Unmanned aerial vehicle path planning method for routing inspection data return and related device

Abstract

The invention discloses an unmanned aerial vehicle path planning method for routing inspection data return and a related device. The unmanned aerial vehicle path planning method comprises the following steps: initializing a task scene for returning routing inspection data; constructing a shortest path planning method based on an improved A * algorithm; in the task scene of returning the inspection data, performing unmanned aerial vehicle path planning for a large-data-volume returning task based on the shortest path planning method of the improved A * algorithm; under the task scene of returning inspection data, unmanned aerial vehicle path planning for small data volume returning tasks is carried out based on the shortest path planning method of the improved A * algorithm, and the method and the related device can be used for planning the path of the unmanned aerial vehicle for the small data volume returning tasks based on an intelligent optimization algorithm and a graph search algorithm. And multi-task flight path planning of post-disaster data return and obstacle avoidance flight of the unmanned aerial vehicle is realized.

Description

Technical Field

[0001] The present invention belongs to the field of unmanned aerial vehicle path planning, and relates to a method and related devices for unmanned aerial vehicle path planning for inspection data feedback. Background Art

[0002] In recent years, disasters have occurred frequently in my country, with many types, wide impacts, and serious economic losses. Timely acquisition and analysis of key data in the disaster-stricken areas after disasters are crucial for disaster prevention and mitigation. However, communication services may be limited or ineffective due to physical damage or power outages. Therefore, how to use limited communication resources to transmit inspection data has become a challenge.

[0003] In recent years, drones, as an emerging technology, have been widely used in military, government governance and civilian fields. Due to their flexible operation and strong mobility, they have shown unique advantages over traditional methods in post-disaster rescue. Therefore, a feasible method for post-disaster inspection is to deploy drones to the disaster center, automatically collect key post-disaster data, and transmit the disaster area data back to the rescue center server through a data return area with perfect communication functions. With their high mobility and terrain adaptability, drones can be flexibly deployed and flown according to needs, covering a wide area in a short time, and reducing manpower and material costs.

[0004] In drone inspection, path planning is at the core, which directly determines whether the drone can successfully and efficiently complete the inspection and data transmission tasks. Path planning algorithms can be divided into three categories according to the different ways of algorithm implementation: graph search-based algorithms, sampling-based algorithms, and intelligent bionics-based algorithms. The representative graph search-based path planning algorithms are Dijstra algorithm and A* algorithm. It is necessary to discretize the spatial environment into Voronoi diagram or grid map first, and then search for an optimal path through the search algorithm; the sampling-based path planning algorithm is to randomly mark points in the environmental space, and gradually cover the entire map by connecting scattered points, so as to find the starting point and the end point. The most representative ones are PRM algorithm and RRT algorithm; the path planning algorithm based on intelligent bionics is an emerging intelligent algorithm that imitates the behavior or ecological mechanism of certain biological populations in nature. Genetic algorithm, ant colony algorithm, particle swarm algorithm, Harris Eagle optimization algorithm are all intelligent bionic algorithms.

[0005] The above three types of algorithms all have certain defects. For example, graph search algorithms usually provide discrete paths, which may not be directly used in scenarios that require smooth paths and are not suitable for the motion models of actual vehicles or drones. When the heuristic function of the A* algorithm is inaccurate, A* may explore a large number of irrelevant paths, wasting memory. In sampling-based algorithms, in obstacle-dense or complex spaces, the sampling points are likely to fall into invalid areas, resulting in a significant decrease in algorithm efficiency. Single-objective intelligent optimization algorithms need to be expanded to handle multi-objective optimization problems, but multi-objective optimization usually increases computational complexity and makes it difficult to balance conflicts between objectives. In addition, the performance of these algorithms is sensitive to problem characteristics and is suitable for specific types of problems, but may perform poorly in other problems.

