Path planning method, device and electronic equipment

Abstract

The present disclosure provides a path planning method and device and electronic equipment, and relates to the technical field of data processing. The method comprises: obtaining a local three-dimensional model corresponding to a forest fire spreading area in a forest area to be extinguished; wherein the local three-dimensional model is used to indicate the spatial position of the forest fire spreading area; obtaining a position space of a fire extinguishing personnel in the forest area to be extinguished, wherein the position space is used to indicate the movable position and / or movable direction of the fire extinguishing personnel; determining a target manifold space according to the position space and the local three-dimensional model; and performing path search from the target manifold space to obtain a target planning path between a starting point and a target point of the fire extinguishing personnel. Thus, the path for the fire extinguishing personnel to go to the specified target point in the forest fire scene can be planned, that is, the path for the fire extinguishing personnel to perform the forest fire extinguishing operation task is reasonably planned to avoid the threat of the fire scene and improve the fire extinguishing efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a path planning method, apparatus and electronic device. Background Technology

[0002] Forest fires typically occur in mountainous areas far from cities. These areas often lack proper roads, making them difficult for rescue and firefighting personnel to access. Furthermore, firefighters are frequently threatened by extreme environmental factors such as flames, smoke, and treacherous terrain. Therefore, in the complex environment of forest fire spread, quickly finding relatively safe routes is crucial for ensuring the efficient and safe operation of firefighters. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] This disclosure proposes a path planning method, device, and electronic equipment to plan the travel path for firefighters to a designated target point in a forest fire scenario. In other words, it enables firefighters to rationally plan their paths during forest fire fighting operations to avoid fire threats and improve fire fighting efficiency.

[0005] The first aspect of this disclosure proposes a path planning method, including:

[0006] Obtain a local 3D model corresponding to the forest fire spread area in the forest area to be extinguished; wherein, the local 3D model is used to indicate the spatial location of the forest fire spread area;

[0007] Obtain the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters;

[0008] The target manifold space is determined based on the configuration space and the local three-dimensional model;

[0009] A path search is performed from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters' movement.

[0010] The path planning method of this disclosure involves obtaining a local 3D model corresponding to the forest fire spread area in the forest area to be extinguished; wherein the local 3D model is used to indicate the spatial location of the forest fire spread area; obtaining the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters; determining the target manifold space based on the configuration space and the local 3D model; and performing a path search from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters. Therefore, in a forest fire scenario, it is possible to plan the travel path for firefighters to a designated target point, that is, to rationally plan the path for firefighters in performing forest fire fighting operations, so as to avoid fire threats and improve fire fighting efficiency.

[0011] A second aspect of this disclosure provides a path planning apparatus, comprising:

[0012] The first acquisition module is used to acquire a local three-dimensional model corresponding to the forest fire spread area in the forest area to be extinguished; wherein, the local three-dimensional model is used to indicate the spatial location of the forest fire spread area;

[0013] The second acquisition module is used to acquire the positional space of the firefighters in the forest area to be extinguished, wherein the positional space is used to indicate the movable position and / or movable direction of the firefighters.

[0014] The determination module is used to determine the target manifold space based on the configuration space and the local three-dimensional model;

[0015] The search module is used to perform path search from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters' movement.

[0016] The path planning device of this embodiment acquires a local three-dimensional model corresponding to the forest fire spread area in the forest area to be extinguished; wherein the local three-dimensional model is used to indicate the spatial location of the forest fire spread area; acquires the configuration space of the firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters; determines the target manifold space based on the configuration space and the local three-dimensional model; and performs a path search from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters. Therefore, in a forest fire scenario, it is possible to plan the travel path for firefighters to a designated target point, that is, to rationally plan the path for firefighters in performing forest fire fighting operations, so as to avoid fire threats and improve fire fighting efficiency.

[0017] A third aspect of this disclosure provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the path planning method as proposed in the first aspect of this disclosure.

[0018] The fourth aspect of this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the path planning method as proposed in the first aspect of this disclosure.

[0019] A fifth aspect of this disclosure provides a computer program product in which, when instructions in the computer program product are executed by a processor, the path planning method as proposed in a first aspect of this disclosure is performed.

[0020] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0022] Figure 1 This is a flowchart illustrating a path planning method provided in an embodiment of the present disclosure.

[0023] Figure 2 This is a schematic diagram of a path search obtained in a forest fire-prone area, as provided in an embodiment of this disclosure.

[0024] Figure 3 This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure;

[0025] Figure 4 This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure;

[0026] Figure 5 These are schematic diagrams illustrating four vertical segmentation scenarios provided in the embodiments of this disclosure;

[0027] Figure 6 This is a schematic diagram of the subdivision results provided in the embodiments of this disclosure;

[0028] Figure 7 This is a schematic diagram of the path topology provided in the embodiments of this disclosure;

[0029] Figure 8 This is a schematic diagram of the target planning path provided in the embodiments of this disclosure;

[0030] Figure 9This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure;

[0031] Figure 10 This is a schematic diagram of the adjusted target planning path provided in an embodiment of the present disclosure;

[0032] Figure 11 This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure;

[0033] Figure 12 This is a schematic diagram of the path search process provided in the embodiments of this disclosure;

[0034] Figure 13 This is a schematic diagram of the overall code framework for path planning provided in the embodiments of this disclosure;

[0035] Figure 14 This is a schematic diagram of the experimental results provided in the embodiments of this disclosure;

[0036] Figure 15 A schematic diagram of fitness change curves for each iteration provided in the embodiments of this disclosure;

[0037] Figure 16 This is a schematic diagram illustrating the implementation principle of the automatic obstacle avoidance motion path planning algorithm provided in the embodiments of this disclosure;

[0038] Figure 17 This is a schematic diagram of the structure of a path planning device provided in an embodiment of the present disclosure. Detailed Implementation

[0039] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0040] The spread of forest fires is a highly complex process, and the trajectory of the fire line affects the firefighters' route planning and firefighting strategies. The direction of fire spread is influenced by factors such as weather conditions and the availability of combustible materials in the forest area.

[0041] Unlike traditional urban road route planning, forest fire fighting route planning is conducted in the absence of roads. Before heading to designated target points in the forest, firefighters need to plan their routes carefully, bypassing the ever-spreading fire and treacherous, steep mountainous terrain to reach relatively safe firefighting sites. However, in real forest fires, firefighters often lack a comprehensive understanding of the fire's spread and are more likely to be trapped within the fire zone during their journey.

