Improved D*lite path planning method and system based on spatial obstacle degree
Through the improved D*lite path planning method based on obstacles, through expansion processing and obstacle map optimization, the problem of insufficient safety and sensitivity of traditional D*Lite algorithms in complex environments is solved, and the rapid and safe return of the drone is achieved.
Patent Information
- Application Number
- CN202510672746.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-23
- Publication Date
- 2025-09-02
AI Technical Summary
When traditional D*Lite algorithms plan paths in complex three-dimensional environments, the sparsity of obstacle point clouds and map construction errors lead to insufficient distance between the path and obstacles, which poses a potential collision risk, and the drone may pass through the inside of the telephone pole tower, and the obstacle sensitivity is insufficient.
By obtaining a three-dimensional point cloud raster map, performing expansion processing, counting the number of times the raster is covered, forming an obstacle map, and bringing the obstacle to the movement cost of the D*lite algorithm, optimizing path planning to reduce curvature and improve security.
It has achieved smooth and safe improvement in the return path of the drone, reduced the average curvature, and ensured that the drone returns quickly and safely in complex environments.
Smart Images
Figure CN120576755A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) navigation technology, and in particular to an improved D*lite path planning method and system based on spatial obstacle degree. Background Art
[0002] Currently, drone path planning is a very important function in drone return technology and has received widespread attention.
[0003] However, for the traditional D*Lite algorithm, when planning a drone's path in a complex 3D environment, the sparsity of the obstacle point cloud and mapping errors can result in insufficient clearance between the planned path and the obstacle surface, posing a potential collision safety hazard. Furthermore, the D*Lite algorithm treats drones as point masses during path planning. In power tower inspection scenarios, drones can potentially pass through the interior of a power tower, resulting in a lack of obstacle sensitivity compared to traditional power inspection methods. Summary of the Invention
[0004] Purpose of the invention: In view of the shortcomings of the existing technology, the present invention provides an improved D*lite path planning method based on spatial obstacle degree in order to solve the problem that traditional power inspection methods are not sensitive enough to obstacles. It also proposes a UAV path planning system that can implement this method to reduce the average curvature of the UAV's return path and achieve rapid and safe return of the UAV.
[0005] The present invention proposes an improved D*lite path planning method based on spatial obstruction, comprising the following steps:
[0006] Step 1: Obtain a 3D point cloud of the target space to form a 3D point cloud grid map;
[0007] Step 2: dilate each grid in the three-dimensional point cloud grid map to obtain an expanded grid network map;
[0008] Step 3: Count the number of times each grid is covered by the expansion area;
[0009] Step 4: Use the number of times each grid is covered by the expansion area in step 3 to obtain the neighborhood obstacle degree of the grid;
[0010] Step 5: Using the neighborhood obstacle degree of the grid to form an obstacle map;
[0011] Step 6: Extract the spatial obstacle degree from the obstacle map and bring it into the movement cost of the D*lite algorithm to obtain an improved D*lite algorithm;
[0012] Step 7: Based on the expanded grid network map described in step 2, the improved D*lite algorithm is used to plan the return path of the UAV.
[0013] In a further embodiment, the number of times the grid is covered by the dilated area is counted using the following formula to obtain the neighborhood obstacle degree D(x, y, z) of the grid:
[0014] D(x,y,z)=D old (x,y,z)+1
[0015] Where D old (x,y,z) is the neighborhood obstruction of the original grid.
[0016] In a further embodiment, the step 5 of forming an obstacle map using the neighborhood obstacle degree of the grid specifically includes:
[0017] The neighborhood obstruction degree D(x, y, z) of the grid is normalized using the following formula to obtain the spatial obstruction degree of the grid:
[0018]
[0019] Where D(x,y,z) is the neighborhood obstacle degree of the grid; D max is the maximum neighborhood obstacle degree; D norm (x, y, z) is the spatial obstruction of the grid;
[0020] According to the spatial obstruction D of the obtained grid norm (x, y, z) form an obstacle map.
