A multi-unmanned aerial vehicle cluster path planning method based on a lightweight A-star algorithm

Abstract

The application discloses a kind of multi-unmanned aerial vehicle cluster path planning methods based on lightweight A star algorithm, belong to unmanned aerial vehicle cluster path planning technical field, it includes: by the scanning work of task environment of reconnaissance group unmanned aerial vehicle, constructs three-dimensional grid map;Flight path is initially planned using lightweight A star algorithm and flight distance matrix is calculated;In the case where all target points have task group unmanned aerial vehicle to reach, with the minimum total path of unmanned aerial vehicle cluster flight as the goal, search out the best flight path planning scheme;For the best flight path planning scheme, the flight path of each task group unmanned aerial vehicle therein is optimized using improved particle swarm algorithm;Optimized flight path is assigned to corresponding task group unmanned aerial vehicle, and it is controlled to complete subsequent task.The application has fast running speed, good performance, can realize multi-unmanned aerial vehicle cluster path planning in real environment, and has strong stability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of multi-unmanned aerial vehicle cluster path planning, in particular to a multi-unmanned aerial vehicle cluster path planning method based on a lightweight A-star algorithm. BACKGROUND

[0002] Multi-unmanned aerial vehicle clusters are widely used in various fields, such as city aerial photography, post-disaster emergency, forest fire monitoring and prevention, etc. Due to the high mobility of unmanned aerial vehicles and the synergy of multi-unmanned aerial vehicles, multi-unmanned aerial vehicle clusters can often complete tasks efficiently and quickly in special situations, and can avoid large risks to protect human safety. The realization of the overall planning of multi-unmanned aerial vehicles is the premise of the efficient work of the unmanned aerial vehicle cluster, and reasonable path planning and task allocation can often enhance the efficiency and execution of the unmanned aerial vehicle cluster.

[0003] In recent years, with the popular application of front-line technologies such as artificial intelligence and autonomous systems and the rapid development of unmanned aerial vehicle systems, unmanned aerial vehicle cluster systems have become a major trend. Their remarkable execution, low cost and little influence on terrain constraints make them play an increasingly prominent role in special situations.

[0004] The existing multi-unmanned aerial vehicle cluster path planning method has a high dependence on the environment, and a single obstacle model cannot meet the demand of path planning in real situations. A specific obstacle model needs to be established according to the actual situation to enable the multi-unmanned aerial vehicle cluster to accurately avoid obstacles. The existing multi-unmanned aerial vehicle cluster path planning method has the defects of falling into local optimum and prematureness, and cannot effectively solve actual problems with multiple constraint conditions. The extreme value solved is not the minimum value point. SUMMARY

[0005] The present application provides a multi-unmanned aerial vehicle cluster path planning method based on a lightweight A-star algorithm to solve the technical problem that the existing multi-unmanned aerial vehicle cluster path planning method falls into local optimum and prematureness, cannot effectively solve actual problems with multiple constraint conditions, and the extreme value solved is not the minimum value point.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] On the one hand, the present application provides a multi-unmanned aerial vehicle cluster path planning method based on a lightweight A-star algorithm, wherein the unmanned aerial vehicles in the unmanned aerial vehicle cluster are divided into reconnaissance group unmanned aerial vehicles and task group unmanned aerial vehicles, and the multi-unmanned aerial vehicle cluster path planning method based on a lightweight A-star algorithm comprises:

[0008] The reconnaissance group unmanned aerial vehicles in the unmanned aerial vehicle cluster perform scanning work on the task environment, obtain obstacle model information and position information, mark target point information, and construct a three-dimensional grid map.