[0006] Existing work has applied various path planning algorithms to conventional UAV inspection flight mission scenarios, but these works can only be applied to UAVs performing simple cruise missions, without considering multi-target constraints such as irregularly distributed points of interest and obstacles in the mission scenarios; in addition, the post-disaster environment with impaired communication conditions is not taken into account, and the return efficiency of inspection data cannot be guaranteed, making the above methods difficult to extend to post-disaster data collection and data return and obstacle avoidance flight multi-target mission applications. Summary of the invention

[0007] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a drone path planning method and related devices for inspection data feedback. The method and related devices can realize multi-task flight path planning of drone post-disaster data feedback and obstacle avoidance flight based on intelligent optimization algorithm and graph search algorithm.

[0008] To achieve the above object, the present invention discloses a UAV path planning method for inspection data return, comprising:

[0009] Initialize the task scenario of returning inspection data;

[0010] Construct the shortest path planning method based on the improved A* algorithm;

[0011] In the task scenario of returning inspection data, based on the shortest path planning method of the improved A* algorithm, the UAV path planning for the task of returning large amounts of data is performed;

[0012] In the task scenario of returning inspection data, based on the shortest path planning method of the improved A* algorithm, UAV path planning for small data volume return tasks is performed.

[0013] The further improvement of the UAV path planning method for inspection data return of the present invention is:

[0014] Furthermore, the process of the task scenario of initializing the return inspection data is as follows:

[0015] 1a) Let the three-dimensional area of ​​the task scene be represented by D, and the set of obstacles in the task scene be Obstacles are simulated with cubes; a data return area is set in the mission scene where the drone can perform data return tasks. The center coordinates of the cth data return area The radius is r c ;

[0016] 1b) The data return area is designed in layers. The data return area is divided into k layers with equal spacing. From the inside to the outside, they are the 1st layer, the 2nd layer, ..., the kth layer. The radius of the mth layer is recorded as Set the transmission rate within each layer to be the same, and the transmission rate between the drone and the data return area to R m ; During the return time, the total amount of data that the drone can return in the data return area is J u (T c );

[0017] 1c) Let the flying speed of the drone be v, and the flying starting point of the drone be S = (x S ,y S ,z S ), the end point of the flight is G = (x G ,y G ,z G );

[0018] 1d) The flight mission is that the drone departs from the starting point S, inspects the mission area D, then flies to the data feedback area c to transmit the inspection data, and flies to the end point G after completing the data feedback.

[0019] Furthermore, in the task scenario of returning inspection data, the process of performing drone path planning for large data volume return tasks based on the shortest path planning method of the improved A* algorithm is as follows:

[0020] 3a) After entering the data transmission area, the drone will fly directly to the center point, hover at the center point to transmit data, and leave the center point and fly to the destination until the remaining data can be transmitted back in the process of passing through the center point;

[0021] 3b) Initialize the starting point S, end point G, task scene D, and data return area set Total amount of data big ;

[0022] 3c) Using the shortest path planning method based on the improved A* algorithm, the shortest flight time from the starting point to the center of the data return area is solved The shortest flight time from the center point of the data return area to the end point

[0023] 3d) Calculate the flight time of the drone passing through each layer in the data return area And the number of returned in, It indicates the flight time of the drone in the data return area under the condition of large data volume;

[0024] 3e) The amount of data transmitted back during the flight The total amount of data J big , calculate the amount of data that the center point needs to return when hovering

[0025] 3f) Output flight path P and total flight time T big .

[0026] Furthermore, Indicates the hovering time at the center point.