[0042] Therefore, in the complex environment of forest fire spread, it is crucial to quickly find relatively safe routes so that firefighters can rationally plan their routes, avoid fire threats, and improve firefighting efficiency during forest fire fighting operations.

[0043] To address the aforementioned problems, this disclosure proposes a path planning method, apparatus, and electronic device.

[0044] The path planning method, apparatus, and electronic device of this disclosure are described below with reference to the accompanying drawings. Before specifically describing the embodiments of this disclosure, commonly used technical terms will be introduced first for ease of understanding:

[0045] Configuration space (or configuration space) is the space of all possible states that a physical system can be in, and it can have external constraints. The configuration space of a typical system has a manifold structure, and therefore it is also called a configuration manifold.

[0046] A cell is a concept in algebraic topology. In this disclosure, it can be understood that a 0-dimensional cell is a point, a 1-dimensional cell is a line segment, a 2-dimensional cell is a topological plane, and a 3-dimensional cell is a topological geometric polyhedron. Furthermore, in the examples of this disclosure, only the definitions and characteristics of 1-, 2-, and 3-dimensional cells are used to determine the manifold space.

[0047] Figure 1 This is a flowchart illustrating a path planning method provided in an embodiment of the present disclosure.

[0048] This disclosure illustrates the example of the path planning method being configured in a path planning device, which can be applied to any electronic device to enable the electronic device to perform path planning functions.

[0049] Among them, electronic devices can be any device with computing capabilities, such as PCs (Personal Computers), mobile terminals, servers, etc. Mobile terminals can be hardware devices with various operating systems, touch screens and / or displays, such as mobile phones, tablets, personal digital assistants, wearable devices, etc.

[0050] like Figure 1 As shown, the path planning method may include the following steps:

[0051] Step 101: Obtain a local 3D model of the forest fire spread area in the forest area to be extinguished; wherein, the local 3D model is used to indicate the spatial location of the forest fire spread area.

[0052] In this embodiment of the disclosure, a local three-dimensional model corresponding to the forest fire spread area in the forest area to be extinguished can be constructed, wherein the local three-dimensional model is used to indicate the spatial location of the forest fire spread area.

[0053] As an example, a real wildfire spread scenario exists in a three-dimensional world, defined as follows: This represents the three-dimensional state space of the forest fire-fighting area for which path planning is to be performed. All subsequent entity modeling is conducted within this three-dimensional state space. In the process.

[0054] Influenced by various environmental factors such as combustibles, temperature, wind speed, and wind direction in the forest area to be extinguished, the spread of forest fires is often irregular. There are two main methods for geometric modeling irregular shapes: 1) boundary representation; 2) solid representation. Based on the actual situation of forest fire spread, this disclosure chooses solid representation to geometrically model the forest fire spread area, providing a set of all spatial points describing the forest fire spread area.

[0055] First, let's explain the geometric modeling in two-dimensional space:

[0056] For a subset of convex polygons in two-dimensional space For any pair of points in a subset, all points on the line segment connecting the pair of points are in that subset. The internal structure of is rigorously mathematically represented as follows:

[0057] For the subset of convex polygons And for λ∈[0,1], we have:

[0058] λx1+(1-λ)x2∈X; (1)

[0059] Assuming the above convex polygon subset consists of m vertices and m edges, given the convex polygon subset in... The vertex sequence in the array is: (x1, y1), (x2, y2), ..., (x m y m If any two points in the vertex sequence form a straight line, the equation of which can be expressed as ax + by + c = 0, where c is a constant. Define function f represents the function given by f(x,y)=ax+by+c, f(x,y)<0 indicates the left side of the line, and f(x,y)>0 indicates the right side of the line.

[0060] Let f i (x, y) represents the distance from (x) to (y). i y i ) to (x i+1 y i+2 Let f be the function generated by the edge of the boundary, where 1 ≤ i ≤ m. m (x, y) represents the process after (x) m ym The line from (x1, y1) to (x1, y1), for 1 ≤ i ≤ m, is a half-plane. Defined as subset of:

[0061]

[0062] In summary, a subset of convex polygons with m edges It can be represented as:

[0063]

[0064] For a set of non-convex polygons It can then be expressed by the following formula:

[0065]

[0066] in, It is a set of half-plane convex polygons represented by formula (3), where 1≤i≤m.

[0067] Secondly, it can extend two-dimensional space to three-dimensional space.

[0068] For three-dimensional state space If we need to replace the aforementioned polygons with polyhedra and the aforementioned half-planes with half-spaces, then the aforementioned concepts can be extended from two dimensions to three dimensions. The boundary of a polyhedron consists of vertices, edges, and faces. Each edge is the boundary between two faces, and each vertex forms three or more boundaries. Assume... As a convex polyhedron, it can be represented by constructing a solid using vertices. Each face has at least three vertices, and the equation of the face passing through these vertices can be expressed by the following formula:

[0069] ax + by + cz + d = 0; (5)

[0070] Where, constant

[0071] Constructing linear functions f(x,y,z)=ax+by+cz+d, let m be The number of faces contained, for Each side, half space Can be defined as subset of:

[0072]

[0073] In summary, a convex polyhedron can be defined as the intersection of the finite number of half-spaces mentioned above:

[0074]

[0075] Furthermore, the spatial set of forest fire spread can be defined. (The local 3D model corresponding to the forest fire spread area in this disclosure) is as follows:

[0076]

[0077] It should be noted that the examples above using polygonal and polyhedral models only exemplify f as a linear function. In practical applications, to more accurately describe the forest fire spread area, f can be extended to a real-valued function, a polynomial with real variables x, y, and z. The length of the fire front can be used as the boundary of the forest fire spread area, and this boundary is closely related to the local three-dimensional model of the forest fire spread area, specifically the variable half-space at time t. It can be defined as:

[0078]

[0079] Variable convex polyhedron at time t It can be defined as:

[0080]

[0081] The spatial set of forest fire spread at time t (referred to in this disclosure as a local three-dimensional model of the forest fire spread region (also known as the time-varying forest fire spread region)). It can be defined as:

[0082]

[0083] Step 102: Obtain the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters.