[0009] Based on the constructed three-dimensional grid map, the flight path of each task group UAV is preliminarily planned by using a lightweight A-star algorithm, taking the current position information of each task group UAV in the UAV cluster as the starting point and each target point as the end point, and a flight distance matrix is calculated; each row of the flight distance matrix represents a task group UAV, and each column of the flight distance matrix represents a target point;

[0010] Based on the flight distance matrix, the total flight path of the UAV cluster corresponding to different flight path planning schemes is calculated respectively, and the best flight path planning scheme is searched under the condition that all target points are reached by task group UAVs, taking the minimum total flight path of the UAV cluster as the target;

[0011] For the best flight path planning scheme, the flight path of each task group UAV is optimized by using an improved particle swarm algorithm to seek the minimum value of the flight path distance and optimize the flight path smoothness;

[0012] The optimized flight path is assigned to the corresponding task group UAV, which is controlled to fly over the corresponding target point and complete the subsequent task.

[0013] Further, in the process of preliminarily planning the flight path of each task group UAV by using the lightweight A-star algorithm, only the points one unit length away in the six directions of above, below, left, right, front and back of the current node are considered when the lightweight A-star algorithm searches for feasible points in the neighborhood.

[0014] Further, the lightweight A-star algorithm calculates the distance from the current node to the neighbor node using Euclidean distance.

[0015] Further, the lightweight A-star algorithm calculates the distance from the neighbor node to the end point using Manhattan distance.

[0016] Further, the optimization of the flight path of each task group UAV in the best flight path planning scheme using the improved particle swarm algorithm includes:

[0017] The improved particle swarm algorithm initializes the particle swarm position according to the flight path of each task group UAV in the best flight path planning scheme, and gives it an initialization speed;

[0018] The fitness value of each particle is calculated according to the fitness formula;

[0019] The individual extreme value and global extreme value of the particle are updated according to the fitness value;

[0020] The position and speed of the particle are updated according to the improved particle position and speed update formula;

[0021] Calculate the fitness of the particle in the new position and update the individual extreme value and global extreme value of the particle;

[0022] Determine whether the end condition is met, if yes, the algorithm ends, if not, continue to update the particle position and velocity, and search for the minimum value of the flight path distance cyclically until the end condition is met.

[0023] Further, the improved particle position and velocity updating formula refers to improving the inertia weight in the particle position and velocity updating formula in the particle swarm algorithm, so that the inertia weight is dynamically adjusted adaptively.

[0024] Further, the inertia weight in the particle position and velocity updating formula in the particle swarm algorithm is improved to realize adaptive dynamic adjustment, which comprises:

[0025] The logarithmic function is used to control the change of the inertia weight, and a random adjustment number subject to Gaussian distribution is added to realize the dynamic adjustment of the inertia weight in the evolution process.

[0026] Further, the expression of the inertia weight ω d is as follows:

[0027]

[0028] Wherein, t is the current iteration number; T is the maximum iteration number; alpha is the inertia adjustment factor; randn is a random number subject to Gaussian distribution; ω min represents the minimum value of the inertia weight without Gaussian distribution random number disturbance, and is used to limit the lower bound of the inertia weight change; ω max represents the maximum value of the inertia weight without Gaussian distribution random number disturbance, and is used to limit the upper bound of the inertia weight change.

[0029] In another aspect, the present application also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to realize the above method.

[0030] In another aspect, the present application also provides a computer readable storage medium, which stores at least one instruction, which is loaded and executed by the processor to realize the above method.

[0031] The technical scheme provided by the present application has at least the following beneficial effects:

[0032] Firstly, the present application can quickly and efficiently complete the multi-unmanned aerial vehicle cluster cooperative flight task, has strong stability, the unmanned aerial vehicle cluster can traverse all target points, find the flight path and distribution method with the smallest group consumption resource, avoid all obstacle points, the path has good smoothness, and the spatial complexity is low; secondly, the present application can well solve the unmanned aerial vehicle flight task in the set environment, reduce the personnel participation, improve the reliability and safety of special tasks; finally, the present application reduces the time consumption of the algorithm, improves the reliability of the algorithm and reduces the probability of the algorithm falling into local optimum by using the improved particle swarm algorithm, and can plan a better path. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0034] Figure 1 is the execution flow diagram of the multi-unmanned aerial vehicle cluster path planning method based on the lightweight A-star algorithm provided by the embodiment of the present application;

