Intelligent unmanned system path planning method and device based on grid bridge detection method

Abstract

This application relates to the field of intelligent autonomous unmanned systems technology, and particularly to a path planning method and apparatus for intelligent unmanned systems based on a grid bridge detection method. The method includes: modeling the entire environment as a grid map based on the size of the intelligent unmanned system and the maximum width of the current channel; using orthogonal bridges to determine the grids within the current channel and storing them in a list; extracting channel boundary points that meet preset judgment criteria to construct a connected landmark map; generating a path connecting the starting point and the target point; and obtaining the final planned path for the intelligent unmanned system. This application's embodiment can perform grid point detection for the current channel based on initial environment modeling and extract current channel boundary points to construct a connected landmark map, ultimately generating the intelligent unmanned system path. By rapidly identifying landmark points within the current channel, the construction rate of the connected landmark map is improved, thereby enhancing the efficiency and accuracy of intelligent unmanned system path planning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent unmanned systems, and in particular to an intelligent unmanned system path planning method and device based on a grid bridge detection method. BACKGROUND

[0002] Path planning research is of great significance to the field of unmanned systems and unmanned equipment. Improving the path planning capabilities of intelligent unmanned systems is the basis for intelligent unmanned systems to efficiently cope with more complex application scenarios and perform more complex tasks.

[0003] In related technologies, path planning of unmanned systems can be performed using sampling-based planning methods such as the Probabilistic Road Map (PRM) method and Rapidly-exploring Random Trees (RRT).

[0004] However, in related technologies, it is difficult to obtain sufficient landmark points in narrow passages, resulting in low efficiency of path planning algorithms and a significant decrease in convergence speed, which cannot guarantee the smooth generation of connected obstacle avoidance paths, making it difficult to apply to unstructured scenes containing narrow passages, and lacking in accuracy and practicality. SUMMARY

[0005] The present application provides an intelligent unmanned system path planning method and device based on a grid bridge detection method to solve the problems in related technologies, such as low efficiency of path planning algorithms and a significant decrease in convergence speed due to the difficulty in obtaining sufficient landmark points in narrow passages, which cannot guarantee the smooth generation of connected obstacle avoidance paths, making it difficult to apply to unstructured scenes containing narrow passages, and lacking in accuracy and practicality.

[0006] The first aspect of the present application provides an intelligent unmanned system path planning method based on a grid bridge detection method, comprising the following steps: modeling the entire environment as a grid map based on the size of the intelligent unmanned system and the maximum width of the current passage; using a predetermined length, direction, and orthogonal bridge with the same direction as the coordinate axis of the grid map to examine each grid of the grid map one by one, determine the grids inside the current passage, and obtain the passage internal grid points and store them in a list; extract the passage boundary points that meet the predetermined judgment criteria from the passage internal grid point storage list, and construct a connected landmark map using the passage boundary points; search in the connected landmark map to generate a path connecting the starting point and the target point, and obtain the final intelligent unmanned system planning path.

[0007] Optionally, in one embodiment of this application, determining the grid inside the current channel includes: if the grid point corresponding to the midpoint of the orthogonal bridge is located in free space, wherein the grid points corresponding to any pair of bridge endpoints are located inside obstacles, then they are determined to be grid points inside the current channel.

[0008] Optionally, in one embodiment of this application, the preset judgment criterion is that if any grid point is detected to be inside the current channel and none of the adjacent grid points are grid points inside the current channel, then the grid point and the previous grid point inside the current channel in the detection process are considered to be the channel boundary point.

[0009] Optionally, in one embodiment of this application, the step of constructing a connected landmark map using the channel boundary points includes: using the starting point, the target point, and the channel boundary points as nodes of the connected landmark map, wherein if the line segments formed by two nodes are all located in free space, then there is an edge between the two nodes, thus constructing an initial landmark map; based on the initial landmark map, uniformly sampling is performed sequentially in the list of grid points stored in the channel and the environmental grid map, wherein if the sampling point is located in free space, then the sampling point is used as a new node, and it is determined whether the line segments formed by the new sampling point and other nodes are all located in free space; if so, then there is an edge between the new node and the corresponding node, thus generating the connected landmark map.