[0021] In a further embodiment, the maximum neighborhood obstacle degree D max Calculated according to the following formula:
[0022]
[0023] In a further embodiment, in step 6, the spatial obstruction is substituted into the movement cost of the D*lite algorithm according to the following formula to obtain an improved D*lite algorithm:
[0024] C(x,y,z)=C base +α·D norm (x,y,z)
[0025] Where C base is the basic moving cost; α is the obstacle influence coefficient; C(x,y,z) is the cost value corresponding to the grid.
[0026] In a further embodiment, step seven specifically includes: planning the return path of the UAV using the improved D*lite algorithm on the expanded grid network map.
[0027] In addition, the present invention also discloses a drone path planning system, which automatically executes the improved D*lite path planning method based on spatial obstruction disclosed in the above embodiment. The path planning system includes:
[0028] The acquisition module is used to obtain the three-dimensional point cloud of the target space and form a three-dimensional point cloud grid map;
[0029] A first operation module is configured to expand each grid in the three-dimensional point cloud grid map to obtain an expanded grid network map;
[0030] The first calculation module is used to count the number of times each grid is covered by the expansion area;
[0031] The second calculation module obtains the neighborhood obstacle degree of the grid by using the number of times each grid is covered by the expansion area; and forms an obstacle degree map using the neighborhood obstacle degree of the grid;
[0032] A third calculation module is used to extract the spatial obstacle degree from the obstacle degree map and bring it into the movement cost of the D*lite algorithm to obtain an improved D*lite algorithm;
[0033] The execution module plans the return path of the UAV using the improved D*lite algorithm based on the expanded grid network map.
[0034] In addition, the present invention also discloses an electronic device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the improved D*lite path planning method based on spatial obstacle degree is implemented.
[0035] In addition, the present invention also discloses a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is run on an electronic device, the electronic device executes the above-mentioned improved D*lite path planning method based on spatial obstacle degree.
[0036] Beneficial effects: The present invention mainly performs expansion processing on each grid in the obtained three-dimensional point cloud grid map; then, the number of times each grid is covered by the expanded area is counted and quantified to obtain the neighborhood obstacle degree of the grid; then, the neighborhood obstacle degree of the grid is used to form an obstacle map; then, the spatial obstacle degree is brought into the movement cost of the D*lite algorithm to obtain the improved D*lite algorithm; finally, the improved D*lite algorithm is used to perform path planning on the expanded grid network map, and finally the return path planning of the UAV is realized. The present invention effectively solves the problem of insufficient sensitivity to obstacles and uneven return path of traditional power inspection methods during the return process of the UAV. It realizes the rapid and safe return of the UAV. The method of the present invention can be used for the path planning of the return of the UAV based on the three-dimensional point cloud grid map, and has broad application value. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 Flowchart of the improved D*lite path planning method based on spatial obstacle degree in the embodiment.
[0038] Figure 2 It is the point cloud grid map in the embodiment.
[0039] Figure 3 This is the expanded point cloud grid map in the embodiment.
[0040] Figure 4 is the obstacle map in the embodiment.
[0041] Figure 5 Schematic diagram of the path planning result in the embodiment. DETAILED DESCRIPTION
[0042] In the following description, numerous specific details are provided to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without one or more of these details. In other instances, certain technical features well known in the art have not been described to avoid confusion with the present invention.
[0043] The embodiment of the present invention adopts a D*lite algorithm based on neighborhood obstacle degree. The core concept is to optimize the D*lite algorithm by updating the cost value parameters by introducing an obstacle degree constraint mechanism. This method first sets a safety radius based on the UAV's wingspan and hovering margin, and uses the Euclidean distance transform to generate an expansion layer for the point cloud data to obtain the corresponding map neighborhood obstacle degree. Secondly, the obstacle degree map is obtained by normalizing the expanded map, forcing path planning to stay away from high-risk areas. Finally, the neighborhood obstacle degree constraint is integrated into the original D*lite algorithm to generate an executable homing path that conforms to flight dynamics. While ensuring planning efficiency, this method significantly improves the minimum separation distance between the path and obstacles, reduces the average curvature of the planned path, and meets the safe homing requirements of UAVs in complex environments.