[0035] Figure 2 is the A-star algorithm flowchart provided by the embodiment of the present application;

[0036] Figure 3 is the particle swarm algorithm flowchart provided by the embodiment of the present application;

[0037] Figure 4 is the system block diagram of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0039] First of all, it should be noted that in the embodiments of the present application, the words such as "exemplarily", "for example" are used to represent as an example, illustration or explanation. Any embodiment or design scheme described as "exemplary" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "exemplarily" is intended to present the concept in a specific way. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0040] First embodiment

[0041] The embodiment provides a multi-unmanned aerial vehicle cluster path planning method based on a lightweight A-star algorithm, wherein the unmanned aerial vehicle cluster is divided into a reconnaissance group unmanned aerial vehicle and a task group unmanned aerial vehicle, the former is responsible for reconnaissance task environment, determining obstacle information and position and searching target point position; the latter is responsible for flying to the upper space of the target point and performing a corresponding task; the method can more accurately plan a flight path through modeling of obstacles in a real environment; and the method adds an improved particle swarm optimization algorithm to optimize the flight path, uses a variable inertia weight to optimize the convergence process of the particle swarm optimization algorithm, so that the particle swarm optimization algorithm can quickly converge in the first half and improve convergence accuracy in the second half, and an optimal task allocation method is found. The method can be implemented by an electronic device, which can be a terminal or a server. The execution process of the method is as shown in Figure 1 The method comprises the following steps:

[0042] Step one: map initialization.

[0043] The reconnaissance group unmanned aerial vehicle in the unmanned aerial vehicle cluster performs scanning work on the task environment, obtains obstacle model information and position information, marks target point information, and establishes a three-dimensional model according to the actual obstacle shape and size, and constructs a three-dimensional grid map, so as to calculate the distance and plan the path subsequently.

[0044] Step two: preliminary path planning.

[0045] The current GPS position information of each task group unmanned aerial vehicle is taken as a starting point, and each target point is taken as an end point, and a flight path is preliminarily planned and a flight distance matrix is calculated by using the lightweight A-star algorithm.

[0046] Needless to say, the lightweight A-star algorithm is an improvement on the existing A-star algorithm, and the improvement point is that when searching for feasible points in the neighborhood, only the points one unit length away in the six directions of top, bottom, left, right, front and back are considered, and the Manhattan distance calculation method is used when calculating the distance.

[0047] Specifically, as shown in Figure 2 The steps of preliminarily planning the flight path by using the lightweight A-star algorithm are as follows:

[0048] (a) initialization of the algorithm model, the current position of the task group unmanned aerial vehicle is used to initialize the unmanned aerial vehicle flight starting point, and the target point position is used to initialize the unmanned aerial vehicle flight end point; an open list is initialized, and the unmanned aerial vehicle flight starting point is put into the open list for storing nodes to be expanded; a closed list is initialized, and the closed list is set to an empty list for storing expanded nodes; a cost function f(n) is defined, which represents the total distance of the flight path.

[0049] f(n) = g(n) + h(n) (1)

[0050] Wherein, g(n) represents the distance from the starting point to the current node; h(n) represents the distance from the current node to the end point.

[0051] (b) Select the node with the smallest f(n) value from the open list as the current node n, first perform the end condition judgment, judge whether this node is the end point, if it is the end point, the path is found, exit the loop, if it is not the end point, continue the loop, find the neighbor nodes of the current node in the above, below, left, right, front and back six directions as the expansion nodes, for each expansion node, first judge whether the node is located in the obstacle area or whether it is in the closed list, if one of them is met, skip this neighbor node, if none of them is met, calculate the g(n), h(n) and total distance f(n) value of the neighbor node, and update it to the open list.

[0052] g n+1 = g n + Cost(n, n+1) (2)

[0053]

[0054] h n+1 = |x n+1 -x end | + |y n+1 -y end | + |z n+1 -z end | (4)

[0055] Wherein, n represents the current node; n+1 represents the neighbor node, the current node is the father node of the neighbor node, as shown in formula (2), the father node can be used to simplify the calculation when calculating the distance from the starting point; Cost represents the distance from the current node to the neighbor node, which is calculated by using the Euclidean distance; h(n+1) is calculated by using the Manhattan distance.