[0027] Further, Input into the openlist in the improved A* shortest path algorithm, and get and

[0028] Furthermore, in the task scenario of returning inspection data, the process of performing drone path planning for small data volume return tasks based on the shortest path planning method of the improved A* algorithm is as follows:

[0029] 4a) Assume that the flight path of the drone in the data return area is from the entry point P in , transfer point P transfer and the exit point P out constitute;

[0030] 4b) Initialize the flight environment D, starting point S, end point G and algorithm parameters;

[0031] 4c) Set the algorithm variable to P in and P out , convert it into P in and P out The angles α1 and α2 between the line connecting the center point and the X-axis, r c Indicates the radius of the cth data return area;

[0032] 4d) Assume the fitness function of the particle swarm algorithm, where the fitness function is the total time T for the drone to complete all flight tasks. small , in, It means the drone flies from the starting point S to Pin time, Indicates that the drone is from P out The shortest time to fly to the destination G, Indicates the flight time of the drone within the data return area;

[0033] 4e) Initialize the position and velocity of the particle swarm;

[0034] 4f) Traverse all particles, use the shortest path planning method based on the improved A* algorithm, input [S, P in ], output Input [P out , G], output

[0035] 4g) Input α1, α2, data volume J, data return area radius r m , using the shortest path algorithm within the data return area based on the binary search method to obtain

[0036] 4h) Calculate the fitness value of each particle and save the current single individual optimal solution Pbest and the overall population optimal solution Gbest;

[0037] 4i) Update the position and velocity of each particle;

[0038] 4j) Repeat steps 4f)-4i) until the maximum number of iterations is reached or the quality of the solution reaches a predetermined threshold, and output the optimal path.

[0039] The present invention discloses a UAV path planning system for inspection data return, comprising:

[0040] Initialization module, used to initialize the task scenario of returning inspection data;

[0041] Building module, used to build the shortest path planning method based on the improved A* algorithm;

[0042] The first planning module is used to perform UAV path planning for large data volume backhaul tasks based on the shortest path planning method of the improved A* algorithm in the task scenario of backhauling inspection data;

[0043] The second planning module is used to perform UAV path planning for small data volume backhaul tasks based on the shortest path planning method of the improved A* algorithm in the task scenario of backhauling inspection data.

[0044] The further improvement of the UAV path planning system for inspection data return of the present invention is:

[0045] Furthermore, the process of the task scenario of initializing the return inspection data is as follows:

[0046] 1a) Let the three-dimensional area of ​​the task scene be represented by D, and the set of obstacles in the task scene be Obstacles are simulated with cubes; a data return area is set in the mission scene where the drone can perform data return tasks. The center coordinates of the cth data return area The radius is r c ;

[0047] 1b) The data return area is designed in layers. The data return area is divided into k layers with equal spacing. From the inside to the outside, they are the 1st layer, the 2nd layer, ..., the kth layer. The radius of the mth layer is recorded as Set the transmission rate within each layer to be the same, and the transmission rate between the drone and the data return area to R m ; During the return time, the total amount of data that the drone can return in the data return area is J u (T c );

[0048] 1c) Let the flying speed of the drone be v, and the flying starting point of the drone be S = (x S ,y S ,z S ), the end point of the flight is G = (x G ,y G ,z G );

[0049] 1d) The flight mission is that the drone departs from the starting point S, inspects the mission area D, then flies to the data feedback area c to transmit the inspection data, and flies to the end point G after completing the data feedback.

[0050] The present invention discloses a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the unmanned aerial vehicle path planning method for inspection data return are implemented.

[0051] The present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the unmanned aerial vehicle path planning method for returning inspection data are implemented.

[0052] The present invention has the following beneficial effects:

[0053] The method and related device for the inspection data return of the present invention are designed to design two flight modes under the data volume conditions in view of the complex and changeable data volume in the actual post-disaster rescue. The improved A* algorithm is used to solve the shortest path planning problem of the UAV. The optimal entry point and exit point of the UAV and the data return area are solved iteratively based on the particle swarm algorithm. The internal path of the UAV in the data return area is calculated based on the dichotomy method. Then, the overall path planning of the UAV is performed according to the above solution results, so that the multi-task path planning of the UAV post-disaster data return and obstacle avoidance flight can be realized based on the intelligent optimization algorithm and the graph search algorithm, and the traditional path planning method solves the problem of high complexity in solving the multi-task path planning. Compared with the prior art, not only the obstacle avoidance problem of the UAV in conventional flight is considered, but also the present invention can be applied to complex post-disaster communication damaged scenes. Moreover, since the path planning method oriented to the size of the data volume is adopted in the present invention, unnecessary energy consumption will not be wasted when planning the path, so it is easier to be extended to various complex post-disaster rescue data return scenes with damaged communication. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0055] Figure 1 is a flow chart of the method of the present invention;