[0044] In one embodiment, the present invention proposes an improved D*lite path planning algorithm based on spatial obstacle degree, see Figures 1 to 5 , the method comprising:
[0045] Step 1: Obtain a three-dimensional point cloud map to form a three-dimensional point cloud raster map;
[0046] Step 2: dilate each grid on the 3D point cloud grid map;
[0047] Step 3: After all points in the point cloud grid map are expanded, the same grid may be overlapped by the expansion areas of multiple points. The number of times each grid is covered by the expansion area is counted;
[0048] Step 4 is as follows:
[0049] After obtaining the statistical data, the data is quantitatively calculated to obtain the neighborhood obstruction degree of the grid. The number of times the grid is covered by the expansion area is counted using the following formula to obtain the neighborhood obstruction degree of the grid.
[0050] D(x,y,z)=D old (x,y,z)+1
[0051] Where D old (x,y,z) is the original neighborhood barrier, D(x,y,z) is the current neighborhood barrier
[0052] Step 5: Obtain the neighborhood obstacle degree of each grid, normalize the neighborhood obstacle degree, and display it on the map to form an obstacle map. Use the following formula to normalize the neighborhood obstacle degree of the grid to obtain the grid obstacle degree.
[0053]
[0054] in,
[0055] Where D norm (x,y,z) is the grid obstacle, D(x,y,z) is the neighborhood obstacle, D max is the maximum neighborhood obstacle degree,
[0056] An obstacle map is generated based on the obtained obstacle levels.
[0057] Step 6: Incorporate the obstruction degree into the D*lite algorithm and bring the spatial obstruction degree into the movement cost of the D*lite algorithm to obtain the improved D*lite algorithm. Use the following formula to calculate the movement cost of the improved D*lite algorithm:
[0058] C(x,y,z)=C base +α·D norm (x,y,z)
[0059] Where C base is the basic moving cost, α is the obstacle influence coefficient, and C(x, y, z) is the cost value corresponding to the grid.
[0060] Step 7: Use the improved D*lite algorithm to perform path planning on the expanded grid network map, and finally realize the return path planning of the UAV.
[0061] The technical process of the improved D*lite path planning method based on spatial obstruction disclosed in the above embodiment can be implemented on a UAV path planning system. The path planning system comprises six parts: an acquisition module, a first operation module, a first calculation module, a second calculation module, a third calculation module, and an execution module. The acquisition module is used to acquire a three-dimensional point cloud of the target space and form a three-dimensional point cloud grid map. The first operation module is used to dilate each grid in the three-dimensional point cloud grid map to obtain an expanded grid network map. The first calculation module is used to count the number of times each grid is covered by the dilated area. The second calculation module uses the number of times each grid is covered by the dilated area to obtain the grid's neighborhood obstruction degree; this obstruction degree map is then formed using the grid's neighborhood obstruction degree. The third calculation module is used to extract the spatial obstruction degree from the obstacle map and apply it to the D*lite algorithm to generate an improved D*lite algorithm. The execution module uses the improved D*lite algorithm based on the expanded grid network map to plan the return path for the UAV.
[0062] The technical process of the improved D*lite path planning method based on spatial obstacle degree disclosed in the above embodiment can be implemented in whole or in part through software, hardware, firmware or any other combination.
[0063] When implemented in hardware, the aforementioned embodiments can be run on an electronic device by compiling all or part of the operating logic and computational processes into software. The electronic device includes a processor, memory, a communication interface, and a communication bus. The processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to execute the technical process of the improved D*lite path planning method based on spatial obstruction levels disclosed in the aforementioned embodiments.
[0064] When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. If the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be embodied in the form of a software product in essence or in other words, the part that contributes to the relevant technology. The software product is stored in a storage medium and includes several instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific hardware, software or firmware, or any combination of hardware, software and firmware.