[0056] After processing each neighbor node, move the current node to the closed list, and then start the next loop to find the next current node to perform this step operation.

[0057] (c) If the end condition is met, that is, the end point of the unmanned aerial vehicle flight is found, take the end point as the starting point, backtrack through its parent node, and save all these points in the list until the starting point, finally get the flight path, and record the total distance of the flight path points.

[0058] (d) Reinitialize the algorithm model, take the current position of the task unmanned aerial vehicle as the starting point, and the positions of the other target points as the end points, re-plan the flight path until all the target points are traversed.

[0059] (e) reinitializing the algorithm model, repeating the above steps for the remaining task group UAVs until all task group UAVs are traversed.

[0060] Step three: task allocation.

[0061] In the case of ensuring that all target points have task group UAVs to reach, the best task allocation method in the flight path matrix is searched out to minimize the total path of the UAV cluster.

[0062] It should be noted that the number of task UAVs is m, and the number of target points is n, and m > n. The distance of the task UAV to each point can be written as a matrix A with m*n, where the mth row of the matrix represents the mth UAV, and the nth column represents the nth target point. According to the total path calculation formula of the UAV cluster, the flight path distance of each case can be calculated and the minimum flight path distance can be found. Based on this, in order to ensure that all target points have task group UAVs to reach and execute tasks, a total distance of the UAV cluster is calculated from each column of the total distance matrix F, and the smallest total distance value is selected. The allocation method is recorded as the task allocation situation in the subsequent steps. The calculation formula is as follows.

[0063]

[0064] Where i(j) is the index of the UAV assigned to target point j (to ensure that different target points are paired with different UAVs); only one element A i(j),j is selected from each column (i.e., each target point) to calculate the distance.

[0065] Step four: path optimization.

[0066] According to the best task allocation method determined in step three, the flight path of each task group UAV is optimized using the improved particle swarm algorithm to find the minimum value of the flight path distance and optimize the smoothness of the flight path.

[0067] It should be noted that the improved particle swarm algorithm initializes the particle swarm position according to the preliminary planned flight path and assigns an initialization speed; the fitness of each particle is calculated according to the fitness formula; the individual extreme value and global extreme value of the particle are updated according to the fitness value; the position and speed of the particle are updated according to the improved particle position and speed update formula; the fitness of the particle in the new position is calculated and the individual extreme value and global extreme value of the particle are updated; whether the calculation precision is met or the maximum iteration number is reached is judged, if met, the algorithm ends, if not met, the particle position and speed are continuously updated, the minimum value of the flight path distance is searched until the end condition is met. Specifically, its execution steps are as Figure 3 shown, including:

[0068] (a) Set the number of iterations nMax and the number of particles m, and initialize the population position according to the preliminary flight path of the task group UAV, and randomly initialize the population speed. Generate enough particle number sample points to provide enough sample solution space for algorithm iteration. At the same time, determine the upper and lower boundaries of the algorithm iteration particles, limit all particles in the particle group to be within the limited upper and lower boundaries.

[0069] (b) Calculate the fitness value F(x i ) of all particles, calculate the size of the feasible solution of all individuals, and provide prior calculation basis for subsequent iteration steps. The size of the fitness value is constructed according to the actual problem, and the abstract problem is converted into a calculable mathematical model, and the size of the fitness value is used to indicate the degree of optimization of the feasible solution.

[0070] (c) Update the individual optimal solution p i and the group optimal solution g best according to the fitness value F(x best ), the core idea of the particle swarm algorithm is to use the individual optimal solution and the group optimal solution to continuously update the iteration, so that the feasible solution of the algorithm approaches the optimal solution in the actual situation. By simulating the social properties of the particle swarm, that is, the individual of the bird, the optimal solution is continuously replaced and iterated.

