Low-altitude unmanned aerial vehicle flight path planning method and system

Abstract

The invention relates to a low-altitude unmanned aerial vehicle flight path planning method and system, and relates to the field of unmanned aerial vehicle navigation and control, and the method comprises the steps: carrying out the primary planning of a flight path according to the information of a plurality of obstacles, and obtaining a primary planning path domain; according to the obstacle information and the bird feature information, bird flight path density analysis between obstacles is carried out, and bird flight path density distribution is obtained; and performing secondary path planning optimization in the primary planning path domain according to bird flight path density distribution to obtain an optimal planning path. According to the invention, the technical problem that the existing method cannot effectively solve the problems of obstacle avoidance and bird interference in the flight process of the low-altitude unmanned aerial vehicle, resulting in insufficient flight safety and poor flight efficiency of the unmanned aerial vehicle can be solved; the flight path with the shortest distance can be selected on the premise of effectively avoiding obstacles and high-bird-density areas, so that the safety and the flight efficiency of the unmanned aerial vehicle during low-altitude flight are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle navigation and control, and in particular to a low-altitude unmanned aerial vehicle flight path planning method and system. Background Art

[0002] With the rapid development of drone applications, low-altitude drones are gradually being widely used in logistics, environmental monitoring, urban inspections, etc. However, during low-altitude flight, drones often face complex and changing flight environments, including various ground obstacles (such as buildings, trees, etc.) and dynamic obstacles (such as birds, etc.), which poses a great challenge to the flight safety and efficiency of drones.

[0003] At present, traditional UAV flight path planning methods mainly focus on avoiding static obstacles. Most of them are based on preset paths or simple obstacle avoidance algorithms, and lack comprehensive consideration of dynamic environments. These methods are usually unable to respond to bird interference during flight in real time, and are unable to accurately calculate safe distances in areas with dense obstacles, resulting in UAVs frequently encountering the risk of collision with obstacles during flight. At the same time, due to the lack of full consideration of the comprehensive factors of dynamic interference and path optimization, existing methods make it impossible for UAVs to choose the optimal path in complex environments, resulting in tortuous and lengthy paths, affecting flight efficiency and endurance. Summary of the invention

[0004] The present invention aims to solve the technical problem that existing flight path planning methods cannot effectively solve the obstacle avoidance and bird interference problems during the flight of low-altitude UAVs, resulting in insufficient UAV flight safety and poor flight efficiency. A low-altitude UAV flight path planning method and system are provided to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a low-altitude UAV flight path planning method, comprising: obtaining information of multiple obstacles in a target flight area, and collecting characteristic information of birds in the target flight area, wherein obstacles include buildings and trees, and the target flight area is the area to be flown through; based on the multiple obstacle information, performing a primary flight path planning of the low-altitude UAV to obtain a primary planned path domain; based on the obstacle information and bird characteristic information, performing a density analysis of bird flight trajectories between obstacles to obtain a bird flight trajectory density distribution; based on the bird flight trajectory density distribution, performing a secondary low-altitude UAV flight path planning optimization within the primary planned path domain to obtain an optimal planned path.

[0006] In a second aspect, the present invention provides a low-altitude UAV flight path planning system, comprising: an area information acquisition module, used to obtain information of multiple obstacles within a target flight area, and collect bird characteristic information within the target flight area, wherein obstacles include buildings and trees, and the target flight area is the area to be flown through; a flight path primary planning module, used to perform a primary planning of the low-altitude UAV flight path according to the multiple obstacle information, and obtain a primary planning path domain; a bird flight trajectory density analysis module, used to perform a bird flight trajectory density analysis between obstacles according to the obstacle information and bird characteristic information, and obtain a bird flight trajectory density distribution; a flight path planning optimization module, used to perform a secondary low-altitude UAV flight path planning optimization within the primary planning path domain according to the bird flight trajectory density distribution, and obtain an optimal planning path.

[0007] In a third aspect, the present invention further provides an electronic device, comprising: At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can perform the steps of the method in the first aspect above.

