A UAV dispatching control method for multi-machine collaborative operation

Abstract

The present invention relates to the field of drone control, and more specifically, to a method for dispatching and controlling drones for collaborative operations of multiple drones, the method comprising: obtaining three-dimensional spatial data of the area to be flown and the position information of drones and obstacles, determining the flight path points of the drones, and obtaining an initial flight path; using an optimization method and an objective function to iteratively optimize the path, and identifying drones with collision risks. After reaching a preset number of iterations, if the objective function is minimized to meet a threshold, the first flight path is output; otherwise, the drones without an optimal solution are marked, the objective function is corrected and optimized continuously until the conditions are met, and the second flight path planning is output to achieve the scheduling of drone collaborative operations. The present invention ensures that the drones maintain a safe distance during flight by iteratively optimizing the objective function, thereby improving the safety of drone flight.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle control, and more specifically, to a method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation. Background Art

[0002] Drone dispatching refers to the process of planning and managing the flight missions, flight paths, take-off and landing times of drones in a multi-drone system. The purpose of this task is to ensure that drones can complete their assigned tasks efficiently and safely while avoiding collisions and conflicts. Therefore, in order to better avoid collisions, drones of the same type often fly together in existing path planning. However, if a large number of drones are required to work together, the same type of drones will be prone to accidents when performing collaborative operations due to the different operating parameters of different types of drones.

[0003] The existing Chinese patent application document with publication number CN116859998A discloses a UAV multi-machine collaborative operation management system, including a management and control center system, the management and control center system includes a UAV control system and a UAV scheduling system, the UAV control system is used to control the work content of the UAV, the UAV scheduling system is used to replace the position between a faulty UAV and a normal UAV, and the UAV control system and the UAV scheduling system are respectively connected to the management and control center system through signals.

[0004] This patent application belongs to the field of multi-machine collaborative operation management technology. It solves the problem of real-time judgment of whether the working drone is working normally. When an abnormality occurs, the backup drone is used to work in time to avoid work suspension due to failure, thereby improving the management efficiency of the drone multi-machine collaborative operation management system. At present, when the existing drones are coordinated and dispatched, the existing path planning algorithm can be used for path planning, and the dispatch control is performed according to the determined path planning results. However, when planning the paths of different types of drones, there may be collision points in the planned paths, which may lead to safety hazards when dispatching drones. Summary of the invention

[0005] In order to solve the problem that when planning paths for different types of drones, there may be collision points in the planned paths, which may lead to safety hazards when dispatching drones, the present invention provides solutions in the following aspects.

[0006] A method for dispatching and controlling unmanned aerial vehicles for multi-machine cooperative operation comprises: obtaining three-dimensional spatial data of a to-be-flying area and position information of unmanned aerial vehicles and obstacles, determining flight path points of unmanned aerial vehicles, and obtaining an initial flight path; using an optimization method and setting an objective function, obtaining unmanned aerial vehicles with collision risks, iteratively optimizing to minimize the objective function, stopping iteration after reaching a preset number of iterations, and in response to the objective function being minimized to be less than or equal to a preset threshold, an optimal solution exists, outputting a first flight path planning, and completing the flight dispatching of unmanned aerial vehicles in cooperative operation; otherwise, when there is no optimal solution, marking the unmanned aerial vehicle without the optimal solution as 0, and marking the unmanned aerial vehicle with the optimal solution as 1, and correcting the objective function based on the unmanned aerial vehicle marked as 1 until reaching a preset number of iterations, and in response to the objective function being minimized to be less than or equal to the preset threshold, outputting a second flight path planning, and thus completing the flight dispatching of unmanned aerial vehicles in cooperative operation; wherein, the corrected objective function satisfies the following relational expression: , where represents the corrected objective function, represents the objective function, Indicates the number of drones marked as 1, Represents a hyperparameter.

[0007] The effect is that by comprehensively utilizing three-dimensional spatial data, information on the location of drones and obstacles, as well as optimization algorithms and objective functions, it is possible to identify and optimize paths with collision risks, ensure flight safety, find the optimal solution through iterative optimization, or adapt to the situation by modifying the objective function when the optimal solution cannot be found directly, and finally output a flight path planning that meets safety and efficiency requirements. This not only improves flight safety, but also improves the efficiency and adaptability of drone scheduling, ensuring the smooth progress of multi-drone collaborative operations.

[0008] Preferably, determining the flight path point of the drone includes:

[0009] Divide the three-dimensional space data, determine the flight area of ​​the drone according to the drone's flight altitude limit, obtain the operation coordinates and starting point coordinates of the drone, and mark obstacle information in the three-dimensional space based on the flight area;

[0010] Among them, one of the drones corresponds to an operation coordinate and a starting point coordinate, and a path planning method is used to obtain the flight path points of the drone from the starting point coordinate to the operation coordinate.

[0011] The effect is that by quickly replanning the route when encountering obstacles or flight conflicts, delays can be reduced, the response speed to emergencies can be improved, unnecessary flight distance and time can be reduced, and energy can be saved.