[0084] In this embodiment of the disclosure, the configuration space of firefighters in the forest area to be extinguished can be obtained, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters, that is, the configuration space is used to indicate the position and / or direction to which the firefighters will move or will move in the future.

[0085] As an example, a configuration space corresponding to firefighters can be defined to indicate the set of spaces in which firefighters will move and transform in the future. The elements in this set can include the future transformations of the firefighters' position, direction, and other movement attributes at a certain moment. The set of all future transformations of the firefighters' movement attributes at that moment is called the configuration space.

[0086] Step 103: Determine the target manifold space based on the configuration space and the local 3D model.

[0087] In this embodiment of the disclosure, the target manifold space can be determined based on the configuration space and the local three-dimensional model. For example, the intersection of the configuration space and the local three-dimensional model can be determined, and the intersection can be removed from the configuration space to obtain the target manifold space.

[0088] Step 104: Perform a path search in the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters.

[0089] The starting point can be the location of the firefighters, and the target point can be the location where the fire needs to be extinguished or the firefighting operation point.

[0090] In this embodiment of the disclosure, a path search can be performed from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters' movement.

[0091] As an example, the forest area awaiting fire suppression and the area where the fire is spreading can be as follows: Figure 2 As shown, a path search can be performed from the target manifold space (such as the area outside the forest fire spread area in the forest area to be extinguished). Assuming that the searched paths are Route 1, Route 2 and Route 3, then the shortest path, Route 2, can be taken as the target planning path.

[0092] The path planning method of this disclosure involves obtaining a local 3D model corresponding to the forest fire spread area in the forest area to be extinguished; wherein the local 3D model is used to indicate the spatial location of the forest fire spread area; obtaining the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters; determining the target manifold space based on the configuration space and the local 3D model; and performing a path search from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters. Therefore, in a forest fire scenario, it is possible to plan the travel path for firefighters to a designated target point, that is, to rationally plan the path for firefighters in performing forest fire fighting operations, so as to avoid fire threats and improve fire fighting efficiency.

[0093] To clearly illustrate how the target manifold space is determined based on the configuration space and the local three-dimensional model in the above embodiments, this disclosure also proposes a path planning method.

[0094] Figure 3 This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure.

[0095] like Figure 3 As shown, the path planning method may include the following steps:

[0096] Step 301: Obtain a local 3D model corresponding to the forest fire spread area in the forest area to be extinguished; wherein, the local 3D model is used to indicate the spatial location of the forest fire spread area.

[0097] Step 302: Obtain the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters.

[0098] The explanation of steps 301 to 302 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0099] Step 303: Determine a first morphological space from the configuration space, wherein the first morphological space contains connected candidate paths.

[0100] In this embodiment of the disclosure, a connected first morphological space can be determined from the configuration space, wherein the first morphological space contains connected candidate paths.

[0101] As an example, in configuration space, the core objective is to determine whether it is possible to reach another point from any other point in the configuration space. Therefore, it is necessary to connect one point to another through continuous paths in the configuration space and further determine whether the two points are connected. For this purpose, one can... A topological space X (denoted as the first morphological space in this disclosure) is defined, which is the set of all connected paths. Since firefighters are in a time-varying state space, a path can be defined as a continuous function, not a set of points, i.e., a path. It can be defined as:

[0102] τ: [0, 1] → X; (12)

[0103] Each point on the path is given by τ(s), where s∈[0,1]. Points in τ(s) can be represented by x1, x2, ... to indicate visited states. Furthermore, the connectivity of the path τ is determined as follows:

[0104] If for all x1, x2∈X, there exists a path such that τ(0)=x1, τ(1)=x2, then the topological space (i.e. the first morphological space)X is considered connected.

[0105] Step 304: Determine the obstacle region based on the intersection of each candidate path in the first morphological space and the local 3D model.

[0106] In this embodiment of the disclosure, the obstacle region can be determined based on the intersection of each candidate path in the first morphological space and the local three-dimensional model.

[0107] As an example, firefighter A is in an obstacle area within the configuration space. It can be represented as:

[0108]

[0109] in, Let A(q) represent the positional form of the firefighters, and let A(q) represent the path that the firefighters can take within the first-form space. q = (x t y t , z t ,h), where,(x t y t , z t ) represents the location of the firefighters, and h represents the unit quaternion. Let A(q) be the set of all positional forms q, in which A(q) and the local 3D model are represented. Intersecting, due to And A(q) is If a set is a closed set, then the obstacle region is... Also for A closed set in [the context of the universe].

[0110] Step 305: Remove the obstacle region from the configuration space to obtain the second morphological space.

[0111] In this embodiment of the disclosure, obstacle regions can be removed from the configuration space to obtain a second morphological space.

[0112] As an example, the second morphological space is labeled as Then we have:

[0113]

[0114] Step 306: Generate the target manifold space based on the interior points of the second morphological space and the boundary points of the second morphological space.

[0115] In this embodiment of the disclosure, a target manifold space can be generated based on the interior points of the second morphological space and the boundary points of the second morphological space.

[0116] As an example, due to configuration space In It is a closed set, therefore As an open set, this means that firefighters can reach any point arbitrarily close to the obstacle (the area of ​​fire spread), which is meaningless in a forest fire scenario. Therefore, it needs to be redefined using a closure approach. Obtain the target manifold space

[0117]

[0118] in, express The set of all interior points in the set. express The set of all boundary points.

[0119] Step 307: Perform a path search in the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters' movement.

[0120] The explanation of step 307 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0121] The path planning method of this disclosure can avoid fire threats and improve the safety of firefighters by removing obstacle areas from the configuration space.

[0122] To clearly illustrate how path search is performed from the target manifold space in the above embodiments, this disclosure also proposes a path planning method.

[0123] Figure 4 This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure.

[0124] like Figure 4 As shown, the path planning method may include the following steps:

[0125] Step 401: Obtain a local 3D model corresponding to the forest fire spread area in the forest area to be extinguished; wherein, the local 3D model is used to indicate the spatial location of the forest fire spread area.

[0126] Step 402: Obtain the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters.

[0127] Step 403: Determine a first morphological space from the configuration space, wherein the first morphological space contains connected candidate paths.

[0128] Step 404: Determine the obstacle region based on the intersection of each candidate path in the first morphological space and the local 3D model.

[0129] Step 405: Determine the target manifold space from the configuration space and the obstacle region.