[0010] Optionally, in one embodiment of this application, after generating the path connecting the starting point and the target point, the method further includes: smoothing the path.

[0011] A second aspect of this application provides a path planning device for an intelligent unmanned system based on a grid bridge detection method, comprising: a modeling module for modeling the entire environment as a grid map based on the size of the intelligent unmanned system and the maximum width of the current channel; a verification module for verifying each grid of the grid map one by one using orthogonal bridges of preset length and direction consistent with the coordinate axis direction of the grid map, determining the grids inside the current channel, and storing the grid points inside the channel in a list; an extraction module for extracting channel boundary points that meet preset judgment criteria from the list of grid points inside the channel, and constructing a connectivity landmark map using the channel boundary points; and a planning module for searching in the connectivity landmark map to generate a path connecting the starting point and the target point, thereby obtaining the final planned path for the intelligent unmanned system.

[0012] Optionally, in one embodiment of this application, the inspection module includes: a judgment unit, used to determine that if the grid point corresponding to the midpoint of the orthogonal bridge is located in free space, wherein any pair of grid points corresponding to the bridge endpoints are located inside an obstacle, then the grid point is determined to be a grid point inside the current channel.

[0013] Optionally, in one embodiment of this application, the preset judgment criterion is that if any grid point is detected to be inside the current channel and none of the adjacent grid points are grid points inside the current channel, then the grid point and the previous grid point inside the current channel in the detection process are considered to be the channel boundary point.

[0014] Optionally, in one embodiment of this application, the extraction module includes: a construction unit, used to use the starting point, the target point, and the channel boundary point as nodes of the connected landmark map, wherein if the line segment formed by two nodes is entirely located in free space, then there is an edge between the two nodes, thus constructing an initial landmark map; and a sampling unit, used to perform uniform sampling in the list of grid points stored in the channel and the environment grid map in sequence based on the initial landmark map, wherein if the sampling point is located in the free space, then the sampling point is used as a new node, and it is determined whether the line segment formed by the new sampling point and other nodes is entirely located in the free space; if so, then there is an edge between the new node and the corresponding node, thus generating the connected landmark map.

[0015] Optionally, in one embodiment of this application, the apparatus further includes a smoothing unit for smoothing the path after generating the path connecting the starting point and the target point.

[0016] A third aspect of this application provides a system comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent unmanned system path planning method based on the grid bridge detection method as described in the above embodiments.

[0017] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent unmanned system path planning method based on grid bridge detection.

[0018] This application embodiment can detect grid points in the current channel based on environmental initialization modeling and extract boundary points of the current channel to construct a connected landmark map, ultimately generating a path for the intelligent unmanned system. By rapidly identifying landmark points within the current channel, the construction rate of the connected landmark map is improved, thereby enhancing the efficiency and accuracy of path planning for the intelligent unmanned system. This solves the problems in related technologies, such as the difficulty in obtaining sufficient landmark points in narrow channels, leading to low efficiency and significantly reduced convergence speed in path planning algorithms. These limitations prevent the successful generation of connected obstacle avoidance paths, making them unsuitable for unstructured scenarios containing narrow channels, and failing to meet the requirements for efficient and accurate path planning for intelligent unmanned systems, resulting in insufficient accuracy and practicality.

[0019] Additional aspects and advantages of this application 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 application. Attached Figure Description

[0020] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0021] Figure 1 This is a flowchart of a path planning method for an intelligent unmanned system based on a grid bridge detection method, according to an embodiment of this application.