[0056] Figure 2 It is a task scenario diagram of the present invention;

[0057] Figure 3 This is a flow chart of the improved A* algorithm in the present invention;

[0058] Figure 4 It is the flow chart of the particle swarm algorithm in the present invention;

[0059] Figure 5 It is a schematic diagram of the internal layers of the data return area in the present invention;

[0060] Figure 6 This is a rendering of the path planning for large amounts of data in the present invention;

[0061] Figure 7 This is a diagram showing the effect of path planning for small data volumes in the present invention. DETAILED DESCRIPTION

[0062] 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 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0064] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0065] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0066] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0067] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0068] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0069] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0070] refer to Figure 1 The UAV path planning method for inspection data return of the present invention comprises the following steps:

[0071] 1) Initialize the task scenario of returning inspection data;

[0072] 2) Shortest path planning method based on improved A* algorithm;

[0073] 3) UAV path planning method for large data volume backhaul missions;

[0074] 4) UAV path planning method for small data backhaul tasks.

[0075] refer to Figure 2 , the specific operation of step 1) is:

[0076] 1a) Let the three-dimensional area of ​​the task scene be represented by D; the set of obstacles in the task scene is Obstacles are simulated with cubes; a data return area is set in the mission scene where the drone can perform data return tasks. The center coordinates of the cth data return area The radius is r c ;

[0077] 1b) The data return area is designed in layers. The data return area is divided into k layers with equal spacing. From the inside to the outside, they are the 1st layer, the 2nd layer, ..., the kth layer. The radius of the mth layer is recorded as Set the transmission rate within each layer to be the same, and the transmission rate between the drone and the data return area to R m ; During the return time, the total amount of data that the drone can return in the data return area is J u (T c );

[0078] 1c) Let the flying speed of the drone be v, and the flying starting point of the drone be S = (x S ,y S ,z S ), the end point of the flight is G = (x G ,y G ,z G );

[0079] 1d) The flight mission is that the drone departs from the starting point S, inspects the mission area D, then flies to the data feedback area c to transmit the inspection data, and flies to the end point G after completing the data feedback.

[0080] refer to Figure 3 , the specific operation of step 2) is:

[0081] 2a) Initialize the map space D, the starting point S, and the target point G, and create empty openList and closeList;

[0082] 2b) Put the take-off point S into openList and search for the position adjacent to S. When an obstacle grid is encountered, the obstacle grid is put into closeList. When a free grid is encountered, the free grid is put into openList and waits for search. At the same time, the current node is used as the parent node of the adjacent grid for the next search;

[0083] 2c) Delete S from openList and put it into closeList; the evaluation function is:

[0084]

[0085] Among them, dist n,g Indicates the distance from the current point to the target point, dist s,g Indicates the distance from the starting point to the target point;

[0086] 2d) Search the adjacent grid. If the adjacent grid is a grid in the closeList or an obstacle grid, no search is performed. If the adjacent grid is a feasible grid and is not in the openList, add the adjacent grid to the openList, calculate the evaluation function value, and set the current node as the parent node.

[0087] 2e) Compare the f value of the current parent node with that of the previous parent node. When the f value of the current parent node is greater than the f value of the previous parent node, the f value of the previous parent node will be used to replace the f value of the current parent node.

