Collision-free path planning method and device based on building components

Abstract

Embodiments of the present disclosure disclose a building component-based collision-free path planning method and device. A specific embodiment of the method comprises: reading a set of vertex coordinates of each building component in a preset space range; connecting an initial path starting point with each arbitrary end point to obtain an initial planning path set; for each initial planning path in the initial planning path set, performing the following first processing steps: in response to determining that an effective distribution node distance in an effective distribution node distance set meets a preset range condition, determining the effective distribution node distance set as a safe planning path, wherein the safe planning path represents a planning path that does not collide. The embodiment improves the quality of the safe planning path, and the spatial safety of path planning is improved.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and more specifically to a collision-free path planning method and apparatus based on building components. Background Technology

[0002] Collision-free path planning based on building components is a technology for planning collision-free paths for building components. Currently, the common approach to collision-free path planning for building components is to rely on human decision-making for path planning from a single starting point to a single ending point. For example, engineers plan a path from a known starting point to a known ending point based on subjective experience, ensuring that no collisions occur along the way.

[0003] However, when using the above method to perform collision-free path planning for building components, the following technical problems often arise: Relying on human decision-making cannot ensure that each path in multi-path planning maintains a safe distance from all obstacles, increasing the likelihood of collisions and resulting in low spatial safety in path planning. Furthermore, the irregularity of obstacles may cause the planned paths to cluster or be unevenly distributed, leading to poor quality and low safety of the generated safe paths. Summary of the Invention

[0004] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0005] Some embodiments of this disclosure propose a collision-free path planning method and apparatus based on building components to solve the technical problems mentioned in the background section above.

[0006] In a first aspect, some embodiments of this disclosure provide a collision-free path planning method based on building components. The method includes: reading a set of vertex coordinates for each building component within a preset spatial range, wherein the vertex coordinate set represents the coordinates of each vertex of each building component in a two-dimensional planar map; connecting an initial path start point with each arbitrary end point using feasible paths to obtain an initial planned path set, wherein the feasible paths represent paths between the initial path start point and any arbitrary end point where no obstacles exist; for each initial planned path in the initial planned path set, performing the following first processing step: determining each intermediate node of the initial planned path as a path reference point set; generating an effective distribution distance set based on the path reference point set; equally dividing each effective distribution distance in the effective distribution distance set to generate effective distribution node distances, obtaining an effective distribution node distance set; in response to determining that the effective distribution node distances in the effective distribution node distance set satisfy a preset range condition, determining the effective distribution node distance set as a safe planned path, wherein the safe planned path represents a planned path where collisions will not occur.

[0007] Secondly, some embodiments of this disclosure provide a collision-free path planning device based on building components. The device includes: a processing unit configured to read a set of vertex coordinates of each building component within a preset spatial range, wherein the set of vertex coordinates represents the vertex coordinates of each building component in a two-dimensional planar map; a connection unit configured to connect an initial path start point with each arbitrary end point using feasible paths to obtain an initial planned path set, wherein the feasible paths represent paths between the initial path start point and the arbitrary end point where no obstacles exist; and an execution unit configured to perform the following first processing steps for each initial planned path in the initial planned path set: determining each intermediate node of the initial planned path as a path reference point set; generating an effective distribution distance set based on the path reference point set; dividing each effective distribution distance in the effective distribution distance set into equal parts to generate effective distribution node distances, thereby obtaining an effective distribution node distance set; and determining the effective distribution node distance set as a safe planned path in response to determining that the effective distribution node distances in the effective distribution node distance set meet a preset range condition, wherein the safe planned path represents a planned path where collisions will not occur.

[0008] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0010] The above embodiments of this disclosure have the following beneficial effects: The collision-free path planning method based on building components in some embodiments of this disclosure improves the quality of safe path planning and enhances the spatial safety of path planning. Specifically, the reason for the low spatial safety of path planning is that relying on manual decision-making cannot ensure that each path in multi-path planning maintains a safe distance from all obstacles, leading to a higher probability of collisions and thus lower spatial safety. Furthermore, because obstacles are irregular, the planned paths may cluster or be unevenly distributed, resulting in poor quality and low safety of the generated safe paths. Based on this, the collision-free path planning method based on building components in some embodiments of this disclosure first reads the vertex coordinate set of each building component within a preset spatial range, where the vertex coordinate set represents the coordinates of each vertex of each building component in a two-dimensional plane map. This allows for the digitization of ambiguous environmental information, providing a data foundation for subsequent processing. Then, feasible paths are connected between the initial path start point and each arbitrary end point to obtain an initial planned path set, where each feasible path indicates that there are no obstacles in the path between the initial path start point and any end point. The approximate feasible directions from the starting point to each endpoint can be determined without relying on manual decision-making. For each initially planned path in the aforementioned initial planned path set, the following first processing step is performed: Each intermediate node of the aforementioned initial planned path is determined as a path reference point set. Dimensionality reduction of complex multi-path systems can decrease problem complexity. Based on the aforementioned path reference point set, an effective distribution distance set is generated. This ensures that each path in multi-path planning maintains a safe distance from all obstacles, significantly reducing the possibility of collisions. Each effective distribution distance in the aforementioned effective distribution distance set is equally divided to generate effective distribution node distances, resulting in an effective distribution node distance set. This avoids path clustering or uneven distribution, improving the quality and safety of the generated safe planned paths. In response to determining that the effective distribution node distances in the aforementioned effective distribution node distance set meet preset range conditions, the effective distribution node distance set is determined as a safe planned path, where the safe planned path represents a planned path that will not collide. Therefore, it ensures that each path in multi-path planning maintains a safe distance from all obstacles, significantly reducing the possibility of collisions. This avoids clustering or uneven distribution of planned paths, improving the quality and safety of the generated safe planned paths. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0012] Figure 1 This is a schematic diagram of an application scenario of the collision-free path planning method based on building components, which is one of the embodiments of this disclosure; Figure 2 This is a flowchart of some embodiments of the collision-free path planning method based on building components according to the present disclosure; Figure 3 This is a structural schematic diagram of some embodiments of the collision-free path planning device based on building components according to the present disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure; Figure 5 This is a schematic diagram of a path according to some embodiments of the collision-free path planning method based on building components disclosed herein; Figure 6 It is an anisotropic neighborhood map of some embodiments of the collision-free path planning device based on building components according to the present disclosure. Detailed Implementation

[0013] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0014] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0015] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0016] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0017] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0018] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] Figure 1 This is a schematic diagram of an application scenario of the collision-free path planning method based on building components, which is one of the embodiments of this disclosure.