[0071] F = Cost o + cost l + cost a + cost h + cost maxh + cost minh + cost v + cost hor (6)

[0072] Where, Cost o represents the risk of whether the path passes through the obstacle; Cost l represents the total length of the path, and usually the shorter the path, the lower the cost; Cost a represents the smoothness of the path, the greater the turning angle of the path, the higher the cost; Cost h represents the cost of the change in height of the path, which represents the energy consumption related to the UAV climbing; Cost maxh is used to limit the maximum height of the path; Cost minh is used to limit the minimum height of the path; Cost v is used to control the vertical change of the path to avoid frequent up and down flight to cause additional energy consumption; Cost hor represents the optimization requirement of the path in the horizontal direction, such as avoiding zigzag or detour.

[0073] (d) Update the velocity and position of the particle according to formula (6), (7), (8), meanwhile, detect and limit all the positions of the particle, and uniformly take the attribute of the dimension as the boundary for the attribute of the particle beyond the boundary.

[0074]

[0075]

[0076] wherein, let the search space be D-dimensional space, the number of particles be n, the position of the i-th particle be represented as ; the velocity change rate of the i-th example be represented as ; each kind of particle has two attributes of position and velocity, the best position searched by the i-th particle so far (individual best position) be denoted as p best ; the best position searched by the whole population so far (global best position) be denoted as g best ; ω be called inertia factor; the position and velocity change range of the d-th dimension be and if the and of the iteration of a certain dimension exceed the boundary value, it is considered as the boundary value; c1, c2 be learning factors, generally take random numbers between (0, 2); rand() be a random number between (0, 1).

[0077] The convergence speed of the particle swarm algorithm depends on ω, when ω is larger, the global search ability of the algorithm is stronger, and it is suitable for global search; when ω is smaller, the search precision of the algorithm is higher, and it is more suitable for local search. Therefore, a logarithmic function is used to control the change of the inertia weight ω, and a random adjustment number subject to Gaussian distribution is added to realize the dynamic adjustment of the inertia weight in the evolution process, enhance the global search ability of the algorithm in the later stage, and reduce the possibility of falling into local optimum. The expression of the improved inertia weight is:

[0078]

[0079] wherein, t be the current iteration number; T be the maximum iteration number; α be inertia adjustment factor, its value range is 0~(ω max -ω min ) / 2, the smaller its value, the smaller the influence of the random number subject to Gaussian distribution on the dynamic change of the inertia weight, the larger its value, the larger the influence of the random number subject to Gaussian distribution on the dynamic change of the inertia weight; randn be a random number satisfying Gaussian distribution; ω min be the minimum value of the inertia weight without disturbance of the random number subject to Gaussian distribution, used to limit the lower bound of the change of the inertia weight; ω maxThe maximum value of the inertia weight is used to limit the upper bound of the change of the inertia weight in the case of non-Gaussian distribution random number disturbance.

[0080] (e) Calculate the fitness of all particles and update the individual optimal solution and the global optimal solution.

[0081] (f) If the operation precision or the number of iterations is met, the algorithm ends, otherwise, jump to step 3 and continue searching.

[0082] (g) The other task group UAVs in the optimal task allocation method are subjected to particle swarm optimization according to the above steps until all task group UAVs in the task allocation method are optimized.

[0083] Step five: task execution.

[0084] The final flight path is assigned to the task group UAVs that need to perform the task, and the task group UAVs are controlled to fly to the target point and complete the subsequent task.

[0085] In summary, the embodiment provides a multi-UAV cluster path planning method based on a lightweight A-star algorithm. First, the method can quickly and efficiently complete the multi-UAV cluster cooperative flight task, has strong stability, and the UAV cluster can traverse all target points, find the flight path and distribution method with the smallest group resource consumption, avoid all obstacle points, and has good path smoothness and low spatial complexity. Second, the method can well solve the UAV flight task in the set environment, reduce personnel participation, and improve the reliability and safety of special tasks. Finally, the method reduces the time consumption of the algorithm, improves the reliability of the algorithm, and reduces the probability of the algorithm falling into local optimum by using the improved particle swarm algorithm, and can plan a better path.