[0022] Figure 2 This is a three-dimensional orthogonal bridge schematic diagram according to an embodiment of this application;

[0023] Figure 3 This is a schematic diagram of the boundary points of a two-dimensional narrow channel according to an embodiment of this application;

[0024] Figure 4 This is a schematic diagram illustrating node identifier index adjustment according to one embodiment of this application;

[0025] Figure 5 This is a schematic diagram of a path smoothing process according to an embodiment of this application;

[0026] Figure 6 This is a schematic diagram of a path smoothing adjustment process according to an embodiment of this application;

[0027] Figure 7 This is a flowchart illustrating path planning for an intelligent unmanned system based on the grid bridge method in a narrow space, according to one embodiment of this application.

[0028] Figure 8 This is a schematic diagram of the intelligent unmanned system path planning device based on the grid bridge detection method according to an embodiment of this application;

[0029] Figure 9This is a schematic diagram of the system according to an embodiment of this application. Detailed Implementation

[0030] The embodiments of this application are described in detail below. Examples of these embodiments are shown 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 application, and should not be construed as limiting this application.

[0031] The following description, with reference to the accompanying drawings, illustrates a path planning method and apparatus for intelligent unmanned systems based on a grid bridge detection method, according to embodiments of this application. Addressing the issues raised in the background section regarding the related technologies, such as the difficulty in acquiring sufficient landmarks within narrow passages leading to low efficiency and significantly reduced convergence speed in path planning algorithms, the inability to guarantee the smooth generation of connected obstacle avoidance paths, and the difficulty in applying these methods to unstructured scenarios containing narrow passages, this application fails to meet the requirements for efficient and accurate path planning in intelligent unmanned systems, resulting in insufficient accuracy and practicality. This application provides a path planning method for intelligent unmanned systems based on a grid bridge detection method. Embodiments of this application can perform grid point detection for the current passage based on environmental initialization modeling and extract the current passage boundary points to construct a connected landmark map, ultimately generating the intelligent unmanned system path. By rapidly identifying landmarks within the current passage, the construction rate of the connected landmark map is improved, thereby enhancing the efficiency and accuracy of intelligent unmanned system path planning. This solves the problems in related technologies, such as the difficulty in obtaining a sufficient number of landmarks in narrow passages, which leads to low efficiency of path planning algorithms, a significant decrease in convergence speed, inability to guarantee the smooth generation of connected obstacle avoidance paths, difficulty in applying to unstructured scenarios containing narrow passages, inability to meet the path planning requirements of efficient and accurate intelligent unmanned systems, and insufficient accuracy and practicality.

[0032] Specifically, Figure 1 This is a flowchart illustrating a path planning method for an intelligent unmanned system based on a grid bridge detection method, provided in an embodiment of this application.

[0033] like Figure 1 As shown, the path planning method for intelligent unmanned systems based on grid bridge detection includes the following steps:

[0034] In step S101, the entire environment is modeled as a grid map based on the size of the intelligent unmanned system and the maximum width of the current channel.

[0035] It is understood that, in the embodiments of this application, the working environment of the current intelligent unmanned system in the channel can be rasterized to construct a raster map. The discrete precision of the rasterization is determined by the size of the intelligent unmanned system and the maximum width of the current channel.

[0036] In actual execution, within the current channel, the cell grid corresponding to free space can be set to 0, and the cell grid corresponding to obstacles can be set to 1. Thus, the entire environment can be modeled as a grid map based on the size of the intelligent unmanned system and the maximum width of the current channel.

[0037] In step S102, using orthogonal bridges with preset lengths and directions consistent with the coordinate axes of the grid map, each grid cell of the grid map is checked one by one to determine the grid cells inside the current channel and store the grid points inside the channel in a list.

[0038] It is understood that in the embodiments of this application, the preset length is related to the maximum width of the current channel. Each grid cell of the grid map can be checked one by one by selecting an orthogonal bridge with a direction consistent with the coordinate axis direction of the grid map that conforms to the preset length.