[0020] exist Figure 1 In the application scenario, firstly, the vertex coordinate set of each building component (e.g., building component 1, building component 2, building component 3, building component 4, building component 5) within a preset spatial range of 100 is read. The vertex coordinate set represents the coordinates of each vertex of each building component on a two-dimensional plane map. Feasible paths are then established between the initial path start point (e.g., the start point) and each arbitrary end point (e.g., end point a, end point b, and end point c) (e.g., solid line connection between the start point and end point a, between the start point and end point b, and between the start point and end point c) to obtain an initial planned path set. The aforementioned feasible paths indicate that there are no obstacles in the path between the initial path start point and any arbitrary end point. For each initial planned path in the aforementioned initial planned path set, the following first processing step is performed: Each intermediate node of the aforementioned initial planned path (e.g., reference node A, reference node B, reference node C, reference node D, reference node E, and reference node F) is determined as a path reference point set. Based on the aforementioned path reference point set, an effective distribution distance set is generated (an effective distribution distance in the effective distribution distance set is, for example, a distance between the starting point and the ending point 'a' connected by a dashed line through building component 1 and building component 2; the dashed line can be a curve or a straight line). It should be understood that... Figure 1 The number of building components, reference nodes, and endpoints can be arbitrary, depending on implementation requirements.

[0021] Continue to refer to Figure 2 The diagram illustrates a flow 200 of some embodiments of a collision-free path planning method based on building components according to the present disclosure. This collision-free path planning method based on building components includes the following steps: Step 201: Read the vertex coordinate set of each building component within the preset spatial range.

[0022] In some embodiments, the execution entity (e.g., a computing device) of the collision-free path planning method based on building components can read the vertex coordinate set of each building component within a preset spatial range via a wired or wireless connection. The vertex coordinate set refers to the coordinates of each vertex of each building component on a two-dimensional planar map.

[0023] The aforementioned preset space range can be a pre-defined range representing spatial dimensions. For example, the preset space range can be a pre-defined two-dimensional planar space of 50 meters long and 30 meters wide. As another example, the preset space range can be a two-dimensional planar space including corridors and rooms where a robot transporting goods is located. The preset space range can also be the range of a sand table used on a construction site to simulate the location of a building development.

[0024] The aforementioned building components can be building structures. These building components can be considered obstacles in a wide road. The aforementioned building components can include, but are not limited to, at least one of the following: walls, columns, doors, and windows.

[0025] The vertex coordinate set mentioned above can represent the coordinates of each vertex of a building component on a two-dimensional plane. For example, assuming the building component is rectangular in shape on the two-dimensional plane, the vertex coordinate set could be [(100, 100), (200, 100), (200, 200), (100, 200)]. Here, there are no restrictions on the shape of the building component; it can be of any shape.

[0026] As an example, the aforementioned execution entity can store the vertex coordinates of each building component within a preset spatial range in clockwise order to generate a vertex coordinate group, thus obtaining a vertex coordinate set.

[0027] It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future wireless connection methods.

[0028] It should be noted that the aforementioned computing devices can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. For example, the computing device can be the aforementioned target terminal. When the computing device is software, it can be installed on the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0029] Step 202: Connect the initial path start point with each arbitrary end point using feasible paths to obtain the initial planned path set.

[0030] In some embodiments, the executing entity can connect the initial path start point with each arbitrary end point using feasible paths to obtain an initial planned path set. Here, a feasible path indicates that there are no obstacles in the path between the initial path start point and any arbitrary end point.

[0031] The initial path starting point can be a pre-defined starting point for each endpoint along the path. For example, the initial path starting point could be (0, 0). The endpoints can be randomly selected. There is no limit to the number of arbitrary endpoints.

[0032] As an example, the aforementioned execution entity can use a path planning algorithm (e.g., Rapidly-exploring Random Tree Star (RRT*)) to connect the initial path start point with each arbitrary end point to obtain an initial planned path set.

[0033] As another example, the aforementioned execution entity can start from the initial path starting point, avoid obstacles on the paths leading to each endpoint, and determine the paths leading to each endpoint after obstacle avoidance as a set of feasible paths, which serves as the initial planned path set.

[0034] Step 203: For each initial planned path in the above initial planned path set, perform the following first processing step: Step 2031: Determine each intermediate node of the initial planned path as the path reference point set.

[0035] In some embodiments, the execution entity may determine each intermediate node of the initial planned path as a set of path reference points.

[0036] The intermediate nodes mentioned above can be nodes in the initial planned path where the path bends. That is, the intermediate nodes can be nodes in the initial planned path where the slope changes.

[0037] As an example, the aforementioned execution entity can first identify each node in the initial planned path where the slope changes as an intermediate node, serving as a set of path reference points.

[0038] Step 2032: Generate an effective distribution distance set based on the above path reference point set.

[0039] In some embodiments, the aforementioned execution entity may generate an effective distribution distance set based on the aforementioned path reference point set.

[0040] Optionally, the aforementioned executing entity can generate an effective distribution distance set based on the aforementioned path reference point set through the following steps: First, for each path reference point in the above path reference point set, perform the following fourth processing step: The first sub-step involves acquiring image data from a pre-defined fan-shaped sensing area around the aforementioned path reference point to obtain a reference point environmental image dataset.

[0041] The aforementioned preset fan-shaped sensing area covers the direction of travel from the path reference point and the areas requiring attention on both sides. This preset fan-shaped sensing area can be a 120-degree fan-shaped sensing area.

[0042] As an example, the aforementioned execution entity can use multiple cameras to collect image data of a preset fan-shaped sensing area around the aforementioned path reference point, thereby obtaining a reference point environmental image dataset.

[0043] The second sub-step involves aligning the reference point environmental image data in the aforementioned reference point environmental image dataset with timestamps and registering their spatial coordinates to generate an environmental perception dataset.

[0044] Among them, the aforementioned environmental perception dataset can be a temporally and spatially consistent reference point environmental image dataset, which can avoid image mismatch caused by the movement of the acquisition device (e.g., multi-view camera).

[0045] As an example, the aforementioned execution entity can convert the environmental image data of various reference points collected at the same time to the same coordinate system with the path reference point as the origin, so as to generate a dataset of environmental images of reference points located at different coordinates at the same time, which can be used as an environmental perception dataset.

[0046] The third sub-step involves determining semantic point cloud segments from the aforementioned environmental perception dataset to obtain a semantic point cloud segment set.