[0130] In this embodiment of the disclosure, an obstacle region can be removed from the configuration space to obtain a second morphological space, and a target manifold space can be generated based on the interior points of the second morphological space and the boundary points of the second morphological space.

[0131] The explanations of steps 401 to 405 can be found in the relevant descriptions in any embodiment of this disclosure, and will not be repeated here.

[0132] Step 406: Based on the vertices of the obstacle region, the target manifold space is vertically divided to obtain multiple cavities.

[0133] In this embodiment of the disclosure, the plurality of cavities may include at least one first type of cavity and a plurality of second type of cavities, wherein the boundary between any two adjacent second type of cavities is a first type of cavity, that is, the first type of cavity is formed by the boundary between any two adjacent second type of cavities.

[0134] In this embodiment of the disclosure, the target manifold space can be vertically divided according to the vertices of the obstacle region to obtain multiple cavities.

[0135] As an example, the modeling approach for non-convex polygons is to divide the non-convex polygons into convex polygons, and then take the union of the divided convex polygons as the set of non-convex polygons. Different division methods determine the complexity of path planning solutions. As a possible implementation, a practical and efficient vertical division method can be used to optimize the modeling of the target manifold space, thereby effectively reducing computational complexity and improving the search efficiency of path planning.

[0136] Denote the target manifold space Target manifold space The vertical partitioning optimization model is as follows: The structure is divided into two finite families. The first finite family includes cells of type 1 (hereinafter referred to as cell 1), and the second finite family includes cells of type 2 (hereinafter referred to as cell 2). Each cell 2 can be a polyhedron (with a cross-section of a trapezoid or triangle with vertical edges). The partitioning of cell 2 is as follows: Let P denote the structure used to define... The set of vertices, where each vertex p∈P, is... For example, in a two-dimensional region, a ray can be used to traverse upwards and downwards from a vertex. Until you meet by To illustrate with a three-dimensional region, one can use a vertex as an endpoint and traverse the plane upwards and downwards. Until you meet Based on whether a vertex can extend in two directions, then we have: Figure 5 The four possible scenarios are shown. Among them, Figure 5 The shaded areas in the image represent obstacle areas. Figure 5 In the above, (1) can extend upwards and downwards, (2) can only extend upwards, (3) can only extend downwards, and (4) cannot extend upwards or downwards.

[0137] Will By dividing according to the aforementioned rays or planes, vertical divisions are produced; extending these rays or planes produces... The partitioning, the partitioning results can be as follows Figure 6 As shown, where, Figure 6 This is a schematic diagram of the spatial cross-section obtained by partitioning. The shaded area represents the obstacle area, and the other areas represent the target manifold space. The cross-section of cell 2 obtained by partitioning only includes trapezoids and triangles. Cell 1 is the surface between cells 2. Figure 6 In the cross-sectional view shown, cell cavity 1 is displayed as a vertical line segment.

[0138] Step 407: Perform a path search from the center of mass of each cell to obtain the target planning path between the starting point and the target point of the firefighters.

[0139] In this embodiment of the disclosure, path search can be performed from the center of mass of each cell to obtain the target planned path between the starting point and the target point of the firefighters' movement.

[0140] In one possible implementation of this disclosure, the path search method can specifically be as follows: for any one of the multiple second-type cavities, at least one first-type cavity connected to the second-type cavity can be determined, and the centroid of the second-type cavity and the centroid of the connected at least one first-type cavity can be connected to obtain at least one sub-path. Thus, a path topology map can be generated based on each sub-path, and a path search can be performed from the path topology map to obtain the target planning path between the starting point and the target point of the firefighters.

[0141] As an example, in order to correctly represent the target manifold space The path topology diagram after vertical partitioning further clarifies the definition of cell cavity 2 as... An open set on a given surface, i.e., the interior of a system or triangle, with cavity 1 being the interior of a line segment or surface. After vertical partitioning, when dealing with path planning problems within cavities, a path topology graph needs to be defined. Where V represents a node (e.g., the centroid of a cell cavity), and E represents a path:

[0142] For each cell cavity C i , let q i Indicates the cavity C i The centroid in the path topology graph In the middle, q i ∈V, each cavity 1 and cavity 2 has a centroid. For cavity 2, an edge is defined from its centroid along its boundary to the centroid of each cavity 1. Each edge is a sub-path between the centroids of cavities. Drawing all the sub-paths forms the path topology graph. For example, a path topology map can be like this Figure 7 As shown.

[0143] Next, a target planning path between the starting point and the target point can be searched from the path topology graph. For example, at least one candidate planning path passing through the starting point and the target point can be searched from the path topology graph. Based on the length of each candidate planning path, the target planning path can be determined from the candidate planning paths. For example, the shortest candidate planning path can be used as the target planning path.

[0144] It should be noted that, by Figure 7 It can be seen that since the cross-section of each cell cavity 2 is a convex polygon, the route topology can reach the centroid of each cell cavity, satisfying the reachability condition, and also satisfying the connectivity condition, because... It is generated from the partitioning of the cell cavity, and this partitioning preserves the target manifold space. Connectivity.

[0145] As one possible implementation, the path search from the path topology graph can be specifically as follows: determine the first target cell where the starting point is located and the second target cell where the target point is located from multiple cells, and perform a path search from the path topology graph to determine whether the path topology graph contains a planned path from the first centroid of the first target cell to the second centroid of the second target cell; if the path topology graph contains a planned path from the first centroid to the second centroid, use the planned path as the target planned path.

[0146] It should be noted that when the path topology graph contains multiple planned paths between the first centroid and the second centroid, the target planned path can be determined from among the planned paths based on their lengths. For example, the shortest planned path can be used as the target planned path.

[0147] As one possible implementation, if the planned path between the first centroid and the second centroid is not included in the path topology map, a prompt message can be generated and displayed, and / or sent to inform relevant personnel that there is no planned path between the starting point and the target point in the forest area to be extinguished.