[0039] It should be noted that the preset length can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0040] In actual operation, when the current channel is a narrow channel, the two-dimensional space length in the preset length can be set to 22r. max The length of the three-dimensional space can be set to 23r. max , where r max This represents the maximum width of the narrow passage. An orthogonal bridge of preset length, aligned with the coordinate axes of the grid map, can be used. The narrow passage's internal grid points are identified by examining each grid cell individually, and these points are stored in a list NList. For example, ... Figure 2 The diagram shown is a schematic diagram of a three-dimensional orthogonal bridge according to an embodiment of this application, which can represent an orthogonal bridge in three-dimensional space with grid point q as the midpoint.

[0041] Optionally, in one embodiment of this application, determining the grid inside the current channel includes: if the grid point corresponding to the midpoint of an orthogonal bridge is located in free space, wherein the grid point corresponding to any pair of bridge endpoints is located inside an obstacle, then it is determined to be a grid point inside the current channel.

[0042] Specifically, if grid q is located in free space, and the grids corresponding to any pair of bridge endpoints of an orthogonal bridge with q as its midpoint are located inside obstacles, then q is considered a grid point within the current channel. For example... Figure 2 As shown, q1q2, q3q4 and q5q6 are the grids corresponding to the bridge endpoints of the orthogonal bridge with q as the midpoint.

[0043] In step S103, the grid points inside the channel are stored in the list, the channel boundary points that meet the preset judgment criteria are extracted, and the channel boundary points are used to construct a connectivity landmark map.

[0044] It is understood that, in the embodiments of this application, based on the list of stored grid points inside the channel obtained by the above steps, channel boundary points that meet the preset judgment criteria can be extracted, and then the starting point and target point of the obtained channel boundary points can be obtained, thereby realizing the construction of the connectivity landmark map.

[0045] It should be noted that the preset judgment criteria can be set by those skilled in the art according to the actual situation, and no specific limitations are made here.

[0046] The embodiments of this application can extract the current channel boundary points and combine the information of the current channel boundary points during the construction of the road map, which can effectively reduce the construction time of the connected road map and improve the construction efficiency of the connected road map.

[0047] Optionally, in one embodiment of this application, the preset judgment criterion is that if any grid point is detected to be inside the current channel and the adjacent grid points are not grid points inside the current channel, then any grid point and the previous grid point inside the current channel in the detection process are considered to be channel boundary points.

[0048] Specifically, if a grid point is detected to be within the current channel, and its neighboring points (four neighboring points in two-dimensional space and six neighboring points in three-dimensional space) are not grid points within the current channel, then this grid point, as well as the previous grid point within the current channel during the detection process, can be considered as a boundary point of the current channel.

[0049] For example Figure 3 The diagram shown is a schematic representation of a two-dimensional narrow passage boundary point according to an embodiment of this application. The gray areas represent obstacles, the arrows indicate the detection direction of the grid bridge method, the gray hollow circles represent detected landmarks within the narrow passage, point p represents the currently detected point, and points p1 to p4 represent its four neighboring points. From the detection direction, it can be seen that point q is the previously detected landmark within the narrow passage. It can also be seen from the detection direction that point p3, a neighbor of p, has been detected and confirmed to be outside the narrow passage. Other neighboring points have not yet undergone grid bridge detection and are therefore considered not to be within the narrow passage. According to the narrow passage boundary point judgment criteria, the currently detected point p and the previously detected landmark q within the narrow passage are considered boundary points of the narrow passage.

[0050] Optionally, in an embodiment of the present application, constructing a connected road map using channel boundary points includes: taking the starting point, the target point, and the channel boundary points as nodes of the connected road map. Among them, if the line segment formed by two nodes is entirely located in the free space, there is an edge between the two nodes, and an initial road map is constructed; based on the initial road map, uniformly sample in the list of internal grid points of the channel and the environmental grid map in sequence. Among them, if the sampling point is located in the free space, the sampling point is taken as a new node, and it is judged whether the line segment formed by the new sampling point and other nodes is entirely located in the free space. If so, there is an edge between the new node and the corresponding node, and a connected road map is generated.