[0008] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the steps of the method in the first aspect are implemented.

[0009] The beneficial effects of the present invention are as follows: by obtaining information of multiple obstacles in a target flight area, and collecting characteristic information of birds in the target flight area; then, a low-altitude UAV flight path is planned once according to the information of multiple obstacles to obtain a primary planned path domain; then, based on the obstacle information and the characteristic information of birds, a density analysis of the bird flight trajectories between obstacles is performed to obtain the density distribution of the bird flight trajectories; finally, based on the density distribution of the bird flight trajectories, a secondary low-altitude UAV flight path planning optimization is performed within the primary planned path domain to obtain the optimal planned path; that is, by comprehensively considering obstacles, bird interference and flight distance to optimize the flight path, the shortest distance flight path can be selected while effectively avoiding obstacles and areas with high bird density, thereby significantly improving the safety and flight efficiency of the UAV during low-altitude flight. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a flow chart of a low-altitude UAV flight path planning method provided by the present invention; Figure 2 A schematic diagram of the structure of a low-altitude UAV flight path planning system provided by the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention; Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0011] In the accompanying drawings, the components represented by the reference numerals are described as follows: Area information acquisition module 01, flight path primary planning module 02, bird flight trajectory density analysis module 03, flight path planning optimization module 04, electronic device 500, memory 510, processor 520, first computer program 511, computer readable storage medium 600, second computer program 611. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0015] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a low-altitude UAV flight path planning method, which specifically includes the following steps: A100: Obtain information of multiple obstacles in a target flight area, and collect characteristic information of birds in the target flight area, wherein obstacles include buildings and trees, and the target flight area is an area to be flown through.

[0016] In one embodiment, step A100 of the present application further includes: A110: Scan and obtain obstacle position information, obstacle model information and obstacle category information of multiple obstacles in the target flight area, wherein the obstacle category information includes buildings and trees; A120: Integrate multiple obstacle position information, multiple obstacle model information and multiple obstacle category information to obtain multiple obstacle information in the target flight area; A130: Collect the average number of birds in the target flight area as bird characteristic information.

[0017] Specifically, first, determine the target flight area of ​​the UAV, which is the area to be flown, that is, the range of the flight path that the UAV is scheduled to pass through. For example, determine the departure position and destination position of the UAV according to the requirements of the mission, and set the area where all potential path selection ranges are located based on the departure position and destination position as the target flight area.

[0018] Next, in the target flight area, detailed information of each obstacle is collected by scanning or sensing technology to obtain obstacle location information, obstacle model information and obstacle category information of multiple obstacles, where obstacle location information refers to the geographical coordinates of each obstacle in order to determine its specific location in the flight area; obstacle model information refers to the three-dimensional model or parameters of obstacles obtained by scanning technology, such as the height, width and structure of buildings, the shape and height of trees, etc.; obstacle category information includes buildings and trees, where buildings include all man-made structures in the target flight area, such as residential buildings, office buildings, industrial buildings, etc., and trees are all natural vegetation structures in the indicator area, such as trees, etc. Then, multiple obstacles and multiple obstacle location information, multiple obstacle model information and multiple obstacle category information are integrated, that is, the location information (coordinates), model information (shape, height, size and other parameters) and category information (building or tree) of each obstacle are merged to form a complete information entry for each obstacle, such as, for each building, the entry contains its specific location, height, width, shape parameters, and multiple obstacle information in the target flight area is obtained. By determining multiple obstacle information, intuitive obstacle distribution data can be provided for flight path planning, ensuring that the drone can effectively sense and avoid obstacles, thereby improving the flight safety of the drone.

[0019] On the other hand, bird activity data is collected in the target flight area, and the average number of birds that appeared in the past predetermined time period is counted as bird characteristic information, such as the number of birds per day in the past 10 days, and the average is calculated. By obtaining multiple obstacle information and bird characteristic information in the target flight area, detailed data support can be provided for the path planning of the UAV, so that it can choose the best path while avoiding obstacles and bird activity areas, thereby improving the safety and efficiency of flight.