[0088] 2f) After searching and judging all grids, the stored parent nodes are connected to obtain the flight path;

[0089] 2g) The flight path is smoothed based on a Bezier curve. After smoothing, each segment of the UAV flight path is a smooth curve, avoiding the problem of too many turning points in the traditional A* algorithm. The Bezier curve formula is: is the control point, is the number of control points of the Bezier curve, is a parameter with a value range from 0 to 1. is the Bessel basis function, and its specific expression is the Bernstein polynomial in the approximation theorem. The specific value can be obtained by the following recursive formula:

[0090]

[0091]

[0092] in, is the Bessel basis function of order 0, and its value is a piecewise function, that is, when The value is 1 when it is in the closed-open interval from i to i+1, and 0 in the rest of the range. is the basis function obtained by the previous recursion.

[0093] refer to Figure 5 , the specific operation of step 3) is:

[0094] 3a) After entering the data transmission area, the drone will fly directly to the center point, hover at the center point to transmit data, and leave the center point and fly to the destination until the remaining data can be transmitted back in the process of passing through the center point;

[0095] 3b) Initialize the starting point S, the end point G, the task scenario D, the data return area set C, and the total amount of data J big ;

[0096] 3c) Use the shortest path planning method based on the improved A* algorithm in step 2) to solve the shortest flight time from the starting point to the center of the data return area The shortest flight time from the center point of the data return area to the end point

[0097] 3d) Calculate the flight time of the drone passing through each layer in the data return area And the number of returned in, It indicates the flight time of the drone in the data return area under the condition of large data volume;

[0098] 3e) The amount of data transmitted back during the flight The total amount of data J big , calculate the amount of data that the center point needs to return when hovering Indicates the hovering time at the center point;

[0099] 3f) Output flight path P and total flight time T big , Among them, solving and The specific method is: Input into the openlist of the improved A* shortest path algorithm for calculation. The specific generated UAV flight path is as follows Figure 6 shown.

[0100] refer to Figure 4 , the specific steps of step 4) are:

[0101] 4a) Assume that the flight path of the drone in the data return area is from the entry point P in , transfer point P transfer and the exit point P out Composition, among which, P in is the intersection point between the drone and the boundary when it enters or exits the data return area, P transfer Indicates the midpoint P of the line connecting the entry point and the exit point middle A point on the line connecting the center point;

[0102] 4b) Initialize the flight environment D, the starting point S, the end point G and the algorithm parameters, such as the population size N, the inertia weight W and the learning factors c1 and c2;

[0103] 4c) Set the algorithm variable to P in With P out , here, in order to facilitate subsequent calculations, it is converted into P in With P out The angles between the line connecting the center point and the X-axis are α1, α2, rc represents the radius of the cth data return area, and different angles correspond to different coordinates; P in With P oit The relationship with the center point is:

[0104]

[0105] 4d) Set the fitness function of the particle swarm algorithm, which is the total time T for the drone to complete all flight tasks. small , in, Indicates that the drone flies from the starting point S to P in time, Indicates that the drone is from P out The shortest time to fly to the destination G, represents the flight time of the drone within the data return area; solve and The specific method is: Put into Figure 3 The openlist in the A* algorithm shown is calculated.

[0106] 4e) Initialize the position and velocity of the particle swarm;

[0107] 4f) Traverse all particles and use the shortest path planning method based on the improved A* algorithm described in step 2) to input [S, P in ], output Input [P out , G], output

[0108] 4g) Input α1, α2, data volume J, data return area radius r m , using the shortest path algorithm within the data return area based on the binary search method to obtain

[0109] 4h) Calculate the fitness value of each particle and save the current single individual optimal solution Pbest and the overall population optimal solution Gbest;

[0110] 4i) Update the position and speed of each particle. For each particle, if the current position is better than the best position encountered before, update its individual optimal solution Pbest. At the same time, find the position with the best fitness from all particles and update it to the global optimal solution Gbest.