[0047] As an example, the aforementioned execution entity can first perform semantic segmentation on the aforementioned environmental perception dataset to generate segmentation results. Then, the segmentation results are combined with depth information obtained through stereo vision to obtain a 3D point cloud. This 3D point cloud includes 3D coordinates and semantic labels. Finally, point clouds belonging to the same semantic category and spatially connected are clustered together to obtain a semantic point cloud fragment set. The aforementioned segmentation results may include, but are not limited to, at least one of the following: roads, buildings, and pedestrians.

[0048] The fourth sub-step involves performing coordinate registration between the aforementioned semantic point cloud fragment set and the preset building component vertex coordinate set to obtain the semantic point cloud fragment coordinate set.

[0049] The aforementioned preset set of building component vertex coordinates can be a set of vertex coordinates of each building component that has been measured in advance using BIM.

[0050] As an example, the aforementioned execution entity can align the set of semantic point cloud fragments with a preset set of vertex coordinates for building components to obtain a set of semantic point cloud fragment coordinates. This set of semantic point cloud fragment coordinates can be a semantic point cloud fragment containing coordinate information.

[0051] The fifth sub-step involves performing risk semantic joint mapping on the coordinate set of the aforementioned semantic point cloud fragments to generate a local risk semantic tensor field.

[0052] As an example, the aforementioned execution entity can first determine the semantic labels and spatial attributes of the aforementioned semantic point cloud fragment coordinate set to generate semantic labels and spatial attributes for the semantic point cloud fragments. Then, based on a preset risk rule base, it determines the risk value of each semantic point cloud fragment coordinate in the aforementioned semantic point cloud fragment coordinate set. Finally, it defines the semantic labels, spatial attributes, and risk values ​​of the aforementioned semantic point cloud fragments as a local risk semantic tensor field. The semantic labels can be "temporary fencing," "wall," or "vegetation." The spatial attributes can be "nearest distance to the path reference point," "occupied volume," or "surface curvature." The preset risk rule base can be a set of rules that takes semantic labels and spatial attributes as input and risk values ​​as output. The risk value ranges from (0, 1). For example, IF semantic label == "load-bearing wall," THEN risk value = 0.99. The local risk semantic tensor field can be [semantic label, spatial attribute, risk value], for example, [temporary fencing, closest distance 1.5 meters, 0.72].

[0053] The sixth sub-step involves constructing an anisotropic neighborhood graph at the aforementioned path reference point based on the aforementioned local risk semantic tensor field.

[0054] As an example, the aforementioned execution entity can divide the local risk semantic tensor field into a grid, connecting the grid as nodes (a node is only connected to its four adjacent nodes: above, below, left, and right), resulting in a graph structure, which serves as an anisotropic neighborhood graph. Each grid cell acts as a node in the graph structure. The weights of edges connecting adjacent grid nodes are not fixed but anisotropic. The weight of an edge is determined by the risk tensors of the two nodes it connects to. Moving from a low-risk node to a high-risk node incurs a higher cost, and vice versa. For example, assuming the local risk semantic tensor field is divided into a 3×3 grid (9 nodes numbered 1-9), the edge weight is obtained by dividing the risk value of the target node by the risk value of the source node, such as... Figure 6As shown, 1 (1) indicates that the risk value of node 1 is 1. 2 (2) indicates that the risk value of node 2 is 2. 3 (5) indicates that the risk value of node 3 is 5. 4 (3) indicates that the risk value of node 4 is 3. 5 (4) indicates that the risk value of node 5 is 4. 6 (4) indicates that the risk value of node 6 is 4. 7 (2) indicates that the risk value of node 7 is 2. 8 (3) indicates that the risk value of node 8 is 3. 9 (1) indicates that the risk value of node 9 is 1. The risk values ​​of node 1 and node 2 are 1 and 2 respectively, as shown in parentheses. The weight of the edge from node 1 to node 2 is 2 ÷ 1 = 1. The weight of the edge from node 2 to node 1 is 0.5. The weight of the edge from node 2 to node 3 is 2.5. The weight of the edge from node 3 to node 2 is 0.4. The weight of the edge from node 1 to node 4 is 3.0. The weight of the edge from node 4 to node 1 is 0.67. The weight of the edge from node 2 to node 5 is 2.0. The weight of the edge from node 5 to node 2 is 0.5. The weight of the edge from node 3 to node 6 is 1.0. The weight of the edge from node 6 to node 3 is 1.0. The weight of the edge from node 4 to node 7 is 0.67. The weight of the edge from node 7 to node 4 is 3.0. The weight of the edge from node 5 to node 8 is 0.75. The weight of the edge from node 8 to node 5 is 1.33. The weight of the edge from node 6 to node 9 is 4.0. The weight of the edge from node 9 to node 6 is 0.25. The weight of the edge from node 7 to node 8 is 0.67. The weight of the edge from node 8 to node 7 is 1.5. The weight of the edge from node 8 to node 9 is 0.33. The weight of the edge from node 9 to node 8 is 3.0.

[0055] The seventh sub-step involves performing a pre-defined conditional traversal of the anisotropic neighborhood graph to generate the optimal local micropath cluster for the current reference point.

[0056] Among them, the aforementioned preset condition can be a pre-defined "reaching the safety boundary".

[0057] As an example, the aforementioned execution entity can use Dijkstra's algorithm to traverse the anisotropic neighborhood graph under predefined conditions, starting from the path reference point, to generate the optimal local micropath cluster for the current reference point. For instance, searching in five directions—left, left-front, front, right-front, and right—from the reference point yields five micropaths. The left path incurs a significant cost increase after only 2 meters (encountering building components), while the right path, even after 8 meters, remains relatively inexpensive.

[0058] The eighth sub-step involves performing a pre-defined conditional traversal of the anisotropic neighborhood graph to generate the optimal local micropath cluster of the path reference points.

[0059] Here, the aforementioned preset condition can be a pre-defined "local path with a cost less than a preset value". The specific value of the aforementioned preset value is not limited here.

[0060] As an example, the aforementioned execution entity can use Dijkstra's algorithm to perform a pre-defined traversal of the anisotropic neighborhood graph to generate the optimal local micropath cluster of the aforementioned path reference points.

[0061] The ninth sub-step involves parameterizing the arc length of the aforementioned optimal local micropath cluster to generate a node spacing sequence.

[0062] As an example, the aforementioned execution entity can measure the arc length (path length) of the optimal local micropath cluster from the starting point (reference point) to each endpoint, obtaining a node interval sequence. The node interval in this sequence can be the arc length of the optimal local micropath cluster. For example, the arc length of the micropath to the left is 2 meters, to the left front is 5 meters, directly ahead is 10 meters, to the right front is 9 meters, and to the right is 8 meters. Then, at this reference point, we obtain a set of safe distance values ​​in different directions [2, 5, 10, 9, 8].