[0020] A200: Based on the information of the multiple obstacles, a low-altitude UAV flight path is planned once to obtain a planned path domain.

[0021] In one embodiment, step A200 of the present application further includes: A210: Obtaining a flight hazard distance threshold; A220: Using the flight hazard distance threshold, compensating and adjusting the obstacle model information in the multiple obstacle information, and obtaining multiple flight obstacle domains; A230: Deleting the multiple flight obstacle domains in the target flight area, completing a low-altitude UAV flight path planning, and obtaining a planned path domain.

[0022] Specifically, first, a flight danger distance threshold is set. The flight danger distance threshold represents the minimum safe distance between the UAV and an obstacle. When the UAV approaches an obstacle and reaches this distance, a danger warning will be generated. The distance can be set according to the type of UAV and the actual flight status. For example, the flight danger distance threshold is set to 1 meter, which means that when the UAV approaches an obstacle within 1 meter, a danger warning will be generated.

[0023] Next, the obstacle model information in the multiple obstacle information is compensated and adjusted using the flight danger distance threshold, that is, a buffer area of ​​the danger distance is added outside the actual boundary of the obstacle according to the position and model parameters (such as shape, size, etc.) of each obstacle. For example, for each obstacle (such as buildings, trees, etc.), a 1-meter buffer distance is added on the basis of its original model boundary as a safety buffer zone to ensure that the UAV does not enter the danger zone during path planning; and multiple flight obstacle domains are obtained.

[0024] Then, the multiple flight obstacle domains are deleted in the target flight area, and the low-altitude UAV flight path is planned once, that is, the area except the multiple flight obstacle domains in the target flight area is set as the safe path area where the UAV can fly, that is, the once-planned path domain, wherein the once-planned path domain includes a safe flight area that avoids obstacles and their buffer areas, ensuring that the UAV stays away from any dangerous areas that may cause collisions during flight. The once-planned path domain is obtained by performing a once-planned flight path, which lays the foundation for subsequent path optimization and dynamic adjustment, so that the UAV can effectively avoid obstacles and improve the safety of low-altitude flight.

[0025] A300: According to the obstacle information and the bird characteristic information, a density analysis of the bird flight tracks between obstacles is performed to obtain a density distribution of the bird flight tracks.

[0026] In one embodiment, step A300 of the present application further includes: A310: Traverse and combine the multiple obstacle information one by one to obtain multiple obstacle information combinations, and generate multiple bird flight trajectories according to the obstacle position information combinations in the multiple obstacle information combinations.

[0027] Specifically, first, all obstacles in the target area are traversed and combined one by one to generate all possible obstacle information combinations, where each obstacle information combination represents a potential flight path between two obstacles, and birds may fly or stay between two obstacles along these paths. Then, based on the location information (such as geographic coordinates) of each set of obstacle pairs, a bird flight trajectory is generated between the two obstacles, and multiple bird flight trajectories corresponding to multiple obstacle information combinations are obtained. By determining multiple bird flight trajectories, the potential activity areas of birds between obstacles can be effectively captured, providing data support for subsequent path planning, thereby improving the safety and effectiveness of flight path planning for low-altitude UAVs.

[0028] A320: Perform flight trajectory density analysis on the multiple bird flight trajectories based on the multiple obstacle information combinations and the bird characteristic information to obtain multiple bird flight trajectory densities, and construct a bird flight trajectory density distribution in combination with the trajectory position information of the multiple bird flight trajectories.

[0029] In one embodiment, step A320 of the present application further includes: A321: Based on the bird flight monitoring data of the same flight area, a sample obstacle information combination set and a sample bird characteristic information set are collected, and the number of bird flight tracks within a preset time under different sample obstacle information combinations and sample bird characteristic information is collected to obtain a sample bird flight track density set; A322: The sample obstacle information combination set and the sample bird characteristic information set are used as input supervised training data, and the sample bird flight track density set is used as output supervised training data to train a bird flight track density predictor; A323: The multiple obstacle information combinations are respectively input into the bird flight track density predictor with the bird characteristic information, and the prediction output obtains multiple bird flight track densities.