[0065] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the present invention itself. Various changes may be made to it in form and detail without departing from the spirit and scope of the present invention as defined in the appended claims.
Claims
1. An improved D*lite path planning method based on spatial obstacle degree, characterized in that: The steps include: Step 1: Obtain a 3D point cloud of the target space to form a 3D point cloud grid map; Step 2: dilate each grid in the three-dimensional point cloud grid map to obtain an expanded grid network map; Step 3: Count the number of times each grid is covered by the expansion area; Step 4: Use the number of times each grid is covered by the expansion area in step 3 to obtain the neighborhood obstacle degree of the grid; Step 5: Using the neighborhood obstacle degree of the grid to form an obstacle map; Step 6: Extract the spatial obstacle degree from the obstacle degree map and bring it into the movement cost of the D*lite algorithm to obtain an improved D*lite algorithm; Step 7: Based on the expanded grid network map described in step 2, the improved D*lite algorithm is used to plan the return path of the UAV.
2. The improved D*lite path planning method based on spatial obstacle degree according to claim 1, characterized in that: The number of times the grid is covered by the expansion area is counted using the following formula to obtain the grid's neighborhood obstacle degree D(x, y, z): D(x,y,z)=D old (x,y,z)+1 Where D old (x,y,z) is the neighborhood obstruction of the original grid.
3. The improved D*lite path planning method based on spatial obstruction according to claim 2, characterized in that: In step 5, the neighborhood obstacle degree of the grid is used to form an obstacle map, which specifically includes: The neighborhood obstruction degree D(x, y, z) of the grid is normalized using the following formula to obtain the spatial obstruction degree of the grid: Where D(x,y,z) is the neighborhood obstacle degree of the grid; D max is the maximum neighborhood obstacle degree; D norm (x, y, z) is the spatial obstruction of the grid; According to the spatial obstruction D of the obtained grid norm (x, y, z) form an obstacle map.
4. The improved D*lite path planning method based on spatial obstacle degree according to claim 3, characterized in that: The maximum neighborhood obstacle degree D max Calculated according to the following formula: Where, Represents any raster in a raster network.
5. The improved D*lite path planning method based on spatial obstacle degree according to claim 3, characterized in that: In step 6, the spatial obstruction is substituted into the movement cost of the D*lite algorithm according to the following formula to obtain the improved D*lite algorithm: C(x,y,z)=C base +α·D norm (x,y,z) Where C base is the basic moving cost; α is the obstacle influence coefficient; C(x,y,z) is the cost value corresponding to the grid.
6. The improved D*lite path planning method based on spatial obstacle degree according to claim 5, characterized in that: Step seven specifically includes: On the expanded grid network map, the improved D*lite algorithm is used to plan the return path of the UAV.
7. A UAV path planning system for automatically executing the improved D*lite path planning method based on spatial obstacle degree according to any one of claims 1 to 6, characterized in that: include: The acquisition module is used to obtain the three-dimensional point cloud of the target space and form a three-dimensional point cloud grid map; A first operation module is configured to expand each grid in the three-dimensional point cloud grid map to obtain an expanded grid network map; The first calculation module is used to count the number of times each grid is covered by the expansion area; The second calculation module obtains the neighborhood obstacle degree of the grid by using the number of times each grid is covered by the expansion area; and forms an obstacle degree map using the neighborhood obstacle degree of the grid; A third calculation module is used to extract the spatial obstacle degree from the obstacle degree map and bring it into the movement cost of the D*lite algorithm to obtain an improved D*lite algorithm; The execution module plans the return path of the UAV using the improved D*lite algorithm based on the expanded grid network map.
8. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the improved D*lite path planning method based on spatial obstacle degree according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that The storage medium stores at least one executable instruction, and when the executable instruction is executed on the electronic device, the electronic device executes the improved D*lite path planning method based on spatial obstacle degree according to any one of claims 1 to 6.