[0063] The second step is to determine the effective distribution distance set as the set of node interval sequences that meet the preset range conditions.

[0064] The aforementioned preset range condition can be the minimum value in a pre-defined node interval sequence.

[0065] As an example, the aforementioned execution entity can combine the node interval sequences that satisfy the preset range conditions in the obtained node interval sequence set into an effective distribution distance set. This combination can be a merging process.

[0066] The content in steps one and two above constitutes an inventive point of this disclosure, solving the technical problem of "a high probability of collision, reducing the safety of path planning." Factors leading to a high probability of collision and reduced safety of path planning often include: existing path planning methods are often unable to handle spaces with irregular obstacles, resulting in poor obstacle avoidance of the generated safe paths, thus increasing the probability of collision and reducing the safety of path planning. Solving these factors can improve the safety of path planning. To achieve this, firstly, in the first sub-step, image data is collected from a preset fan-shaped sensing area around the aforementioned path reference point to obtain a reference point environmental image dataset. Secondly, the reference point environmental image data in the aforementioned reference point environmental image dataset is time-stamped and spatially coordinate-registered to generate an environmental perception dataset. Thirdly, semantic point cloud fragments are determined from the aforementioned environmental perception dataset to obtain a semantic point cloud fragment set. Fourthly, the semantic point cloud fragment set is coordinate-registered with a preset set of building component vertex coordinates to obtain a semantic point cloud fragment coordinate set. A set of semantic point cloud fragment coordinates with precise coordinates and rich semantics was generated, providing a complete data foundation for subsequent steps. Then, in the fifth sub-step, risk semantic joint mapping was performed on the aforementioned semantic point cloud fragment coordinate set to generate a local risk semantic tensor field. This elevates the environment from a binary obstacle space to a continuous risk field, representing path planning safety with risk values, quantifying obstacle avoidance effectiveness, and helping to reduce the probability of collisions. In the sixth sub-step, based on the aforementioned local risk semantic tensor field, an anisotropic neighborhood graph was constructed at the aforementioned path reference point. In the seventh sub-step, the aforementioned anisotropic neighborhood graph was traversed under preset conditions to generate the optimal local micropath cluster for the current reference point. Transforming the risk field into anisotropic graph and searching for it automatically discovers the optimal safe passage in complex environments, finding the lowest-cost lateral micropath that comprehensively considers risk and distance. Therefore, even with irregular obstacles, this scheme can reduce the probability of collisions. In the eighth sub-step, the arc length of the aforementioned optimal local micropath cluster was parameterized to generate a node interval sequence. Therefore, it not only improves the obstacle avoidance effect of safe paths and reduces the probability of collisions, but also improves the safety of path planning.

[0067] Optionally, the aforementioned executing entity can generate an effective distribution distance set based on the aforementioned path reference point set through the following steps: The first step involves generating a first ray equation and a second ray equation for each path reference point in the aforementioned path reference point set. The first ray equation represents the equation for a ray emanating from the path reference point in the positive direction towards a building component, and the second ray equation represents the equation for a ray emanating from the path reference point in the opposite direction towards another building component. The positive direction can include above and to the left. The opposite direction can include below and to the right.

[0068] The equation for the first ray can be the reference point coordinates + t × the unit angle bisector vector in the positive direction, where t is greater than 0 and represents the distance from the reference point to the building component. The equation for the second ray can be the reference point coordinates + m × the unit angle bisector vector in the opposite direction, where m is less than 0 and represents the distance from the reference point to the building component.

[0069] Optionally, the aforementioned executing entity can generate the first ray equation and the second ray equation based on the aforementioned path reference point through the following steps: The first sub-step involves determining the preceding and succeeding vectors of the aforementioned path reference points to generate the preceding and succeeding vectors of the reference points.

[0070] The preceding vector can be a vector pointing from the preceding node to the reference point. The preceding node is the node preceding the path reference point, with the direction from the start point to the end point as the forward direction. The succeeding vector can be a vector pointing from the reference point to the succeeding node. The succeeding node is the node following the path reference point, with the direction from the start point to the end point as the forward direction.

[0071] The second sub-step involves standardizing the aforementioned reference point preceding vector and reference point succeeding vector to generate standardized reference point preceding vector and standardized reference point succeeding vector.

[0072] As an example, the aforementioned execution entity can first determine the modulus of the preceding and succeeding vectors of the reference point. Then, it can divide the preceding and succeeding vectors of the reference point by the modulus to obtain the standardized preceding and succeeding vectors of the reference point.

[0073] The third sub-step involves generating a safety space vector based on the aforementioned standardized reference point preceding vector and the aforementioned standardized reference point succeeding vector.

[0074] As an example, the aforementioned executing entity can add the preceding vector of the standardized reference point and the succeeding vector of the standardized reference point to obtain the angle bisector vector representing the direction of path forward, which serves as the safety space vector.

[0075] The fourth sub-step is to standardize the aforementioned security space vector to generate a unit security space vector.

[0076] As an example, the aforementioned executing entity can divide each of the two components in the aforementioned security space vector by the modulus of the aforementioned security space vector to obtain a unit security space vector.

[0077] The fifth sub-step is to determine the reverse vector of the unit safety space based on the aforementioned unit safety space vector.

[0078] As an example, the aforementioned execution entity can invert the aforementioned unit security space vector to obtain the unit security space inverse vector. For example, if the unit security space vector is (0.8, 0.5), then the unit security space inverse vector is (-0.8, -0.5).

[0079] The sixth sub-step involves constructing the first ray equation based on the aforementioned unit safety space vector and the aforementioned path reference point.

[0080] As an example, the aforementioned executing entity can add the aforementioned path reference point to the aforementioned unit safety space vector multiplied by the distance from the path reference point to the building component to obtain the first ray equation. That is, the first ray equation is: [path reference point coordinates] + [t × unit safety space vector] (unit angle bisector vector in the positive direction), where t is greater than 0, and t represents the distance from the reference point to the building component.

[0081] The seventh sub-step involves constructing the second ray equation based on the aforementioned unit safety space reverse vector and the aforementioned path reference point.

[0082] As an example, the aforementioned executing entity can add the aforementioned path reference point to the aforementioned unit safety space reverse vector multiplied by the distance from the path reference point to the building component to obtain the second ray equation. That is, the second ray equation is: [path reference point coordinates] + [m × unit safety space reverse vector] (unit angle bisector vector in the opposite direction), where m is less than 0, and m represents the distance from the reference point to the building component.

[0083] The second step is to generate an effective distribution distance set based on the above vertex coordinate set, the above first ray equation, and the above second ray equation.