[0030] Specifically, based on the bird flight monitoring data in the same flight area, a sample obstacle information combination set and a sample bird characteristic information set are collected. For example, representative sample obstacle combinations are collected from similar environments or similar flight areas, including information such as the distance, model, and category of obstacles. These sample combinations cover the spatial characteristics and distribution between different obstacle pairs, forming a representative obstacle combination set, which is convenient for analyzing the flight behavior of birds between various combinations, and obtaining a sample obstacle information combination set; bird characteristic information in the same flight area is collected, including parameters such as the number of birds, species, and activity frequency, to obtain a sample bird characteristic information set. Next, the number of bird flight trajectories within a preset time under different sample obstacle information combinations and sample bird characteristic information is collected, that is, under different sample obstacle combinations and bird characteristic conditions, the number of bird flight trajectories between each obstacle pair within a preset time (for example, 1 hour) is obtained, and the number of bird flight trajectories is set as the sample bird flight trajectory density to obtain a sample bird flight trajectory density set, wherein the more the number of bird flight trajectories, the greater the bird trajectory density, and the higher the risk to the drone.

[0031] Then, a bird flight trajectory density predictor was constructed based on the BP neural network. The bird flight trajectory density predictor is a BP neural network model that can be iteratively optimized in machine learning, including an input layer, multiple hidden layers and an output layer. The input data of the input layer is a combination of obstacle information (obstacle distance, model, category, etc.) and bird feature information (number of birds, activity frequency, etc.). The hidden layer is used to transmit and process complex nonlinear relationships between neurons to enhance the model's ability to learn the relationship between input features and flight trajectory density. The output data of the output layer is the bird flight trajectory density.

[0032] The sample obstacle information combination set and the sample bird feature information set are further used as input supervised training data, and the sample bird flight track density set is used as output supervised training data to supervise the bird flight track density predictor. First, the sample input data set is passed into the network, and the output of each layer is calculated until the bird flight track density predicted by the model is obtained; then the error between the predicted value and the true output label is calculated at the output layer. The error is usually measured by the mean square error or cross entropy loss function; then the error gradient is used for back propagation, and the weights and biases are updated layer by layer. This process calculates the gradient through the chain rule, so that the model continuously adjusts the parameters to minimize the prediction error; finally, the iterative process of forward propagation and back propagation is repeated, and the error is gradually reduced through optimization algorithms such as gradient descent until the error converges or reaches the set number of training times, and a trained bird flight track density predictor is obtained.

[0033] Then, each set of obstacle information combination in the target flight area (including the distance between obstacles, model parameters, categories, etc.) and bird characteristic information (such as the number of birds, activity frequency, etc.) are integrated into input data to obtain multiple input data, and the multiple input data are respectively input into the bird flight trajectory density predictor for prediction, and multiple bird flight trajectory densities are output. By obtaining multiple bird flight trajectory densities, high-risk paths with dense bird populations in the flight area can be identified, and the drone can be helped to plan a safe, low-interference optimal flight path, thereby significantly improving the safety and efficiency of the drone's low-altitude flight.

[0034] Finally, the density distribution of bird flight tracks is constructed based on the density of multiple bird flight tracks and the track position information of multiple bird flight tracks. That is, the density value of each track is mapped to its corresponding position coordinates, and the density values ​​of all tracks are integrated on the same distribution map to show the density of bird activities in different areas. In the distribution map, the density value of each track can be marked by color depth or other visualization methods. For example, the higher the density, the darker the color, and the low-density path is marked with a light color. By constructing the density distribution of bird flight tracks, a key reference basis is provided for drone path planning, enabling drones to avoid high-density bird activity areas, reduce interference and collision risks, and ensure the safety and efficiency of flight missions.