[0051] It can be understood that, in the embodiments of the present application, the starting point, the target point, and the remaining current channel boundary points can be used to construct an initial road map, and then a hybrid sampling method is used to expand the connected road map. Among them, if the starting point and the target point can be connected in the road map, or the number of sampling times exceeds the maximum limit, the construction process of the road map ends.

[0052] In the actual execution process, the starting point, the target point, and the current channel boundary points can be used as the initial nodes of the connected road map and different identification indexes are assigned. If the line segment formed by two nodes is entirely located in the free space, there is an edge between the two nodes, and the identification of these two nodes is adjusted according to the identification index adjustment strategy. Then, uniformly sample in the current channel grid point list NList and the environmental grid map in sequence. If the sampling point is located in the free space, the sampling point is taken as a new node of the road map and a new identification index is assigned. It is judged whether the line segment formed by the new sampling point and other nodes of the road map is entirely located in the free space. If so, there is an edge between the new node and this node, and the identification index corresponding to the node is adjusted according to the identification index adjustment strategy.

[0053] Specifically, the starting point and the target point being able to be connected in the road map can mean that the identification indexes of the starting point and the target point are the same, that is, the starting point and the target point are in the same connected component, and a path connecting the starting point and the target point can be found in the road map through a graph search algorithm. The identification index adjustment can be to assign a new index identification to the node when the new node cannot be connected to other nodes. If the identifications of the nodes connected to the new node are all the same, the identification of the new node is also set to this identification. If the nodes connected to the new node have different identifications, for example Figure 4 As shown, it is assumed that the new node can be connected to the node with the identification of i and the node with the identification of j (i < j) at the same time. Then the index identification of the new node is set to i, that is, the smallest identification among the index identifications of the nodes connected to it. At the same time, for all nodes with the identification of j, their identifications are modified to i.

[0054] In step S104, a search is performed in the connected landmark map to generate a path connecting the starting point and the target point, thus obtaining the final intelligent unmanned system planning path.

[0055] In some embodiments, graph search algorithms, such as Dijkstar's algorithm or A* algorithm, can be used to search the landmark graph constructed in the above steps to generate a path connecting the starting point and the target point, thus obtaining the final intelligent unmanned system path planning result.

[0056] Optionally, in one embodiment of this application, after generating the path connecting the starting point and the target point, the method further includes: smoothing the path.

[0057] Specifically, such as Figure 5 As shown, the path generated in the above steps can first be discretized into a series of path points at certain length intervals, let P o P represents the original path after discretization. o (i) represents P o Let P be the i-th path point. s Indicates the adjusted path, w s This indicates that the latest addition to P s The path points in the code, initially P o (1) as w s Join P s middle.

[0058] Furthermore, from P o (2) Begin by checking P in sequence. o For each path point P o (i) and w s Connectivity (check P) o (i) and w s The line segment w formed s P o (i) Whether the entire line segment w lies in free space. s P o (i) If it is in free space, then preserve line segment w. s P o (i), otherwise, denote line segment w. s P o (i) The first intersection point with the obstacle is O, and point O and point w s If the distance between them is d, then the line segment w s P o (i-1) on w s A point at a distance d is added to P as a new path point. s In the middle, w s Updated to include the latest P s The path points. Next, check the newly added path point w.s With target point P o The connectivity of (n). If line segment w s P o If (n) is in free space, then P o (n) Add to P s If the condition is met, the algorithm ends. Otherwise, repeat the above steps for P. o (i) and w s The connectivity check process continues until P is detected. o Last path point P o (n). Finally, P o (n) Add to P s Afterwards, a new path P connecting the starting point and the target point is obtained. s P s Compared to the original path P o It is smoother.