[0111] 4j) Repeat steps 4f)-4i) until the maximum number of iterations is reached or the quality of the solution reaches a predetermined threshold, and output the optimal path. The specific generated flight path is as follows: Figure 7 shown.

[0112] like Figure 5 For details of the data return area, refer to Figure 5 The specific steps of the shortest path algorithm within the data return area based on the dichotomy method in step 4g) are:

[0113] 4g1) Initialize the total amount of data J small , angle α1, α2, radius of data return area r m , tolerance value tol, maximum number of iterations max_iterations, set the left boundary Right border in

[0114] 4g2) Call the data volume calculation method based on the angle value to calculate The corresponding data volume and flight time when Already greater than or equal to J small , return directly and t1 as the solution;

[0115] 4g3) Call the data volume calculation method based on the angle value to calculate The corresponding data volume and flight time

[0116] 4g4) Calculate the difference between the boundary value and the required data volume: Check the existence of the solution: When μ min ·μ max >0, it means the target value is not within the search interval and an error is reported;

[0117] 4g5) Initialize iteration counter n = 0, enter the loop, and execute the following steps for each iteration:

[0118] 4g6) Calculate the midpoint value of the angle: Let Call the data volume calculation algorithm to get The amount of data in the direction and flight time Calculate the difference between midpoints

[0119] 4g7) Check the termination condition: the absolute value of the midpoint function value The output angle value and flight time When the current interval length Output and

[0120] 4g8) Based on the midpoint difference Difference μ from the left boundary min The symbol relationship adjusts the search interval: when and μ min have the same sign, then let Otherwise, update the right border:

[0121] 4g9) At each iteration, the counter is incremented by 1. When the maximum number of iterations max_iterations is reached and no solution is found, "Iterations exceed limit" is returned.

[0122] 4g10) Returns the direction angle that meets the conditions And the corresponding flight time

[0123] The specific steps of the method for calculating the amount of data based on the angle value in step 4g2) are:

[0124] 4g2-1) Initialize P in and P out The corresponding angles α1, α2, the UAV path and P in and P out Angle of connecting line

[0125] 4g2-2) Make the following calculations:

[0126] P in To P middle The distance d in,m = r4·sinθ;

[0127] P transfer To P middle The distance d t,m = r4·sinθ·tanθ;

[0128] To P middle The distance d c,m = r4·cosθ;

[0129] To P transfer The length d c,t =r4·cosθ-r4·sinθ·tanθ;

[0130] 4g2-3) Angle between the flight path and the center line

[0131] 4g2-4) According to the trigonometric formula: c 2 =a 2 +b 2 -2ab·cos c, then:

[0132] Assuming that the data area is divided into 4 layers, the relationship between the data area radius and the flight path d4 is:

[0133] r4 2 =d4 2 +d 4,ct 2 -2d4·d 4,ct ·cosβ;

[0134] r4 2 =(d4-d 4,ct ·cosβ) 2 +d 4,ct 2 ·(1-(cosβ) 2 )

[0135] =(d4-d 4,ct ·cosβ) 2 +d 4,ct 2 +(sinβ) 2

[0136] get: Only valid when d4>0;

[0137] Similarly, for

[0138] 4g2-5) The flight distance of the drone on the fourth layer is: d4-d3, and the flight time is:

[0139] 4g2-6)

[0140] 4g2-7) Flight time within the area The amount of data that can be returned during this process is:

[0141]

[0142] 4g2-8) Output the amount of data under this angle flight path.

[0143] Embodiment 2

[0144] The UAV path planning system for inspection data return of the present invention comprises:

[0145] Initialization module, used to initialize the task scenario of returning inspection data;

[0146] Building module, used to build the shortest path planning method based on the improved A* algorithm;

[0147] The first planning module is used to perform UAV path planning for large data volume backhaul tasks based on the shortest path planning method of the improved A* algorithm in the task scenario of backhauling inspection data;

[0148] The second planning module is used to perform UAV path planning for small data volume backhaul tasks based on the shortest path planning method of the improved A* algorithm in the task scenario of backhauling inspection data.