[0148] As an example, such as Figure 7 As shown, the route topology map is obtained. Then, you can refer to the route topology map. Determine the initial point q I to target point q G The target planning path between them. Specifically, we can let C0 and C... k They respectively represent the contents of q I and q G The cell cavity, in the figure Searching for a result by q I to qG If the route does not exist, report that there is no solution; if it exists, let C1, C2, ..., C k-1 These represent the directions from C0 to C. k The calculated path sequence connects the cell cavities C1, C2, ..., C in sequence. k-1 The center of mass q in i (i = 1, 2, ..., k-1), then an initial solution for a path can be obtained. By formula (12), τ(0) = q I τ(1)=q G Connect q0 to q along the path topology graph k For each point in the path, the solution τ can be obtained: [0, 1] → Furthermore, it guarantees that the generated path solution will not collide with obstacles (i.e., areas affected by wildfires) at the current moment. For example, the target planned path obtained through the search can be as follows: Figure 8 As shown.

[0149] The path planning method of this disclosure involves vertically partitioning the target manifold space based on the vertices of the obstacle region to obtain multiple cavities; and performing path search from the centroid of each cavity to obtain the target planned path between the starting point and the target point of the firefighters. Thus, it is possible to effectively search for and obtain the target planned path between the starting point and the target point from the target manifold space.

[0150] It should be noted that during the route planning process, in addition to the area where the forest fire spreads affecting the rescue route planning, changes in the terrain around the forest itself will also affect the rescue route planning. For example, steep terrain and terrain with many undulations will affect the speed at which firefighters can safely move.

[0151] In addition, different path slopes will also affect the speed of firefighters. In order to optimize the cost of path planning, the slope of each sub-path on the target planned path can be calculated and the slope information can be used as a speed constraint to further optimize the travel time of the target planned path.

[0152] As an example, the travel speed at different slopes can be shown in Table 1:

[0153] Table 1. Correspondence between slope and travel speed

[0154]

[0155] Furthermore, firefighters should adhere to principles such as minimizing mountain crossings and avoiding valleys between mountains when traversing forests. Special terrain makes it difficult for firefighters to assess their surroundings, significantly depleting their energy. Moreover, the varied terrain can generate unique wind patterns such as eddies, circulation currents, foehn winds, and valley winds, which can lead to highly complex and potentially fatal forest fires. Therefore, to ensure the safety of firefighters, it is advisable to analyze whether the planned route enters areas with special terrain features, thereby increasing the cost of discrete planning within these areas and optimizing the safety of the planned route.

[0156] Based on the above principles, the travel cost can be optimized using a fitness function based on terrain conditions. The following section combines... Figure 9 The above process will be explained in detail.

[0157] Figure 9 This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure.

[0158] like Figure 9 As shown, based on any of the above embodiments, the path planning method may further include the following steps:

[0159] Step 901: For any two adjacent centroids in the target planning path, determine the slope and path length of the target sub-path between any two adjacent centroids.

[0160] In this embodiment of the disclosure, the slope of the target sub-path and the path length of the target sub-path can be determined for any two adjacent centroids in the target planned path.

[0161] Step 902: Determine the travel speed corresponding to the target sub-path based on the slope.

[0162] In this embodiment of the disclosure, a travel speed matching the slope of a target sub-path can be queried. For example, the travel speed corresponding to the target sub-path can be obtained by looking up Table 1 based on the slope of the target sub-path. For instance, if the slope of the target sub-path is 7°, the travel speed can be 90 steps per minute.

[0163] Step 903: Determine the sub-fitness of the target sub-path based on the travel speed and path length.

[0164] In this embodiment of the disclosure, the adaptability of the target sub-path can be determined based on the travel speed and path length.

[0165] As an example, label S(q) i q i+1 ) is the center of mass qi to the center of mass q i+1 The path length function between them For the center of mass q i to the center of mass q i+1 The velocity adjustment function between these points (i.e., the velocity adjustment function determined according to different slope magnitudes) then the centroid q i to the center of mass q i+1 The sub-fitness of the target sub-path can be compared with There is a negative correlation.

[0166] Step 904: Determine the fitness of the target planning path based on the sub-fitness of each target sub-path.

[0167] In this embodiment of the disclosure, the fitness of the target planning path can be determined based on the fitness of each target sub-path.

[0168] As an example, the fitness of the goal-oriented path can be:

[0169]

[0170] Where, q i (i = 1, 2, ..., k) refers to the centroids along the path of the target program, S(q i q i+1 ) is the center of mass q i to the center of mass q i+1 The path length function between them M(q) is the speed adjustment function determined according to different slopes. i q i+1 ) is the function to determine whether a path falls within a preferred region, and m is the corresponding preference coefficient. As mentioned above, the preference coefficient is relatively low for dangerous terrain areas and relatively high for flat, safe areas. α and β are cost adjustment weights, which can be taken as 1. g(q1, q2, ..., q k () refers to the fitness of the target planning path.

[0171] Step 905: Update the position of each centroid and / or the travel speed of each target sub-path in the target planning path based on fitness.

[0172] In this embodiment of the disclosure, the positions of each centroid and / or the travel speeds of each target sub-path in the target planning path can be iterated for a set number of rounds D based on fitness, so as to update the positions of each centroid and / or the travel speeds of each target sub-path. Alternatively, the positions of each centroid and / or the travel speeds of each target sub-path in the target planning path can be updated based on fitness until the fitness converges.

[0173] As an example, one could adopt Figure 9 The adjustment method of the illustrated embodiment is for Figure 8 The positions of the centroids in the target planning path are adjusted, and the adjusted target planning path can be as follows: Figure 10 As shown. It should be noted that, Figure 10 Arrow 1 points to a safe road section, while arrow 2 points to a dangerous area.

[0174] The path planning method of this disclosure can update the target planned path to balance the safety of the target planned path with the travel time or travel cost of firefighters.

[0175] As one possible approach, to improve path planning effectiveness and save firefighters' travel time, the target planned path can be further optimized. The following section will combine... Figure 11 The above process will be explained in detail.

[0176] Figure 11 This is a flowchart illustrating another path planning method provided in an embodiment of the present disclosure.

[0177] like Figure 11 As shown, based on any of the above embodiments, the path planning method may further include the following steps:

[0178] Step 1101: Determine the path planning area where the target planned path is located from the forest area to be extinguished.

[0179] In this embodiment of the disclosure, the path planning area where the target planned path is located can be determined from the forest area to be extinguished or the target manifold space. For example, the path planning area can be extracted from the target manifold space, wherein the path planning area contains the target planned path.

[0180] Step 1102: Divide the path planning area into grids to obtain multiple grid points.