[0059] For example Figure 6 The diagram shown illustrates a path smoothing adjustment process according to an embodiment of this application. The gray area A represents an obstacle. The broken line a and its corresponding small circle represent the original path P. o The discrete path points, the polyline b, and the corresponding small circle represent the adjusted path P. s And waypoints on the path. Dashed lines represent line segments that collide, and arrows indicate the direction of path adjustment when a collision occurs.

[0060] The embodiments of this application can smoothly adjust the path after generating the path connecting the starting point and the target point, and remove redundant path points on the original path, which can effectively reduce the path length and path corners, thereby making the obtained path planning results more accurate and practical.

[0061] The following detailed description of the working content of the embodiments of this application is based on a specific example, such as... Figure 7 The diagram shown is the overall flowchart of path planning for an intelligent unmanned system based on the grid bridge method in a narrow space.

[0062] Step S701: Select an appropriate grid discretization precision based on the size of the intelligent unmanned system and the maximum width of the narrow passage, and rasterize the working environment to obtain the corresponding grid map. The grid cell corresponding to free space has a value of 0, and the grid cell corresponding to obstacles has a value of 1.

[0063] Step S702: Using an orthogonal bridge of a certain length and with the same direction as the grid map coordinate axis, examine each grid cell one by one to identify the grid points inside the narrow passage.

[0064] Step S703: During the process of detecting grid points inside the narrow channel, extract the boundary points of the narrow channel.

[0065] Step S704: Construct an initial landmark map using the narrow passage boundary points, starting point, and target point, and then uniformly sample and blend the narrow passage grid point set and the environment grid map to expand the connected landmark map.

[0066] Step S705: Use a graph search algorithm to search in the connected landmark graph to generate a path connecting the starting point and the target point.

[0067] Step S706: Smoothly adjust the path generated by the graph search algorithm to obtain the final obstacle avoidance path.

[0068] According to the intelligent unmanned system path planning method based on grid bridge detection proposed in this application, this application embodiment can detect grid points in the current channel based on environmental initialization modeling and extract the boundary points of the current channel to realize the construction of a connected landmark map, and finally generate the intelligent unmanned system path. By quickly identifying landmark points in the current channel, the construction rate of the connected landmark map is improved, thereby enhancing the efficiency and accuracy of intelligent unmanned system path planning. This solves the problems in related technologies, such as the difficulty in obtaining a sufficient number of landmark points in narrow channels, leading to low efficiency of path planning algorithms, significantly reduced convergence speed, inability to guarantee the smooth generation of connected obstacle avoidance paths, difficulty in applying to unstructured scenarios containing narrow channels, and inability to meet the requirements of efficient and accurate intelligent unmanned system path planning, resulting in insufficient accuracy and practicality.

[0069] Next, referring to the accompanying drawings, we describe the intelligent unmanned system path planning device based on the grid bridge detection method proposed in the embodiments of this application.

[0070] Figure 8 This is a schematic diagram of the intelligent unmanned system path planning device based on the grid bridge detection method according to an embodiment of this application.

[0071] like Figure 8 As shown, the intelligent unmanned system path planning device 10 based on grid bridge detection method includes: modeling module 100, inspection module 200, extraction module 300 and planning module 400.

[0072] Among them, the modeling module 100 is used to model the entire environment as a grid map based on the size of the intelligent unmanned system and the maximum width of the current channel.

[0073] The inspection module 200 is used to inspect each grid of the grid map one by one using orthogonal bridges with preset length and direction consistent with the coordinate axis direction of the grid map, determine the grid inside the current channel, and store the grid points inside the channel into a list.

[0074] The extraction module 300 is used to store grid points inside the channel into a list, extract channel boundary points that meet preset judgment criteria, and use the channel boundary points to construct a connectivity landmark map.

[0075] The planning module 400 is used to search in the connected road map, generate a path connecting the starting point and the target point, and obtain the final intelligent unmanned system planning path.