[0084] Optionally, the aforementioned execution entity can generate an effective distribution distance set based on the aforementioned vertex coordinate set, the aforementioned first ray equation, and the aforementioned second ray equation through the following steps: The first sub-step involves performing the following second processing step for each vertex coordinate group in the aforementioned vertex coordinate set: Sub-step one involves parameterizing the above vertex coordinate set into line segments to generate a set of line segment equations for building components.

[0085] As an example, the aforementioned execution entity can parameterize each edge corresponding to the vertex coordinate group using Q(s) = a + s × (ba) to generate the building component line segment equations, thus obtaining the building component line segment equation set. Here, Q(s) represents the building component line segment equation in the building component line segment equation set. The range of s is [0, 1]. s is used to determine the positional relationship between the intersection point and the line segment; that is, when s = 0, it indicates that the intersection point is located at the starting point of the line segment. When s = 1, it indicates that the intersection point is located at the ending point of the line segment. When s is at (0, 1), it indicates that the intersection point is located on a line segment excluding the endpoints. a represents the coordinates of the left endpoint of the edge (the direction of the ray is to the left), and b represents the coordinates of the right endpoint of the edge. For example, if a represents (5, 1) and b represents (5, 4), then Q(s) = (5, 1) + s × (0, 3).

[0086] Sub-step two: Based on the above set of line segment equations for building components, the above first ray equation, and the above second ray equation, generate the coordinate set of the forward intersection point and the coordinate set of the reverse intersection point.

[0087] Optionally, the aforementioned execution entity can generate a set of coordinates for positive intersection points and a set of coordinates for negative intersection points based on the aforementioned set of line segment equations for building components, the aforementioned first ray equation, and the aforementioned second ray equation through the following steps: The first step is to solve for the line segment equation of each building component in the above set of building component line segment equations and the first ray equation to generate a first parameter and a second parameter. The first parameter represents the distance from the reference point to the positive intersection point, and the second parameter represents whether the positive intersection point is located on the edge containing the building component.

[0088] As an example, the aforementioned executing entity can equate each building component line segment equation in the aforementioned set of building component line segment equations with the aforementioned first ray equation to determine the first and second parameters in the aforementioned set of building component line segment equations and the aforementioned first ray equation, i.e., the first parameter is t and the second parameter is s. For example, path reference point coordinates + t × unit safety space vector = a + s × (ba) to generate the first parameter t and the second parameter s. Specifically, if the path reference point coordinates are (2, 2), the unit safety space vector is (1, 0), a is (5, 1), and b is (5, 4), then (2, 2) + t × (1, 0) = (2 + t, 2) = (5, 1) + s × (0, 3) = (5, 1 + 3s), then t = 3, s ≈ 0.33. This means that the distance from the intersection point to the path reference point is 3, and the intersection point is located at approximately 1 / 3 of the position of the line segment emanating from the path reference point.

[0089] The second step is to determine the coordinates of the positive intersection point based on the first parameter and the second parameter satisfying the preset first condition, and obtain the set of positive intersection point coordinates.

[0090] Here, the aforementioned first preset condition can be "the first parameter t is greater than 0, and the second parameter s is within [0, 1]".

[0091] As an example, the aforementioned execution entity can substitute the coordinates of each path reference point in the line segment, the corresponding unit safety space vector of the path reference point coordinates, and the first parameter into the first ray equation to generate the coordinates of the positive intersection point, thus obtaining the set of positive intersection point coordinates.

[0092] The third step involves solving the line segment equations and second ray equations for each building component in the aforementioned set of building component line segment equations to generate the third and fourth parameters. The third parameter represents the distance from the reference point to the reverse intersection point, and the fourth parameter represents whether the reverse intersection point is located on the edge containing the building component.

[0093] As an example, the aforementioned execution entity can equate each building component line segment equation in the aforementioned building component line segment equation set with the aforementioned second ray equation to determine the third and fourth parameters in the aforementioned building component line segment equation set and the aforementioned second ray equation, i.e., the third parameter is m and the fourth parameter is s (same as the second parameter). For example, path reference point coordinates + m × unit safety space vector = a + s × (ba) to generate the third parameter m and the fourth parameter s. Specifically, if the path reference point coordinates are (5, 5), the unit safety space vector is (1, 0), a is (2, 4), and b is (2, 6), then (5, 5) + m × (1, 0) = (5 + m, 5) = (2, 4) + s × (0, 2) = (2, 4 + 2s), then m = -3 and s = 0.5. This means that the intersection point is located in the opposite direction of the path reference point, the distance from the path reference point is 3, and the intersection point is located at approximately 1 / 2 of the position of the line segment emanating from the path reference point.

[0094] Fourth step: In response to determining that the above third parameter and the above fourth parameter satisfy the preset second condition, determine the coordinates of the reverse intersection point according to the above third parameter, and obtain the set of coordinates of the reverse intersection point.

[0095] Here, the first preset condition can be "the third parameter m is less than 0, and the fourth parameter s is within [0, 1]".

[0096] As an example, the aforementioned execution entity can substitute the coordinates of each path reference point in the line segment, the corresponding unit safety space reverse vector of the path reference point coordinates, and the third parameter into the second ray equation to generate the coordinates of the reverse intersection point, thus obtaining the set of reverse intersection point coordinates.

[0097] Sub-step three: Determine the coordinates of the intersection points that are closest to the path reference points corresponding to the first ray equation and the second ray equation, respectively, in the forward intersection point coordinate set and the reverse intersection point coordinate set.

[0098] As an example, the aforementioned execution entity can determine the distance between the path reference point and the coordinates of each forward intersection point in the forward intersection point coordinate set, thus obtaining a forward intersection point distance set. Then, it can determine the distance between the path reference point and the coordinates of each reverse intersection point in the reverse intersection point coordinate set, thus obtaining a reverse intersection point distance set. Finally, the coordinates corresponding to the smallest intersection point distance in the aforementioned forward intersection point distance set and the aforementioned reverse intersection point distance set are respectively determined as the minimum forward intersection point coordinates and the minimum reverse intersection point coordinates.

[0099] The second sub-step generates an effective distribution distance set based on the obtained minimum forward intersection point coordinate set and minimum reverse intersection point coordinate set.

[0100] Optionally, the aforementioned executing entity can generate an effective distribution distance set based on the obtained minimum forward intersection coordinate set and minimum reverse intersection coordinate set through the following steps: The first step is to determine the boundary distribution distance set by the distance between the obtained minimum positive intersection point coordinate set and minimum negative intersection point coordinate set and the path reference point corresponding to the first ray equation and the second ray equation.