[0086] Second embodiment

[0087] The embodiment provides an electronic device, such as Figure 4 As shown in the figure, the electronic device includes a processor and a memory; wherein the processor and the memory can be connected through a communication bus; the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment. In addition, the electronic device can also include a transceiver, and the processor and the transceiver can be connected through a communication bus, and the transceiver is used for communication with other devices.

[0088] Next, the various components of the electronic device will be described in detail: Figure 4

[0089] ​The processor is the control center of the electronic device. The electronic device can include multiple processors. Each of the processors can be a single-CPU or a multi-CPU. The processor can be one processor or a collective term of multiple processing elements. For example, the processor can be one or more central processing units (CPUs), other general purpose processors, application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement one or more embodiments of the present application, such as one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor can be a microprocessor or any conventional processor, or the like. The processor can perform various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0090] In a specific implementation, as an embodiment, the processor can include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 1, of course, this is only an exemplary description. Figure 4

[0091] The memory is used to store software programs for implementing the solution of the present application, and is controlled by the processor to perform the implementation. The specific implementation can refer to the method embodiments described above, and will not be described here.

[0092] ​Optionally, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may be integrated with the processor or may exist independently, and may be accessed through the interface circuit of the electronic device (…). Figure 4 (Not shown in the image) is coupled to the processor; however, this embodiment of the invention does not impose specific limitations on this.

[0093] The transceiver may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function. The transceiver can be integrated with the processor or exist independently, and is connected through the interface circuit of the electronic device (…). Figure 4 (Not shown in the image) is coupled to the processor, and this embodiment of the invention does not specifically limit this.

[0094] In addition, it should be noted that, Figure 4 The structure of the electronic device shown is not intended to limit the device. Actual devices may include more or fewer components than shown, or combine certain components, or have different component arrangements. Furthermore, the technical effects achieved by this electronic device when performing the method of the first embodiment described above can be referenced to the technical effects described in the first embodiment; therefore, they will not be repeated here.

[0095] Third Embodiment

[0096] This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.

[0097] Moreover, it should be noted that the present application can be provided as a method, an apparatus, or a computer program product. Therefore, the embodiments of the present application can take the form of an entirely or partially hardware embodiment, an entirely or partially software embodiment, or an embodiment combining software and hardware aspects. Furthermore, when implemented in software, the embodiments of the present application can take the form of a computer program product including one or more computer program instructions embodied on one or more computer-usable storage media (media). The computer program instructions can be executed by a computer, a processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart block or blocks or in the flowcharts and / or block diagrams. These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing terminal device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart block or blocks or the flowcharts and / or block diagrams.

[0098] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate one or more functions implemented in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The apparatus that implements the functions specified in one or more flows and / or blocks.

[0099] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart block or blocks or the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block(s). Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block(s). Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block(s).

[0100] It should also be noted that, in the present document, the terms such as first and second, etc. are merely used to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or terminal device. Without more limitations, the element defined by the statement "including a…", does not exclude the presence of other identical elements in the process, method, article or terminal device including the element. In addition, the term "and / or" is merely a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " in the present document generally represents an "or" relationship between the front and rear associated objects, but it can also represent an "and / or" relationship, which can be understood in the context before and after. "One or more" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0101] In addition, it can be understood that in various embodiments of the present application, the size of the sequence number of the above processes does not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0102] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or in a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0103] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of functional modules / units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms. The units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment. In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present, or two or more units can be integrated in one unit.

[0104] If the method is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0105] Finally, it should be noted that the above description is only the preferred embodiment of the application, it should be pointed out that although the preferred embodiment of the application has been described, for those skilled in the art, once the basic creative concept of the application is known, several improvements and refinements can be made without departing from the principles of the application, and these improvements and refinements should also be considered as the protection scope of the application. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the application.