[0076] Optionally, in one embodiment of this application, the verification module 200 includes a judgment unit.

[0077] The judgment unit is used to determine that if the grid point corresponding to the midpoint of the orthogonal bridge is located in free space, and the grid point corresponding to any pair of bridge endpoints is located inside an obstacle, then the grid point is determined to be inside the current channel.

[0078] Optionally, in one embodiment of this application, the preset judgment criterion is that if any grid point is detected to be inside the current channel and the adjacent grid points are not grid points inside the current channel, then any grid point and the previous grid point inside the current channel in the detection process are considered to be channel boundary points.

[0079] Optionally, in one embodiment of this application, the extraction module 300 includes a construction unit and a sampling unit.

[0080] The construction unit is used to take the starting point, the target point and the channel boundary point as nodes of the connected landmark map. If the line segment formed by two nodes is entirely in free space, then there is an edge between the two nodes, thus constructing the initial landmark map.

[0081] The sampling unit is used to uniformly sample grid points stored in the channel and the environment grid map in sequence based on the initial landmark map. If the sampling point is located in free space, the sampling point is taken as a new node, and it is determined whether the line segment formed by the new sampling point and other nodes is entirely located in free space. If so, there is an edge between the new node and the corresponding node, and a connected landmark map is generated.

[0082] Optionally, in one embodiment of this application, the device 10 further includes a smoothing unit.

[0083] The smoothing unit is used to smooth the path after generating the path connecting the starting point and the target point.

[0084] It should be noted that the foregoing explanation of the path planning method embodiment for intelligent unmanned systems based on grid bridge detection also applies to the path planning device for intelligent unmanned systems based on grid bridge detection in this embodiment, and will not be repeated here.

[0085] According to the intelligent unmanned system path planning device based on the grid bridge detection method proposed in this application, this application embodiment can detect grid points of the current channel based on environmental initialization modeling and extract the boundary points of the current channel to realize the construction of a connected landmark map, and finally generate the intelligent unmanned system path. By quickly identifying landmark points in the current channel, the construction rate of the connected landmark map is improved, thereby enhancing the efficiency and accuracy of intelligent unmanned system path planning. This solves the problems in related technologies, such as the difficulty in obtaining a sufficient number of landmark points in narrow channels, resulting in low efficiency of path planning algorithms, a significant decrease in convergence speed, inability to guarantee the smooth generation of connected obstacle avoidance paths, difficulty in applying to unstructured scenarios containing narrow channels, and inability to meet the requirements of efficient and accurate intelligent unmanned system path planning, as well as insufficient accuracy and practicality.

[0086] Figure 9 A schematic diagram of the system provided in an embodiment of this application. The system may include:

[0087] The memory 901, the processor 902, and the computer program stored on the memory 901 and capable of running on the processor 902.

[0088] When the processor 902 executes the program, it implements the intelligent unmanned system path planning method based on grid bridge detection provided in the above embodiments.

[0089] Furthermore, the system also includes:

[0090] Communication interface 903 is used for communication between memory 901 and processor 902.

[0091] The memory 901 is used to store computer programs that can run on the processor 902.

[0092] The memory 901 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0093] If the memory 901, processor 902, and communication interface 903 are implemented independently, then the communication interface 903, memory 901, and processor 902 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation,Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0094] Optionally, in a specific implementation, if the memory 901, processor 902, and communication interface 903 are integrated on a single chip, then the memory 901, processor 902, and communication interface 903 can communicate with each other through an internal interface.

[0095] The processor 902 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0096] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent unmanned system path planning method based on grid bridge detection.

[0097] 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 application. 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.

[0098] 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 application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0099] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application 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 should be understood by those skilled in the art to which embodiments of this application pertain.

[0100] 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 by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0101] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N 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.

[0102] 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.

[0103] Furthermore, the functional units in the various embodiments of this application 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.

