between the direction of the current path point pointing to the target path point and the preset direction is smaller than the preset angle, the target path point is determined as the next path point.

7. The method according to claim 6, characterized in that The determining a next path point according to the target path point and the at least one acquired current path point includes: Determining angles between the directions of the acquired current path points pointing to the target path points and the preset directions; If at least one angle among the angles is less than or equal to a preset angle, determining an acquired current path point corresponding to a minimum angle among the at least one angle as a new parent node of the target path point, or determining a path point that is first explored among at least one acquired current path point corresponding to each of the at least one angle as a new parent node of the target path point, deleting the path points between the new parent node of the target path point and the target path point, and determining the target path point as the next path point; When all of the angles are greater than the preset angle, a second random point is randomly generated in the two-dimensional grid map, the current path point finally obtained is moved in the direction of the second random point by the sampling step size, a new target path point is explored, and the next path point is determined based on the new target path point.

8. The method according to any one of claims 1 to 3, characterized in that The smoothing process on the initial path to obtain a target path of the cable tunnel ground in the traversable area includes: Sampling the initial path at preset intervals to obtain a plurality of control points; wherein the number of the plurality of control points is greater than the number of the plurality of path points used to construct the initial path; According to preset boundary conditions, a spline curve is used to fit the multiple control points to obtain a target path of the cable tunnel ground in the passable area; wherein the boundary conditions include: the first-order derivative and the second-order derivative of the starting position point of the target path are both 0, and the first-order derivative and the second-order derivative of the ending position point of the target path are both 0.

9. A path planning device for a cable tunnel, characterized in that: The device comprises: A skeleton line determination unit is used to extract the initial skeleton line of the passable area in the two-dimensional grid map of the cable tunnel area to be inspected; a guiding node determining unit, configured to extract a guiding node for guiding the direction of path exploration from the initial skeleton line; An initial path determining unit, configured to construct an initial path of the cable tunnel ground in the traversable area by combining random sampling and guided sampling by the guide node; The target path determination unit is used to smooth the initial path to obtain a target path of the cable tunnel ground in the passable area; the target path is the driving path of the tunnel inspection device on the cable tunnel ground.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images