[0035] A400: According to the density distribution of the bird flight paths, a secondary low-altitude UAV flight path planning optimization is performed within the primary planned path domain to obtain an optimal planned path.

[0036] In one embodiment, step A400 of the present application further includes: A410: Randomly generate a first planned path within the primary planned path domain.

[0037] Specifically, according to the starting and ending positions set for the UAV to fly in the target flight area, a group of path points are randomly generated in the once planned path domain, and these points are connected one by one to form a continuous path, namely the first planned path.

[0038] A420: According to the bird flight track density distribution, obtain the bird flight track density of the bird flight track passed by the first planned path, and calculate and obtain the first path fitness of the first planned path.

[0039] In one embodiment, step A420 of the present application further includes: A421: According to the bird flight track density distribution, obtain the density of multiple bird flight tracks of the first planned path; A422: Obtain the first path distance of the first planned path; A423: According to the first path distance and the density of multiple bird flight tracks, calculate and obtain the first path fitness, as shown in the following formula: ; Among them, PFIT is the path fitness, and is the weight, is the path distance, is the minimum path distance of the target flight area, M is the number of multiple bird flight trajectories, is the flight trajectory density of the i-th passing bird, is the average bird flight track density of the bird flight track density distribution.

[0040] Specifically, the first planned path is compared with the bird flight track density distribution, and the bird flight tracks that intersect with the bird flight track density distribution map on the first planned path are extracted as multiple passing bird flight tracks, that is, multiple bird flight tracks passing on the first planned path. For each intersecting passing bird flight track, the corresponding bird flight track density value in the bird flight track density distribution map is extracted as the multiple passing bird flight track density of the multiple passing bird flight tracks passing on the first planned path. The greater the density of the multiple passing bird flight tracks, the greater the danger of the drone during the flight of the first planned path.

[0041] On the other hand, a first path distance of the first planned path, that is, the length of the first planned path is obtained.

[0042] Construct path fitness calculation function: ; In the path fitness calculation function, PFIT is the path fitness, wherein the larger the path fitness, the better the path, and the path fitness is negatively correlated with the path distance and the density of bird flight trajectories, that is, the smaller the path distance, the smaller the density of bird flight trajectories, and the greater the path fitness; is the path distance weight, is the flight safety weight, where the path distance weight is used to measure the importance of the path distance in the fitness calculation. The larger the path distance weight is, the more the path fitness is inclined to the shortest path to improve flight efficiency; the flight safety weight is used to measure the impact of bird interference density on fitness. The larger the flight safety weight is, the more the path fitness will focus on avoiding areas with dense bird activities to improve flight safety; the path distance weight and flight safety weight can be set by technicians in this field according to the actual flight requirements of the UAV, for example, 0.4 and 0.6 respectively; is the path distance, is the minimum path distance of the target flight area, that is, the minimum flight distance between the starting point and the end point, such as the straight-line distance. M is the number of multiple bird flight trajectories passing through, is the flight trajectory density of the i-th passing bird, is the average bird flight track density of the bird flight track density distribution, which can be obtained by calculating the mean.

[0043] Then, based on the path fitness calculation function, the first path fitness of the first planned path is calculated according to the first path distance and the density of multiple bird flight trajectories. By constructing the path fitness calculation function, the quality of the planned path can be accurately and quantitatively evaluated, thereby providing a basis for optimizing flight path planning.

[0044] A430: Continue to perform secondary low-altitude UAV flight path planning optimization in the primary planning path domain until the optimization converges and outputs the optimal planning path with the maximum path fitness.

[0045] Specifically, a second planned path is then randomly selected within the domain of the first planned path, and the first path fitness of the second planned path is calculated; using the same method, the secondary low-altitude UAV flight path planning iterative optimization is continued within the domain of the first planned path until a predetermined number of optimization searches is met. The predetermined number of optimization searches can be set according to the optimization accuracy requirements. For example, the predetermined number of optimization searches can be set to 500 times, and then the optimization converges. At this time, multiple path fitnesses of multiple planned paths are obtained, and the planned path with the largest path fitness is selected as the optimal planned path.