[0101] As an example, the aforementioned executing entity can determine the boundary distribution distance set by Euclidean distance between the obtained minimum forward intersection point coordinate set and minimum reverse intersection point coordinate set and the coordinates of the path reference point.

[0102] The second step is to generate an effective distribution distance set based on the above boundary distribution distance set and the preset safety boundary distance.

[0103] The aforementioned preset safety boundary distance can be a pre-defined boundary distance at which a collision will not occur.

[0104] As an example, the aforementioned executing entity can subtract the preset safety boundary distance from each boundary distribution distance in the aforementioned boundary distribution distance set to generate an effective distribution distance, thus obtaining an effective distribution distance set.

[0105] The third step involves determining that there is an effective distribution distance less than a preset value in the above effective distribution distance set, identifying the boundary distribution distance corresponding to at least one effective distribution distance less than the preset value as an effective distribution distance group, and replacing the effective distribution distance group with at least one effective distribution distance less than the preset value in the above effective distribution distance set to obtain an effective distribution distance set.

[0106] The aforementioned preset value can be a pre-defined minimum value. For example, the aforementioned preset value can be 0.

[0107] As an example, the aforementioned execution entity can remove at least one valid distribution distance from the set of valid distribution distances that is less than a preset value, resulting in a set of valid distribution distances after removal. Then, the set of valid distribution distances is added to the set of valid distribution distances after removal, thus obtaining a set of valid distribution distances. Here, valid distribution distances less than 0 will inevitably collide with building components, so there is no need to subtract the preset safety boundary distance; instead, the distance from the reference point to the building component is directly used as the valid distribution distance, which effectively allows for fault tolerance.

[0108] Step 2033: Divide each effective distribution distance in the above effective distribution distance set into equal parts to generate effective distribution node distances, thus obtaining the effective distribution node distance set.

[0109] In some embodiments, the execution entity may divide each effective distribution distance in the effective distribution distance set into equal parts to generate effective distribution node distances, thereby obtaining an effective distribution node distance set.

[0110] As an example, the aforementioned execution entity can first determine the number of detection nodes. Then, according to the number of detection nodes, it determines the segment length for each effective distribution distance in the aforementioned effective distribution distance set to generate effective distribution segment lengths, thus obtaining a set of effective distribution segment lengths as the effective distribution node distance set. For example, assuming the number of detection nodes is 4 and the effective distribution distance is 560, the corresponding effective distribution segment length is 560 / (4+1) = 112, meaning that a node is equally divided every 112 units of distance.

[0111] In the process of adopting technical solutions to address the problems mentioned in the background section, the following issues often arise: Traditional equal division methods often fail to consider the safety differences of the nodes themselves, which may result in the generated path being too close to obstacles or not smooth enough, thus reducing the safety of actual path passage.

[0112] Faced with the above-mentioned technical problems, the inventors decided to adopt the following solution: Optionally, the aforementioned executing entity can perform the following steps to equally divide each effective distribution distance in the aforementioned effective distribution distance set to generate effective distribution node distances, thus obtaining the effective distribution node distance set: First, for each effective distribution distance in the above effective distribution distance set, perform the following third processing step: The first sub-step is to score the effective distribution distance to generate an effective distribution distance risk score and an effective distribution distance traversability score. The effective distribution distance risk score represents the degree of proximity to the safety boundary, and the effective distribution distance traversability score represents the cost of moving from the previous path node to the current path node.

[0113] As an example, the aforementioned execution entity can calculate the risk score for the effective distribution distance using the formula: 1 / node position + 1 / (distance from node to safety boundary - node position). For instance, if the node position is 1 meter and the distance from the node to the safety boundary is 5 meters, the effective distribution distance risk score is 5 / 4. The closer the node is to the safety boundary, the smaller the denominator, and the higher the effective distribution distance risk score. Then, the effective distribution distance is assessed using the straight-line distance between the current node and the previous node to generate an effective distribution distance traversal score. For example, if the previous node is (2, 2) and the current node is (5, 5), the effective distribution distance traversal score is the square root of 18, approximately 4.24.

[0114] The second sub-step involves weighting and fusing the aforementioned effective distribution distance risk score and effective distribution distance access score according to preset risk weights and access weights to obtain a comprehensive cost function.

[0115] The preset risk weight is 0.7, and the preset passage weight is 0.3.

[0116] As an example, the aforementioned executing entity can obtain the comprehensive cost function by weighting and fusing the effective distribution distance risk score and the effective distribution distance access score using the comprehensive cost function = risk weight × effective distribution distance risk score + access weight × effective distribution distance access score.

[0117] The second step involves performing the following iterative processing steps on the obtained comprehensive cost function set: The first sub-step is to select an initial random population, wherein the initial random population includes a preset number of path nodes.

[0118] As an example, the aforementioned execution entity can randomly generate 4 schemes within the range [0, 10]. Each scheme includes 2 randomly sorted positions to obtain an initial random population. For example, the initial random population could be {coordinates of path node A: [1.5, 8.5], coordinates of path node B: [3.0, 7.0], coordinates of path node C: [4.5, 9.0]}.

[0119] The second sub-step involves determining the comprehensive cost value of the initial random population based on the obtained comprehensive cost function set, resulting in a comprehensive cost value set, which is the set of comprehensive cost values ​​for all path nodes in the initial random population.

[0120] As an example, the aforementioned executing entity can substitute the path nodes in the initial random population into the comprehensive cost function set to determine the comprehensive cost value, thereby obtaining the comprehensive cost value set.

[0121] The third sub-step involves converting each comprehensive value in the aforementioned comprehensive value set into fitness, thus obtaining a fitness set.

[0122] As an example, the aforementioned executing entity can convert each comprehensive value in the comprehensive value set into fitness by 1 / (1+comprehensive value), thus obtaining a fitness set.

[0123] The fourth sub-step involves selecting path node schemes with fitness values ​​greater than a preset fitness value from the initial random population based on the fitness set mentioned above, as the target path scheme.

[0124] Here, the preset fitness value can be 0.8. The above path node scheme can be "Path node A: [1.5, 8.5], Path node B: [3.0, 7.0]".

[0125] As an example, the aforementioned executing entity can determine the fitness values ​​in the fitness set that are greater than a preset fitness value as the target fitness. Then, the path node schemes corresponding to the target fitness in the aforementioned initial random population are determined as the target path schemes.

[0126] The fifth sub-step involves mixing the aforementioned target path schemes to generate a candidate scheme set, and using this candidate scheme set as the initial random population to continue executing the aforementioned iterative processing steps.