[0149] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0150] Embodiment 3

[0151] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for unmanned aerial vehicle path planning for inspection data return are implemented, for example, including: initializing the task scenario for returning inspection data; constructing the shortest path planning method based on the improved A* algorithm; in the task scenario for returning inspection data, based on the shortest path planning method of the improved A* algorithm, performing unmanned aerial vehicle path planning for large data volume return tasks; in the task scenario for returning inspection data, based on the shortest path planning method of the improved A* algorithm, performing unmanned aerial vehicle path planning for small data volume return tasks. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, the network interface, and the memory are interconnected through an internal bus, and the internal bus may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include memory and nonvolatile memory and provides instructions and data to the processor.

[0152] Embodiment 4

[0153] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the drone path planning method for inspection data return are implemented, for example, including: initializing the task scenario of returning inspection data; constructing the shortest path planning method based on the improved A* algorithm; in the task scenario of returning inspection data, based on the shortest path planning method of the improved A* algorithm, performing drone path planning for large data volume return tasks; in the task scenario of returning inspection data, based on the shortest path planning method of the improved A* algorithm, performing drone path planning for small data volume return tasks. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, disk, etc.

[0154] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0155] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 processor, 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.

[0156] 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 1 A function specified in one or more boxes.

[0157] 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 The steps for the functions specified in one or more boxes.

[0158] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and disclosure of the invention. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0159] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0160] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A UAV path planning method for inspection data return, characterized in that: include: Initialize the task scenario of returning inspection data; Construct the shortest path planning method based on the improved A* algorithm; In the task scenario of returning inspection data, based on the shortest path planning method of the improved A* algorithm, the UAV path planning for the task of returning large amounts of data is performed; In the task scenario of returning inspection data, based on the shortest path planning method of the improved A* algorithm, UAV path planning for small data volume return tasks is performed.

2. The method for UAV path planning for inspection data return according to claim 1 is characterized in that: The process of the task scenario of initializing the return inspection data is as follows: 1a) Let the three-dimensional area of ​​the task scene be represented by D, and the set of obstacles in the task scene be Obstacles are simulated with cubes; a data return area is set in the mission scene where the drone can perform data return tasks. The center coordinates of the cth data return area The radius is r c ; 1b) The data return area is designed in layers. The data return area is divided into k layers with equal spacing. From the inside to the outside, they are the 1st layer, the 2nd layer, ..., the kth layer. The radius of the mth layer is recorded as Set the transmission rate within each layer to be the same, and the transmission rate between the drone and the data return area to R m ; During the return time, the total amount of data that the drone can return in the data return area is J u (T c ); 1c) Let the flying speed of the drone be v, and the flying starting point of the drone be S = (x S ,y S ,z S ), the end point of the flight is G = (x G ,y G ,z G ); 1d) The flight mission is that the drone departs from the starting point S, inspects the mission area D, then flies to the data feedback area c to transmit the inspection data, and flies to the end point G after completing the data feedback.

3. The method for UAV path planning for inspection data return according to claim 1 is characterized in that: In the task scenario of returning inspection data, the process of performing drone path planning for large data volume return tasks based on the shortest path planning method of the improved A* algorithm is as follows: 3a) After entering the data transmission area, the drone will fly directly to the center point, hover at the center point to transmit data, and leave the center point and fly to the destination until the remaining data can be transmitted back in the process of passing through the center point; 3b) Initialize the starting point S, end point G, task scene D, and data return area set Total amount of data big ; 3c) Using the shortest path planning method based on the improved A* algorithm, the shortest flight time from the starting point to the center of the data return area is solved The shortest flight time from the center point of the data return area to the end point 3d) Calculate the flight time of the drone passing through each layer in the data return area And the number of returned in, It indicates the flight time of the drone in the data return area under the condition of large data volume; 3e) The amount of data transmitted back during the flight The total amount of data J big , calculate the amount of data that the center point needs to return when hovering 3f) Output flight path P and total flight time T big .