[0046] The present invention provides a method for low-altitude UAV flight path planning, which has at least the following technical effects: By obtaining information on multiple obstacles in the target flight area and collecting characteristic information on birds in the target flight area; then planning the low-altitude UAV flight path once according to the information on multiple obstacles to obtain a planned path domain; then, based on the obstacle information and bird characteristic information, the density of bird flight trajectories between obstacles is analyzed to obtain the density distribution of bird flight trajectories; finally, based on the density distribution of bird flight trajectories, a secondary low-altitude UAV flight path planning optimization is performed within the planned path domain to obtain the optimal planned path; that is, by comprehensively considering obstacles, bird interference and flight distance to optimize the flight path, the shortest distance flight path can be selected while effectively avoiding obstacles and high bird density areas, thereby significantly improving the safety and flight efficiency of the UAV during low-altitude flight.

[0047] Embodiment 2, as Figure 2 As shown, based on the same inventive concept as the low-altitude UAV flight path planning method provided in Embodiment 1, the embodiment of the present invention further provides a low-altitude UAV flight path planning system, including: The area information acquisition module 01 is used to obtain information on multiple obstacles in the target flight area and collect bird characteristic information in the target flight area, wherein obstacles include buildings and trees, and the target flight area is the area to be flown through; the flight path primary planning module 02 is used to perform primary planning of the low-altitude UAV flight path according to the multiple obstacle information and obtain a primary planning path domain; the bird flight trajectory density analysis module 03 is used to perform bird flight trajectory density analysis between obstacles according to the obstacle information and bird characteristic information and obtain bird flight trajectory density distribution; the flight path planning optimization module 04 is used to perform secondary low-altitude UAV flight path planning optimization in the primary planning path domain according to the bird flight trajectory density distribution and obtain the optimal planning path.

[0048] In one embodiment, the low-altitude UAV flight path planning system further includes: Scan and obtain obstacle position information, obstacle model information and obstacle category information of multiple obstacles in a target flight area, wherein the obstacle category information includes buildings and trees; integrate multiple obstacle position information, multiple obstacle model information and multiple obstacle category information to obtain multiple obstacle information in the target flight area; collect the average number of birds in the target flight area as bird characteristic information.

[0049] In one embodiment, the low-altitude UAV flight path planning system further includes: Acquire a flight hazard distance threshold; use the flight hazard distance threshold to compensate and adjust the obstacle model information in the multiple obstacle information to obtain multiple flight obstacle domains; delete the multiple flight obstacle domains in the target flight area, complete a low-altitude UAV flight path planning, and obtain a planned path domain.

[0050] In one embodiment, the low-altitude UAV flight path planning system further includes: The multiple obstacle information are traversed and combined one by one to obtain multiple obstacle information combinations, and multiple bird flight tracks are generated according to the obstacle position information combinations within the multiple obstacle information combinations; flight track density analysis of the multiple bird flight tracks is performed according to the multiple obstacle information combinations and the bird characteristic information to obtain multiple bird flight track densities, and a bird flight track density distribution is constructed in combination with the track position information of the multiple bird flight tracks.

[0051] In one embodiment, the low-altitude UAV flight path planning system further includes: According to the bird flight monitoring data of the same flight area, a sample obstacle information combination set and a sample bird characteristic information set are collected, and the number of bird flight tracks within a preset time under different sample obstacle information combinations and sample bird characteristic information is collected to obtain a sample bird flight track density set; the sample obstacle information combination set and the sample bird characteristic information set are used as input supervised training data, and the sample bird flight track density set is used as output supervised training data to train a bird flight track density predictor; the multiple obstacle information combinations and the bird characteristic information are respectively input into the bird flight track density predictor, and the prediction output obtains multiple bird flight track densities.