[0181] In this embodiment of the disclosure, the path planning area can be divided into grids to obtain multiple grid points. For example, the grid size can be set according to actual application requirements, and the path planning area can be divided into grids according to the set grid size to obtain multiple grid points.

[0182] Step 1103: Based on the position and velocity information of multiple grid points, perform path search from multiple grid points to obtain the optimized target planning path between the starting point and the target point.

[0183] The velocity information for each grid point can be determined based on the slope of that grid point.

[0184] In this embodiment of the disclosure, a path search can be performed from multiple grid points based on the location and velocity information of multiple grid points to obtain an optimized target planning path between the starting point and the target point.

[0185] One possible implementation is to use a particle swarm optimization algorithm to perform path search from multiple grid points to obtain an optimized target path between the starting point and the target point. Each particle vector can be determined based on the position and velocity information of the grid point.

[0186] In other words, a path search based on particle swarm optimization (PSO) can be used. First, particle vectors are initialized in the firefighters' configuration space using a vertical partitioning method. When generating the PSO vector, a vertex search is performed to check if there is a collision with the fire-affected area at the current moment (or in this iteration). If a collision occurs, other vertices are selected; otherwise, the particle vector is inserted into the topological space X (i.e., the first morphological space) as a candidate population (path) in the PSO. Then, the next particle vector is generated, and this process is repeated to generate a PSO of a given size. The fitness (including path length and travel time) of each candidate population in the PSO vector is calculated. The optimal fitness of the individual and the optimal fitness of the population are used as update indicators for the particle vector, continuously iterating and optimizing to find a relatively safe and shorter optimized path in the time-varying spatial domain. For example, the path search process can be as follows: Figure 12 As shown.

[0187] Figure 12 In each iteration, the particle velocity can be determined based on pbest and gbest, where pbest refers to the path with the highest fitness in this iteration, and gbest refers to the path with the highest fitness in all iterations (i.e., the globally optimal path).

[0188] In this disclosure, considering that ordinary particle swarm optimization (PSO) algorithms often suffer from poor route planning performance and low global convergence due to rapid local convergence, this disclosure improves the calculation method of weights and cognitive factors in the update rate formula of the PSO algorithm to enhance the global convergence of path planning in forest fire scenarios. For example, the improved PSO algorithm's update rate method and the definitions of weights and cognitive factors can be as follows:

[0189]

[0190]

[0191]

[0192]

[0193] Among them, v t v represents the velocity at the current moment or in this iteration. t-1 The velocity of the previous moment or the previous iteration; w t To update the weights for the current moment or the current iteration, w t-1 The weights are updated based on the velocity of the previous time step or iteration; ε(0,1) is a random number in (0,1); pid is generated based on the particle vectors in pbest (i.e., the optimal path in this iteration) and is used to indicate the position information of pbest (i.e., pid indicates the optimal path position in its own population); pgd is generated based on the particle vectors in gbest (i.e., the global optimal path) and is used to indicate the position information of gbest (i.e., pgd indicates the optimal path position in all populations); pos is the current position of the particle. Self-awareness factors at the current moment or in this iteration; The social cognitive factor at the current moment or in this iteration; d is the current iteration number, D is the total number of iterations; w min , These are the minimum values ​​of the weights, self-awareness factor, and social-awareness factor, respectively. For the first iteration, w... 0 , It can be the initial value set.

[0194] In other words, for the first iteration, the update weight of the first iteration can be determined according to the set weight, and the movement speed of each grid point or particle can be updated according to the update weight of the first iteration to obtain the movement speed of each grid point or particle obtained by the first iteration update; for the i-th iteration, the update weight of the i-th iteration can be determined according to the update weight of the (i-1)-th iteration and the ratio of i to D, and the movement speed of each grid point or particle obtained by the (i-1)-th iteration update can be updated according to the update weight of the i-th iteration to obtain the movement speed of each grid point or particle obtained by the i-th iteration update; where i = 2, 3, ..., D.

[0195] From formulas (18), (19) and (20), it can be seen that in the early stage of iteration, the speed update weight w t Larger, the particle's self-awareness factor Larger, social cognitive factors When the value is relatively small, the particle has good global search capability. As the number of iterations increases, the speed of updating the weight w increases. t Reduce self-awareness factors Decrease, social cognitive factors The increase in size enhances the particle's local search capability. This ensures that the particle possesses both good global search capability in early iterations and good local search capability in later iterations, thereby improving both global convergence performance and convergence speed.

[0196] As an example, the inventors used Matlab 2022a to write a path planning example for a forest fire scenario. The data used were DEM (Digital Elevation Model) data of a certain region and a defined forest fire spread area. The overall code framework is as follows: Figure 13 As shown in the figure. Here, maxgbest refers to the best path with the highest fitness (gbest), pidx and pidy are the coordinates of pid, maxpgdx and maxgpdy are the coordinates of pgd with the highest fitness, and maxfitvalueall is the path with the highest fitness.

[0197] The path with the highest fitness obtained by path search can be as follows: Figure 14 As shown in curve 3, after multiple experiments and parameter adjustments, in the runnable instance, the average running time of the code for 20 iterations was 0.5 seconds. Within 20 iterations, the fitness remained essentially unchanged, indicating that the fitness had reached the convergence condition, demonstrating good convergence performance. For example, the fitness change curve measured in the experiment can be seen as follows: Figure 15 As shown.

[0198] In any embodiment of this disclosure, the implementation principle of the automatic risk avoidance motion path planning algorithm in a forest fire spread scenario can be as follows: Figure 16 As shown, a time-varying motion planning approach is adopted, introducing a time-varying free state space (i.e., the target manifold space) as the initial input for motion path planning calculation. Vertical cell partitioning and an improved particle swarm optimization algorithm are used to reduce the computational complexity of the time-varying motion planning model and improve the global convergence effect and convergence speed. This ensures the computational efficiency of motion path planning for firefighters in forest fire scenarios and provides effective protection for the safety of forest fire rescue scenarios and the accessibility assessment of firefighters to the target point.

[0199] in, Figure 16 The system assumes three conditions: firefighters cannot enter the area where the forest fire is spreading; firefighters have variable movement speeds, but there is an upper limit to their movement speed; and each movement path planning calculation scenario is limited to a specific spatial range.