Claims

1. A multi-UAV swarm path planning method based on the lightweight A-Star algorithm, wherein, The drones in the drone swarm are divided into reconnaissance drones and mission drones. The method for multi-drone swarm path planning based on the lightweight A-Star algorithm includes: The reconnaissance drones in the drone swarm scan the mission environment to obtain obstacle model information and location information, mark target point information, and build a three-dimensional grid map. Based on the constructed 3D grid map, the flight path of each task group UAV in the UAV swarm is initially planned using the current position information of each task group UAV as the starting point and each target point as the ending point, and the flight distance matrix is ​​calculated. Each row of the flight distance matrix represents a task group UAV, and each column of the flight distance matrix represents a target point. Based on the flight distance matrix, the total flight path of the UAV swarm corresponding to different flight path planning schemes is calculated. Under the premise of ensuring that all target points are reached by task group UAVs, the optimal flight path planning scheme is searched with the goal of minimizing the total flight path of the UAV swarm. For the optimal flight path planning scheme, an improved particle swarm optimization algorithm is used to optimize the flight path of each task group UAV, seeking the minimum value of the flight path distance and optimizing the smoothness of the flight path. The optimized flight path is assigned to the corresponding task group drones, which are then controlled to fly to the corresponding target point and complete the subsequent tasks.

2. The multi-UAV swarm path planning method based on the lightweight A-Star algorithm as described in claim 1, characterized in that, In the process of initially planning the flight path of each task group UAV using the lightweight A-Star algorithm, when searching for feasible points in the neighborhood, the lightweight A-Star algorithm only considers points that are one unit away from the current node in six directions: above, below, left, right, in front, and behind it.

3. The multi-UAV swarm path planning method based on the lightweight A-Star algorithm as described in claim 2, characterized in that, The lightweight A* algorithm uses Euclidean distance to calculate the distance from the current node to its neighboring nodes.

4. The multi-UAV swarm path planning method based on the lightweight A-Star algorithm as described in claim 3, characterized in that, The lightweight A* algorithm uses Manhattan distance to calculate the distance from neighboring nodes to the endpoint.

5. The multi-UAV swarm path planning method based on the lightweight A-Star algorithm as described in claim 1, characterized in that, The optimal flight path planning scheme uses an improved particle swarm optimization algorithm to optimize the flight path of each drone in the task group, including: The improved particle swarm algorithm initializes the particle swarm position and assigns it an initial velocity based on the flight path of each drone in the optimal flight path planning scheme. Calculate the fitness value for each particle according to the fitness formula; Update the individual and global extrema of particles based on their fitness values; The particle's position and velocity are updated according to the improved particle position and velocity update formula; Calculate the fitness of the particle at the new position and update the individual extrema and global extrema of the particle; Determine if the termination condition is met. If it is, the algorithm terminates. If not, continue updating the particle position and velocity, and iteratively search for the minimum value of the flight path distance until the termination condition is met.

6. The multi-UAV swarm path planning method based on the lightweight A-Star algorithm as described in claim 5, characterized in that, The improved particle position and velocity update formula refers to improving the inertia weight in the particle position and velocity update formula of the particle swarm algorithm to enable adaptive dynamic adjustment.

7. The multi-UAV swarm path planning method based on the lightweight A-Star algorithm as described in claim 6, characterized in that, The improvement to the inertia weight in the particle position and velocity update formula of the particle swarm optimization algorithm, enabling it to achieve adaptive dynamic adjustment, includes: A logarithmic function is used to control the change in inertia weight, and a random adjustment number following a Gaussian distribution is added to implement dynamic adjustment of the inertia weight during the evolution process.

8. The multi-UAV swarm path planning method based on the lightweight A-Star algorithm as described in claim 7, characterized in that, The inertial weight ω d The expression is: Where t is the current iteration number; T is the maximum iteration number; α is the inertia adjustment factor; randn is a random number that follows a Gaussian distribution; ω min ω represents the minimum value of the inertia weight without Gaussian random number perturbation, used to define the lower bound of the change in inertia weight; max This represents the maximum value of the inertia weight without Gaussian random number perturbation, and is used to define the upper bound of the change in the inertia weight.

Images