4. The method for UAV path planning for inspection data return according to claim 3 is characterized in that: Indicates the hovering time at the center point.

5. The method for UAV path planning for inspection data return according to claim 3 is characterized in that: Will Input into the openlist in the improved A* shortest path algorithm, and get and 6. The method for UAV path planning for inspection data return according to claim 1 is characterized in that: In the task scenario of returning inspection data, the process of performing drone path planning for small data volume return tasks based on the shortest path planning method of the improved A* algorithm is as follows: 4a) Assume that the flight path of the drone in the data return area is from the entry point P in , transfer point P transfer and the exit point P out constitute; 4b) Initialize the flight environment D, starting point S, end point G and algorithm parameters; 4c) Set the algorithm variable to P in and P out , convert it into P in and P out The angles α1 and α2 between the line connecting the center point and the X-axis, r c Indicates the radius of the cth data return area; 4d) Assume the fitness function of the particle swarm algorithm, where the fitness function is the total time T for the drone to complete all flight tasks. small , in, It means the drone flies from the starting point S to P in time, Indicates that the drone is from P out The shortest time to fly to the destination G, Indicates the flight time of the drone within the data return area; 4e) Initialize the position and velocity of the particle swarm; 4f) Traverse all particles, use the shortest path planning method based on the improved A* algorithm, input [S, P in ], output Input [P out , G], output 4g) Input α1, α2, data volume J, data return area radius r m , using the shortest path algorithm within the data return area based on the binary search method to obtain 4h) Calculate the fitness value of each particle and save the current single individual optimal solution Pbest and the overall population optimal solution Gbest; 4i) Update the position and velocity of each particle; 4j) Repeat steps 4f)-4i) until the maximum number of iterations is reached or the quality of the solution reaches a predetermined threshold, and output the optimal path.

7. A drone path planning system for inspection data return, characterized in that: include: Initialization module, used to initialize the task scenario of returning inspection data; Building module, used to build the shortest path planning method based on the improved A* algorithm; The first planning module is used to perform UAV path planning for large data volume backhaul tasks based on the shortest path planning method of the improved A* algorithm in the task scenario of backhauling inspection data; The second planning module is used to perform UAV path planning for small data volume backhaul tasks based on the shortest path planning method of the improved A* algorithm in the task scenario of backhauling inspection data.

8. The UAV path planning system for inspection data return according to claim 7 is characterized in that: The process of the task scenario of initializing the return inspection data is as follows: 1a) Let the three-dimensional area of ​​the task scene be represented by D, and the set of obstacles in the task scene be Obstacles are simulated with cubes; a data return area is set in the mission scene where the drone can perform data return tasks. The center coordinates of the cth data return area The radius is r c ; 1b) The data return area is designed in layers. The data return area is divided into k layers with equal spacing. From the inside to the outside, they are the 1st layer, the 2nd layer, ..., the kth layer. The radius of the mth layer is recorded as Set the transmission rate within each layer to be the same, and the transmission rate between the drone and the data return area to R m ; During the return time, the total amount of data that the drone can return in the data return area is J u (T c ); 1c) Let the flying speed of the drone be v, and the flying starting point of the drone be S = (x S ,y S ,z S ), the end point of the flight is G = (x G ,y G ,z G ); 1d) The flight mission is that the drone departs from the starting point S, inspects the mission area D, then flies to the data feedback area c to transmit the inspection data, and flies to the end point G after completing the data feedback.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the drone path planning method for inspection data feedback as described in any one of claims 1-6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the drone path planning method for inspection data feedback as described in any one of claims 1 to 6 are implemented.

Images