[0200] In the planning process of time-varying forest fire spread areas, not only is a local three-dimensional model of the forest fire spread area coupled, but dangerous terrain factors are also coupled into the motion path planning. The complex calculation models of dangerous factors in the two forest fire scenarios serve as key inputs to the forest fire scenario space. On the one hand, this improves the accuracy of the time-varying free state space, and on the other hand, it enhances the applicability of the algorithm in real-world scenarios.

[0201] With the above Figures 1 to 11 Corresponding to the path planning method provided in the embodiments, this disclosure also provides a path planning device. Because the path planning device provided in the embodiments of this disclosure is similar to the one described above... Figures 1 to 11 The path planning method provided in the embodiments corresponds to the path planning device provided in the embodiments of this disclosure, and will not be described in detail in the embodiments of this disclosure.

[0202] Figure 17 This is a schematic diagram of the structure of a path planning device provided in an embodiment of the present disclosure.

[0203] like Figure 17 As shown, the path planning device 1700 may include: a first acquisition module 1701, a second acquisition module 1702, a determination module 1703, and a search module 1704.

[0204] The first acquisition module 1701 is used to acquire a local three-dimensional model corresponding to the forest fire spread area in the forest area to be extinguished; wherein the local three-dimensional model is used to indicate the spatial location of the forest fire spread area.

[0205] The second acquisition module 1702 is used to acquire the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters.

[0206] The determination module 1703 is used to determine the target manifold space based on the configuration space and the local three-dimensional model.

[0207] Search module 1704 is used to perform path search from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters.

[0208] In one possible implementation of this disclosure, the determining module 1703 is specifically used for: determining a first morphological space from the configuration space, wherein the first morphological space contains connected candidate paths; determining an obstacle region based on the intersection of each candidate path in the first morphological space with the local three-dimensional model; removing the obstacle region from the configuration space to obtain a second morphological space; and generating a target manifold space based on the interior points of the second morphological space and the boundary points of the second morphological space.

[0209] In one possible implementation of this disclosure, the search module 1704 is specifically used to: vertically divide the target manifold space according to the vertices of the obstacle region to obtain multiple cavities; and perform path search from the centroid of each cavity to obtain the target planned path between the starting point and the target point of the firefighters.

[0210] In one possible implementation of this disclosure, the plurality of cavities includes at least one first-type cavity and a plurality of second-type cavities, and the boundary between any two adjacent second-type cavities constitutes a first-type cavity; the search module 1704 is specifically configured to: for any second-type cavity, determine at least one first-type cavity connected to the second-type cavity; connect the centroid of the second-type cavity and the centroid of the at least one connected first-type cavity to obtain at least one sub-path; generate a path topology map based on each sub-path; and perform path search from the path topology map to obtain the target planned path between the starting point and the target point of the firefighters.

[0211] In one possible implementation of this disclosure, the search module 1704 is specifically configured to: determine a first target cell where the starting point is located and a second target cell where the target point is located from a plurality of cells; perform a path search from the path topology graph to determine whether the path topology graph contains a planned path from the first centroid of the first target cell to the second centroid of the second target cell; and if the path topology graph contains a planned path from the first centroid to the second centroid, use the planned path as the target planned path.

[0212] In one possible implementation of this disclosure, the path planning device 1700 may further include:

[0213] The generation module is used to generate prompt information when the planned path between the first centroid and the second centroid is not included in the path topology map.

[0214] The processing module is used to display and / or send prompt messages.

[0215] The prompt information is used to indicate that there is no planned path between the starting point and the target point in the forest area to be extinguished.

[0216] In one possible implementation of this disclosure, the path planning device 1700 may further include:

[0217] The update module is used to determine the slope and path length of the target sub-path between any two adjacent centroids in the target planned path; determine the travel speed corresponding to the target sub-path based on the slope; determine the sub-fitness of the target sub-path based on the travel speed and path length; determine the fitness of the target planned path based on the sub-fitness of each target sub-path; and update the position of each centroid and / or the travel speed of each target sub-path in the target planned path based on the fitness.

[0218] In one possible implementation of this disclosure, the path planning device 1700 may further include:

[0219] The optimization module is used to determine the path planning area where the target planned path is located from the forest area to be extinguished; divide the path planning area into grids to obtain multiple grid points; and search for a path from the multiple grid points based on the location and velocity information of the multiple grid points to obtain the optimized target planned path between the starting point and the target point.

[0220] The path planning device of this embodiment acquires a local three-dimensional model corresponding to the forest fire spread area in the forest area to be extinguished; wherein the local three-dimensional model is used to indicate the spatial location of the forest fire spread area; acquires the configuration space of the firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters; determines the target manifold space based on the configuration space and the local three-dimensional model; and performs a path search from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters. Therefore, in a forest fire scenario, it is possible to plan the travel path for firefighters to a designated target point, that is, to rationally plan the path for firefighters in performing forest fire fighting operations, so as to avoid fire threats and improve fire fighting efficiency.

[0221] To implement the above embodiments, this disclosure also proposes an electronic device, which may include: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the path planning method proposed in any of the foregoing embodiments of this disclosure.

[0222] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the path planning method proposed in any of the foregoing embodiments of this disclosure.

[0223] To implement the above embodiments, this disclosure also proposes a computer program product that, when the instructions in the computer program product are executed by a processor, performs the path planning method as proposed in any of the foregoing embodiments of this disclosure.