[0127] As an example, the aforementioned execution entity can perform single-point cross-intersection on the target path scheme by exchanging nodes at preset random positions to generate a candidate scheme set, and use this candidate scheme set as the initial random population to continue executing the aforementioned iterative processing steps. The preset random position can be a pre-defined second node. For example, the target path scheme can be "path node A: [1.5, 8.5], path node B: [3.0, 7.0]", and after single-point cross-intersection, it becomes "path node A: [1.5, 7.0], path node B: [3.0, 8.5]", which is the candidate scheme set.

[0128] The third step is to select the target path scheme with the highest fitness from the target path scheme set obtained in response to the determination that the number of iterations of the above iterative processing steps has reached the preset number of iterations. Then, each effective distribution distance in the above effective distribution distance set is divided to generate effective distribution node distances, thus obtaining the effective distribution node distance set.

[0129] Here, the preset number of iterations can be 5.

[0130] As an example, the aforementioned execution entity determines the target path scheme with the highest fitness in the obtained target path scheme set as the optimal path scheme. It then divides each effective distribution distance in the above effective distribution distance set to generate effective distribution node distances, thus obtaining an effective distribution node distance set. For example, the obtained target path scheme set could be {path node X fitness 0.8: [2.2, 7.8], path node Y fitness 0.79: [2.5, 7.5]}. The target path scheme with the highest fitness is [2.2, 7.8]. Therefore, the path node at a distance of 2.2 from the reference point and 7.8 from the boundary is the dividing point. That is, using 2.2 as the equal division point, the division starts from the reference point to obtain the effective distribution node distance set. Figure 5 As shown, the distance between the reference point and the division points is 2.2. The distances between all the division points are the same.

[0131] The relevant content in steps one through three above constitutes an inventive point of this disclosure, solving the technical problem of "reducing the safety of actual path passage." Factors that lead to the inability to consider the safety differences of the nodes themselves, thus reducing the safety of actual path passage, often include: traditional equal-division methods typically fail to consider the safety differences of the nodes themselves, resulting in generated paths that may be too close to obstacles or not smooth enough, thereby reducing the safety of actual path passage. Solving these factors can improve the safety of actual path passage. To achieve this, firstly, the effective distribution distance is scored to generate an effective distribution distance risk score and an effective distribution distance passage score. Based on preset risk weights and passage weights, the effective distribution distance risk score and the effective distribution distance passage score are weighted and fused to obtain a comprehensive cost function. The following iterative processing steps are performed on the obtained comprehensive cost function set: an initial random population is selected, wherein the initial random population includes a preset number of path nodes. Based on the obtained comprehensive cost function set, the comprehensive cost value of the initial random population is determined, resulting in a comprehensive cost value set. Therefore, by randomly generating multiple possible node distribution schemes, rich initial solutions and diversity are provided for the optimization process, preventing the algorithm from prematurely falling into local optima. Next, each comprehensive cost value in the comprehensive cost value set is converted into fitness, resulting in a fitness set. Converting comprehensive cost into fitness allows for the identification of subsequent excellent solutions (low cost, high fitness). Based on the fitness set, path node schemes with fitness greater than a preset fitness value are selected from the initial random population as target path schemes. By considering the safety differences of the nodes themselves, the generated paths may be too close to obstacles, improving the safety of actual path passage. The aforementioned target path schemes are mixed to generate a candidate scheme set, which is then used as an initial random population to continue the iterative processing steps. In response to the determination that the number of iterations in the iterative processing steps has reached a preset number, the target path scheme with the highest fitness is selected from the obtained target path scheme set. This is used to partition each effective distribution distance in the effective distribution distance set, generating effective distribution node distances, thus obtaining an effective distribution node distance set. Therefore, by using random generation and fitness transformation, considering the inherent safety differences of nodes, the generated path can be prevented from being too close to obstacles. Furthermore, the generated target path scheme avoids being too rough, thereby improving the safety of actual path passage.

[0132] Step 2034: In response to determining that the effective distribution node distances in the above effective distribution node distance set meet the preset range conditions, the effective distribution node distance set is determined as a safe planning path.

[0133] In some embodiments, the execution entity may determine the effective distribution node distance set as a safe planning path in response to determining that the effective distribution node distances in the effective distribution node distance set meet a preset range condition, wherein the safe planning path represents a planning path that will not cause a collision.

[0134] The aforementioned preset range condition can be a pre-defined condition that "does not exist inside the aforementioned building components".

[0135] As an example, the aforementioned execution entity can connect the distances of each effective distribution node in the effective distribution node distance set that meets the preset range conditions to obtain a safe planning path that is spatially distributed and maintains at least a preset safety boundary distance from all obstacles.

[0136] Further reference Figure 3 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a collision-free path planning device based on building components. These device embodiments are similar to... Figure 2 Corresponding to the method embodiments shown, this collision-free path planning device based on building components can be specifically applied to various electronic devices.

[0137] like Figure 3 As shown, a collision-free path planning device 300 based on building components in some embodiments includes: a processing unit 301, a connection unit 302, and an execution unit 303. The processing unit 301 is configured to read the vertex coordinate set of each building component within a preset spatial range, wherein the vertex coordinate set is the coordinate of each vertex of each building component in a two-dimensional planar map; the connection unit 302 is configured to connect the initial path start point with each arbitrary end point through feasible paths to obtain an initial planned path set, wherein the feasible path represents the absence of obstacles in the path between the initial path start point and any arbitrary end point; the execution unit 303 is configured to perform the following first processing steps for each initial planned path in the initial planned path set: determining each intermediate node of the initial planned path as a path reference point set; generating an effective distribution distance set based on the path reference point set; dividing each effective distribution distance in the effective distribution distance set equally to generate an effective distribution node distance set; and determining the effective distribution node distance set as a safe planned path in response to determining that the effective distribution node distance in the effective distribution node distance set meets a preset range condition, wherein the safe planned path represents a planned path that will not cause a collision.

[0138] It is understandable that the units described in the building component-based collision-free path planning device 300 are related to the reference... Figure 2The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the collision-free path planning device 300 based on building components and the units contained therein, and will not be repeated here.

[0139] The following is for reference. Figure 4 It shows a schematic diagram of the structure of an electronic device 400 (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0140] like Figure 4 As shown, the electronic device 400 may include a processing unit 401 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the electronic device 400. The processing unit 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0141] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 4 Each box shown can represent a device or multiple devices as needed.