[0052] In one embodiment, the low-altitude UAV flight path planning system further includes: A first planned path is randomly generated within the primary planned path domain; according to the bird flight trajectory density distribution, the bird flight trajectory density of the bird flight trajectory passed by the first planned path is obtained, and the first path fitness of the first planned path is calculated; and secondary low-altitude UAV flight path planning optimization is continued within the primary planned path domain until the optimization converges, and an optimal planned path with the maximum path fitness is output.

[0053] In one embodiment, the low-altitude UAV flight path planning system further includes: According to the bird flight track density distribution, multiple bird flight track densities of multiple bird flight tracks passed by the first planned path are obtained; a first path distance of the first planned path is obtained; and a first path fitness is calculated according to the first path distance and multiple bird flight track densities, as shown in the following formula: ; Among them, PFIT is the path fitness, and is the weight, is the path distance, is the minimum path distance of the target flight area, M is the number of multiple bird flight trajectories, is the flight trajectory density of the i-th passing bird, is the average bird flight track density of the bird flight track density distribution.

[0054] For example 3, please refer to Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: obtaining information of multiple obstacles in a target flight area, and collecting characteristic information of birds in the target flight area, wherein obstacles include buildings and trees, and the target flight area is an area to be flown through; based on the information of multiple obstacles, performing a primary planning of the flight path of a low-altitude UAV to obtain a primary planning path domain; based on the obstacle information and the characteristic information of birds, performing a density analysis of the flight trajectories of birds between obstacles to obtain a density distribution of the flight trajectories of birds; based on the density distribution of the flight trajectories of birds, performing a secondary low-altitude UAV flight path planning optimization in the primary planning path domain to obtain an optimal planning path.

[0055] Example 4, please refer to Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by the processor, the following steps are implemented: obtaining multiple obstacle information in a target flight area, and collecting bird characteristic information in the target flight area, wherein obstacles include buildings and trees, and the target flight area is an area to be flown through; based on the multiple obstacle information, a low-altitude UAV flight path is planned once to obtain a primary planned path domain; based on the obstacle information and bird characteristic information, a bird flight trajectory density analysis is performed between obstacles to obtain a bird flight trajectory density distribution; based on the bird flight trajectory density distribution, a secondary low-altitude UAV flight path planning optimization is performed within the primary planned path domain to obtain an optimal planned path.

[0056] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0057] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0061] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0062] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A low-altitude UAV flight path planning method, characterized in that: Methods include: Obtaining information of multiple obstacles in a target flight area, and collecting characteristic information of birds in the target flight area, wherein obstacles include buildings and trees, and the target flight area is an area to be flown through; According to the plurality of obstacle information, a low-altitude UAV flight path is planned once to obtain a planned path domain; According to the obstacle information and the bird characteristic information, a density analysis of the bird flight tracks between obstacles is performed to obtain a density distribution of the bird flight tracks; According to the density distribution of the bird flight paths, a secondary low-altitude UAV flight path planning optimization is performed within the primary planning path domain to obtain the optimal planning path.

2. A low-altitude UAV flight path planning method according to claim 1, characterized in that: Obtaining information about multiple obstacles in a target flight area and collecting characteristic information about birds in the target flight area, including: Scan and obtain obstacle position information, obstacle model information, and obstacle category information of multiple obstacles in the target flight area, wherein the obstacle category information includes buildings and trees; Integrate multiple obstacle position information, multiple obstacle model information and multiple obstacle category information to obtain multiple obstacle information in the target flight area; The average number of birds in the target flight area is collected as bird characteristic information.

3. A low-altitude UAV flight path planning method according to claim 1, characterized in that: According to the plurality of obstacle information, a low-altitude UAV flight path is planned once to obtain a planned path domain, including: Get the flight danger distance threshold; Using the flight hazard distance threshold, compensating and adjusting obstacle model information in the plurality of obstacle information to obtain a plurality of flight obstacle regions; The multiple flight obstacle domains are deleted in the target flight area, a low-altitude UAV flight path planning is completed, and a planned path domain is obtained.