[0104] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A path planning method for an intelligent unmanned system based on grid bridge detection, characterized in that, Includes the following steps: Based on the size of the intelligent unmanned system and the maximum width of the current channel, the entire environment is modeled as a grid map; Using orthogonal bridges with a preset length and direction consistent with the coordinate axis direction of the grid map, each grid of the grid map is examined one by one to determine the grid inside the current channel and the grid points inside the channel are stored in a list. The grid points inside the channel are stored in a list, the channel boundary points that meet the preset judgment criteria are extracted, and the channel boundary points are used to construct a connectivity landmark map; as well as A search is performed on the connected landmark map to generate a path connecting the starting point and the target point, thus obtaining the final planned path of the intelligent unmanned system. Determining the grid within the current channel includes: If the grid point corresponding to the midpoint of the orthogonal bridge is located in free space, and any grid point corresponding to any pair of bridge endpoints is located inside an obstacle, then it is determined to be a grid point inside the current channel. The preset judgment criterion is that if any grid point is detected to be inside the current channel and none of the adjacent grid points are grid points inside the current channel, then any grid point and the previous grid point inside the current channel in the detection process are considered to be the channel boundary point. The construction of a connectivity landmark map using the channel boundary points includes: The starting point, the target point, and the channel boundary point are used as nodes of the connected landmark map. If the line segment formed by two nodes is entirely in free space, then there is an edge between the two nodes, thus constructing the initial landmark map. Based on the initial landmark map, uniform sampling is performed sequentially in the list of grid points stored inside the channel and in the grid map. If the sampling point is located in the free space, the sampling point is taken as a new node, and it is determined whether the line segment formed by the new node and other nodes is entirely located in the free space. If so, there is an edge between the new node and the corresponding node, and the connected landmark map is generated.

2. The method according to claim 1, characterized in that, After generating the path connecting the starting point and the target point, the process also includes: The path is then smoothly adjusted.

3. A path planning device for an intelligent unmanned system based on a grid bridge detection method, characterized in that, include: The modeling module is used to model the entire environment as a grid map based on the size of the intelligent unmanned system and the maximum width of the current channel. The inspection module is used to inspect each grid of the grid map one by one using orthogonal bridges with a preset length and direction consistent with the coordinate axis direction of the grid map, determine the grid inside the current channel, and store the grid points inside the channel into a list. The extraction module is used to store grid points inside the channel into a list, extract channel boundary points that meet preset judgment criteria, and use the channel boundary points to construct a connectivity landmark map; as well as The planning module is used to search the connected landmark map, generate a path connecting the starting point and the target point, and obtain the final planned path of the intelligent unmanned system. The inspection module includes: The judgment unit is used to determine that if the grid point corresponding to the midpoint of the orthogonal bridge is located in free space, and the grid points corresponding to any pair of bridge endpoints are located inside the obstacle, then the grid point is determined to be a grid point inside the current channel. The preset judgment criterion is that if any grid point is detected to be inside the current channel and none of the adjacent grid points are grid points inside the current channel, then any grid point and the previous grid point inside the current channel in the detection process are considered to be the channel boundary point. The construction of a connectivity landmark map using the channel boundary points includes: The starting point, the target point, and the channel boundary point are used as nodes of the connected landmark map. If the line segment formed by two nodes is entirely in free space, then there is an edge between the two nodes, thus constructing the initial landmark map. Based on the initial landmark map, uniform sampling is performed sequentially in the list of grid points stored inside the channel and in the grid map. If the sampling point is located in the free space, the sampling point is taken as a new node, and it is determined whether the line segment formed by the new node and other nodes is entirely located in the free space. If so, there is an edge between the new node and the corresponding node, and the connected landmark map is generated.

4. A system, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent unmanned system path planning method based on grid bridge detection as described in any one of claims 1-2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the intelligent unmanned system path planning method based on grid bridge detection as described in any one of claims 1-2.

Images