[0224] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0225] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0226] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0227] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0228] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0229] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0230] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0231] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A path planning method, characterized in that, The method includes: Obtain a local 3D model corresponding to the forest fire spread area in the forest area to be extinguished; wherein, the local 3D model is used to indicate the spatial location of the forest fire spread area; Obtain the configuration space of firefighters in the forest area to be extinguished, wherein the configuration space is used to indicate the movable position and / or movable direction of the firefighters; Determining a target manifold space based on the configuration space and the local 3D model includes: determining a first morphological space from the configuration space, wherein the first morphological space contains connected candidate paths; determining an obstacle region based on the intersection of each candidate path in the first morphological space and the local 3D model; removing the obstacle region from the configuration space to obtain a second morphological space; and generating the target manifold space based on the interior points and boundary points of the second morphological space. The path search is performed in the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters' movement; including: vertically dividing the target manifold space according to the vertices of the obstacle area to obtain multiple cavities; and performing a path search from the centroid of each of the cavities to obtain the target planned path between the starting point and the target point of the firefighters' movement. For any two adjacent centroids in the target planning path, determine the slope and path length of the target sub-path between the two adjacent centroids; determine the travel speed corresponding to the target sub-path based on the slope; determine the sub-fitness of the target sub-path based on the travel speed and the path length; determine the fitness of the target planning path based on the sub-fitness of each target sub-path; update the position of each centroid and / or the travel speed of each target sub-path based on the fitness. The path planning area where the target planned path is located is determined from the forest area to be extinguished; the path planning area is divided into grids to obtain multiple grid points; based on the position and velocity information of the multiple grid points, a path search is performed from the multiple grid points using a particle swarm optimization algorithm to obtain the optimized target planned path between the starting point and the target point; wherein, each particle vector can be determined based on the position and velocity information of the grid points; The path search based on the particle swarm optimization algorithm from the multiple grid points includes: initializing particle vectors in the configuration space of the firefighters according to the vertical partitioning method; performing vertex search when generating particle swarm vectors; checking whether the current iteration collides with the forest fire spread area; if a collision occurs, selecting other vertices; if no collision occurs, inserting the particle vector into the first morphological space as a candidate population path in the particle swarm; then generating the next particle vector; repeatedly generating a particle swarm of a given size; calculating the fitness of each candidate population in the particle swarm vector; using the individual optimal fitness and the population optimal fitness as the update index of the particle vector; continuously iterating and optimizing to find the optimal path in the time-varying spatial domain. The fitness of the target programming path is represented as follows: Where, q i (i = 1, 2, ..., k) refers to the centroids traversed by the target program path, S(q i ,q i+1 ) is the center of mass q i to the center of mass q i+1 The path length function between them M(q) is the speed adjustment function determined according to different slopes. i ,q i+1 ) is the function to determine whether a path falls within a preferred region, m is the corresponding preference coefficient, α and β are cost adjustment weights, and g(q1,q2,…,q) is the value of g. k () refers to the fitness of the target planning path.

2. The method according to claim 1, characterized in that, The plurality of cavities includes at least one first type of cavity and a plurality of second type cavities, wherein the boundary between any two adjacent second type cavities constitutes the first type of cavity; The step of performing a path search from the centroid of each of the cell cavities to obtain the target planned path between the starting point and the target point of the firefighters' movement includes: For any second type of cavity, identify at least one first type of cavity connected to the second type of cavity; Connect the centroid of the second type of cell cavity to the centroid of at least one connected first type of cell cavity to obtain at least one sub-path; Generate a path topology graph based on each of the sub-paths; A path search is performed from the path topology map to obtain the target planned path between the starting point and the target point of the firefighters' movement.

3. The method according to claim 2, characterized in that, The step of performing a path search from the path topology map to obtain the target planned path between the starting point and the target point of the firefighters' movement includes: Determine the first target cell cavity where the starting point is located and the second target cell cavity where the target point is located from the plurality of cell cavities; A path search is performed from the path topology graph to determine whether the path topology graph contains a planned path from the first centroid of the first target cell to the second centroid of the second target cell. If the path topology graph contains a planned path between the first centroid and the second centroid, the planned path is taken as the target planned path.

4. The method according to claim 3, characterized in that, The method further includes: If the planned path between the first centroid and the second centroid is not included in the path topology map, a prompt message is generated; Display the prompt message, and / or send the prompt message; The prompt information is used to indicate that there is no planned path between the starting point and the target point in the forest area to be extinguished.

5. A path planning device, characterized in that, The device includes: The first acquisition module is used to acquire a local three-dimensional model corresponding to the forest fire spread area in the forest area to be extinguished; wherein, the local three-dimensional model is used to indicate the spatial location of the forest fire spread area; The second acquisition module is used to acquire the positional space of the firefighters in the forest area to be extinguished, wherein the positional space is used to indicate the movable position and / or movable direction of the firefighters. A determination module is used to determine a target manifold space based on the configuration space and the local 3D model; including: determining a first morphological space from the configuration space, wherein the first morphological space contains connected candidate paths; determining an obstacle region based on the intersection of each candidate path in the first morphological space and the local 3D model; removing the obstacle region from the configuration space to obtain a second morphological space; and generating the target manifold space based on the interior points of the second morphological space and the boundary points of the second morphological space. The search module is used to perform path search from the target manifold space to obtain the target planned path between the starting point and the target point of the firefighters; including: vertically partitioning the target manifold space according to the vertices of the obstacle area to obtain multiple cavities; performing path search from the centroids of each cavity to obtain the target planned path between the starting point and the target point of the firefighters; determining the slope and path length of the target sub-path between any two adjacent centroids in the target planned path; determining the travel speed corresponding to the target sub-path based on the slope; determining the sub-fitness of the target sub-path based on the travel speed and the path length; determining the fitness of the target planned path based on the sub-fitness of each target sub-path; updating the position of each centroid and / or the travel speed of each target sub-path based on the fitness; determining the path planning area where the target planned path is located from the forest area to be extinguished; and updating the path planning area. The process involves dividing the data into grids to obtain multiple grid points. Based on the position and velocity information of these grid points, a path search is performed using a particle swarm optimization algorithm to obtain the optimized target planning path between the starting point and the target point. Each particle vector can be determined based on the position and velocity information of the grid points. The path search using the particle swarm optimization algorithm includes: initializing particle vectors in the configuration space of the firefighters using a vertical partitioning method; performing vertex search when generating the particle swarm vector; checking whether the current iteration collides with the forest fire spread area; if a collision occurs, selecting other vertices; if no collision occurs, inserting the particle vector into the first morphological space as a candidate population path in the particle swarm; then generating the next particle vector; repeatedly generating a particle swarm of a given size; calculating the fitness of each candidate population in the particle swarm vector; using the individual optimal fitness and the population optimal fitness as update indicators for the particle vector; and continuously iterating and optimizing to find an optimal path in the time-varying spatial domain. The fitness of the target programming path is represented as follows: Where, q i (i = 1, 2, ..., k) refers to the centroids traversed by the target program path, S(q i ,q i+1 ) is the center of mass q i to the center of mass q i+1 The path length function between them M(q) is the speed adjustment function determined according to different slopes. i ,q i+1 ) is the function to determine whether a path falls within a preferred region, m is the corresponding preference coefficient, α and β are cost adjustment weights, and g(q1,q2,…,q) is the value of g. k () refers to the fitness of the target planning path.

6. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the method as described in any one of claims 1-4.

Images