4. A low-altitude UAV flight path planning method according to claim 1, characterized in that: According to the obstacle information and the bird characteristic information, the bird flight track density analysis between obstacles is performed to obtain the bird flight track density distribution, including: The plurality of obstacle information are traversed and combined one by one to obtain a plurality of obstacle information combinations, and a plurality of bird flight trajectories are generated according to the obstacle position information combinations in the plurality of obstacle information combinations; According to the combination of the multiple obstacle information and the bird characteristic information, a flight trajectory density analysis of the multiple bird flight trajectories is performed to obtain multiple bird flight trajectory densities, and the bird flight trajectory density distribution is constructed in combination with the trajectory position information of the multiple bird flight trajectories.

5. A low-altitude UAV flight path planning method according to claim 4, characterized in that: According to the plurality of obstacle information combinations and the bird characteristic information, performing flight track density analysis of the plurality of bird flight tracks to obtain a plurality of bird flight track densities includes: According to the bird flight monitoring data of the same flight area, a sample obstacle information combination set and a sample bird characteristic information set are collected, and the number of bird flight trajectories within a preset time under different sample obstacle information combinations and sample bird characteristic information is collected to obtain a sample bird flight trajectory density set; The sample obstacle information combination set and the sample bird feature information set are used as input supervised training data, and the sample bird flight track density set is used as output supervised training data to train a bird flight track density predictor; The plurality of obstacle information combinations and the bird feature information are respectively input into the bird flight track density predictor, and a plurality of bird flight track densities are obtained by prediction output.

6. A low-altitude UAV flight path planning method according to claim 1, characterized in that: According to the density distribution of the bird flight tracks, a secondary low-altitude UAV flight path planning optimization is performed within the primary planning path domain to obtain an optimal planning path, including: Randomly generating a first planned path within the primary planned path domain; According to the bird flight track density distribution, the bird flight track density of the bird flight track passed by the first planned path is obtained, and the first path fitness of the first planned path is obtained by calculation; Continue to perform secondary low-altitude UAV flight path planning optimization in the primary planning path domain until the optimization converges and outputs the optimal planning path with the maximum path fitness.

7. A low-altitude UAV flight path planning method according to claim 6, characterized in that: According to the bird flight track density distribution, obtaining the bird flight track density of the bird flight track passed by the first planned path, and calculating and obtaining the first path fitness of the first planned path, including: According to the bird flight track density distribution, obtaining a plurality of bird flight track densities of a plurality of bird flight tracks passed by the first planned path; Acquire a first path distance of the first planned path; According to the first path distance and the density of multiple flight paths of passing birds, the first path fitness is calculated as follows: ； Among them, PFIT is the path fitness, and is the weight, is the path distance, is the minimum path distance of the target flight area, M is the number of multiple bird flight trajectories, is the flight trajectory density of the i-th passing bird, is the average bird flight track density of the bird flight track density distribution.

8. A low-altitude UAV flight path planning system, characterized in that: The steps for implementing a low-altitude UAV flight path planning method as described in any one of claims 1 to 7 include: An area information acquisition module is used to acquire information of multiple obstacles in a target flight area and collect characteristic information of birds in the target flight area, wherein obstacles include buildings and trees, and the target flight area is an area to be flown through; A flight path primary planning module is used to perform a primary planning of the low-altitude UAV flight path according to the plurality of obstacle information to obtain a primary planning path domain; A bird flight track density analysis module is used to perform bird flight track density analysis between obstacles based on the obstacle information and bird feature information to obtain bird flight track density distribution; The flight path planning and optimization module is used to perform secondary low-altitude UAV flight path planning and optimization within the primary planning path domain according to the density distribution of the bird flight trajectory to obtain the optimal planning path.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the steps of a low-altitude UAV flight path planning method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the steps of a low-altitude UAV flight path planning method as described in any one of claims 1 to 7.

Images