[0142] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from storage device 408, or installed from ROM 402. When the computer program is executed by processing device 401, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0143] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0144] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0145] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: read a set of vertex coordinates of each building component within a preset spatial range, wherein the set of vertex coordinates represents the vertex coordinates of each building component in a two-dimensional planar map; connect the initial path start point with each arbitrary end point using feasible paths to obtain an initial planned path set, wherein the feasible path represents the absence of obstacles in the path between the initial path start point and any arbitrary end point; for each initial planned path in the initial planned path set, perform the following first processing step: determine each intermediate node of the initial planned path as a path reference point set; generate an effective distribution distance set based on the path reference point set; divide each effective distribution distance in the effective distribution distance set into equal parts to generate effective distribution node distances, obtaining an effective distribution node distance set; in response to determining that the effective distribution node distances in the effective distribution node distance set meet a preset range condition, determine the effective distribution node distance set as a safe planned path, wherein the safe planned path represents a planned path that will not result in a collision.

[0146] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0147] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0148] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0149] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for collision-free path planning based on building components, characterized in that, include: Read the vertex coordinate set of each building component within a preset spatial range, wherein the vertex coordinate set is the coordinate of each vertex of each building component in a two-dimensional plane map; Connect the initial path start point with each arbitrary end point using feasible paths to obtain the initial planned path set, wherein the feasible path indicates that there are no obstacles in the path between the initial path start point and any arbitrary end point; For each initial planned path in the initial planned path set, perform the following first processing step: Each intermediate node of the initial planned path is determined as a path reference point set; Based on the path reference point set, generate an effective distribution distance set; Each effective distribution distance in the effective distribution distance set is divided equally to generate effective distribution node distances, thus obtaining an effective distribution node distance set; In response to determining that the effective distribution node distances in the effective distribution node distance set meet a preset range condition, the effective distribution node distance set is determined as a safe planning path, wherein the safe planning path represents a planning path that will not cause a collision.

2. The method according to claim 1, characterized in that, The step of generating an effective distribution distance set based on the path reference point set includes: For each path reference point in the set of path reference points, a first ray equation and a second ray equation are generated based on the path reference point, wherein the first ray equation represents the equation of a ray from the path reference point toward a building component in the positive direction, and the second ray equation represents the equation of a ray from the path reference point toward another building component in the opposite direction. Based on the set of vertex coordinates, the first ray equation, and the second ray equation, generate an effective distribution distance set.

3. The method according to claim 2, characterized in that, The step of generating the first ray equation and the second ray equation based on the path reference point includes: The preceding and succeeding vectors of the path reference points are determined to generate the preceding and succeeding vectors of the reference points. The reference point preceding vector and the reference point succeeding vector are standardized to generate standardized reference point preceding vector and standardized reference point succeeding vector. A safety space vector is generated based on the preceding vector of the standardized reference point and the succeeding vector of the standardized reference point. The security space vector is standardized to generate a unit security space vector; Based on the unit safety space vector, determine the unit safety space reverse vector; Based on the unit safety space vector and the path reference point, construct the first ray equation; The second ray equation is constructed based on the unit safety space reverse vector and the path reference point.

4. The method according to claim 2, characterized in that, The step of generating an effective distribution distance set based on the vertex coordinate set, the first ray equation, and the second ray equation includes: For each vertex coordinate group in the vertex coordinate group set, perform the following second processing step: The vertex coordinate set is parameterized to generate a set of line segment equations for building components; Based on the set of line segment equations of the building components, the first ray equation, and the second ray equation, generate a set of coordinates for positive intersection points and a set of coordinates for negative intersection points; The coordinates of the intersection points that are least distant from the path reference points corresponding to the first ray equation and the second ray equation are determined in the forward intersection point coordinate set and the reverse intersection point coordinate set, respectively, as the minimum forward intersection point coordinates and the minimum reverse intersection point coordinates; Based on the obtained minimum forward intersection coordinate set and minimum reverse intersection coordinate set, generate the effective distribution distance set.

5. The method according to claim 4, characterized in that, The step of generating a set of coordinates for positive intersection points and a set of coordinates for negative intersection points based on the set of line segment equations of the building components, the first ray equation, and the second ray equation includes: Solve the line segment equation of each building component in the set of building component line segment equations and the first ray equation to generate a first parameter and a second parameter, wherein the first parameter represents the distance from the reference point to the positive intersection point, and the second parameter represents whether the positive intersection point is located on the edge where the building component is located; In response to determining that the first parameter and the second parameter satisfy a preset first condition, the coordinates of the positive intersection point are determined based on the first parameter, and a set of positive intersection point coordinates is obtained; Solve the line segment equation and the second ray equation for each building component in the set of building component line segment equations to generate a third parameter and a fourth parameter, wherein the third parameter represents the distance from the reference point to the reverse intersection point, and the fourth parameter represents whether the reverse intersection point is located on the edge where the building component is located. In response to determining that the third parameter and the fourth parameter satisfy a preset second condition, the coordinates of the reverse intersection point are determined based on the third parameter, and a set of reverse intersection point coordinates is obtained.

6. The method according to claim 4, characterized in that, The step of generating an effective distribution distance set based on the obtained minimum positive intersection point coordinate set and minimum negative intersection point coordinate set includes: The distances between the obtained minimum positive intersection point coordinate set and minimum negative intersection point coordinate set and the path reference points corresponding to the first ray equation and the second ray equation are determined as the boundary distribution distance set; Based on the boundary distribution distance set and the preset safety boundary distance, an effective distribution distance set is generated; In response to determining that there is an effective distribution distance less than a preset value in the effective distribution distance set, the boundary distribution distance corresponding to at least one effective distribution distance less than the preset value is determined as an effective distribution distance group, and the effective distribution distance group is replaced by at least one effective distribution distance less than the preset value in the effective distribution distance set to obtain an effective distribution distance set.

7. A collision-free path planning device based on building components, characterized in that, include: The processing unit is configured to read the vertex coordinate set of each building component within a preset spatial range, wherein the vertex coordinate set is the coordinate of each vertex of each building component in a two-dimensional plane map; The connection unit is configured to connect the initial path start point with each arbitrary end point through feasible paths to obtain an initial planned path set, wherein the feasible path indicates that there are no obstacles in the path between the initial path start point and any end point; The execution unit is configured to perform the following first processing steps for each initial planning path in the initial planning path set: determining each intermediate node of the initial planning path as a path reference point set; generating an effective distribution distance set based on the path reference point set; dividing each effective distribution distance in the effective distribution distance set into equal parts to generate effective distribution node distances, thus obtaining an effective distribution node distance set; and determining the effective distribution node distance set as a safe planning path in response to determining that the effective distribution node distances in the effective distribution node distance set meet a preset range condition, wherein the safe planning path represents a planning path that will not cause a collision.

8. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer-readable medium, characterized in that, It stores a computer program thereon, wherein the computer program, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images