[0012] Preferably, the setting of the objective function includes:

[0013] Taking any UAV as the target, determine the flight path points of the target, calculate the minimum distance points between the flight path of the target UAV and the flight paths of other UAVs, and use the flight simulation data of the same type of the target to obtain the disturbance radius;

[0014] A step function is used, and the value is 1 when the minimum spacing point is less than the safety threshold, otherwise, the value is 0. The preset hyperparameters are used as weights to obtain the penalty term for collision risk, and the difference between the penalty term and the disturbance radius is used to set the objective function.

[0015] The effect is: by calculating the minimum spacing point between drones, accurately assessing the risk of collision and ensuring flight safety, using step functions and disturbance radius to dynamically adjust the flight path of the drone to avoid potential collisions, and by minimizing the objective function, balancing flight safety and efficiency, reducing unnecessary path adjustments, optimizing the flight path of multiple drones during collaborative operations, reducing mutual interference, and improving collaborative efficiency.

[0016] Preferably, the outputting the first flight path plan includes:

[0017] According to the set objective function, UAVs with collision risks in the flight space are obtained, a collision UAV set is constructed, the disturbance radius and safety threshold are determined according to the flight speed of the UAV, and a safety buffer zone is created for each UAV. The safety buffer zone is used as an obstacle to generate variable obstacle points. Based on the variable obstacle points, a path planning algorithm is used to correct the initial flight path for the UAVs with collision risks, and the first flight path plan is output.

[0018] The effects are: by determining the disturbance radius and safety threshold according to the flight speed of the drone, a safety buffer zone is created for each drone, enhancing flight safety; the safety buffer zone is used as an obstacle to generate variable obstacle points, making path planning more flexible and adaptable, and the path planning algorithm is used to correct the initial flight path for drones with collision risks, improving the safety and efficiency of the path. By accurately identifying risks, creating safety buffer zones, dynamically generating obstacles, and optimizing path planning, not only the safety of drone flights is improved, but also the flight efficiency and collaborative operation capabilities are improved.

[0019] Preferably, the safety buffer zone includes:

[0020] Taking any UAV as the target, each flight path point on the flight path of other normally flying UAVs other than the target is taken as the center of the circle, and the safety threshold is used as the radius to expand it, thus generating a safety buffer zone for each UAV.

[0021] Preferably, the outputting the second flight path planning further includes:

[0022] Obtain the normal section of the flight path corresponding to the UAV marked as 0, obtain the projection coordinates of the obstacles corresponding to the flight paths of other UAVs on their normal sections, and obtain the projection data on the normal section, wherein the position of the projection data on the normal section is marked as A, and the position of the non-projection data is marked as B;

[0023] Perform convex hull detection on the projection data marked as A, and obtain the convex hull result as the normal section matrix for flight path planning of the drone from the inside to the outside of the multi-drone formation;

[0024] The refinement algorithm is used to obtain the center line of the normal section matrix, and the intersection of the center line and the boundary of the normal section matrix is ​​obtained as the expected position point outside the multi-UAV formation; the 2D path planning algorithm is used to obtain the path of the UAV from the coordinates of the normal section matrix to the operating coordinate point, and the path planning is completed.

[0025] The effect is: by obtaining the normal section of the UAV's flight path and the projection coordinates of the obstacles, the spatial limitations around the UAV can be identified, so as to plan a more accurate flight path. By detecting the convex hull and obtaining the center line, a safe path can be found for the UAV to avoid obstacles, reduce the risk of collision, and improve flight safety. Using the 2D path planning algorithm, the shortest path from the current position to the target position can be quickly planned for the UAV, thereby improving flight efficiency and reducing energy consumption.

[0026] Preferably, the flight distance and the flight time are obtained according to the second flight path planning, and the normal section matrix at the continuous flight time intervals and the change amount of the normal section matrix at the continuous flight time intervals are obtained with the flight time as the interval;

[0027] In response to the change in the normal section matrix being less than a preset variable, it indicates that the flight path adjustment can be made from inside the multi-UAV formation to outside; otherwise, it indicates that the adjustment cannot be made.

[0028] The effect is that by continuously monitoring the changes in the slice matrix, potential obstacles and risks on the flight path can be identified in real time, and the flight path can be adjusted in time to ensure safety. By setting preset variables to determine whether the flight path needs to be adjusted, the drone can be prevented from entering high-risk areas and the possibility of collisions and other flight accidents can be reduced.

[0029] Preferably, the outputting the second flight path planning further includes:

[0030] The drone marked as 0 is decelerated until the distance between it and other drones reaches the preset control distance. The flight paths of all drones in front are regarded as obstacles and the path is replanned.

[0031] The present invention has the following effects:

[0032] 1. The present invention effectively identifies and resolves potential collision risks in the flight path by comprehensively considering the three-dimensional spatial data of drones, obstacle location information, and mutual interference between drones. By iteratively optimizing the objective function, it ensures that drones maintain a safe distance during flight, significantly reducing the possibility of collision between drones during collaborative operations, thereby improving the overall flight safety.

[0033] 2. By setting the objective function and performing iterative optimization, the present invention can plan an efficient flight path for each drone. On the premise of ensuring safety, the path planning algorithm in the method takes into account the flight speed and disturbance radius, creates a safety buffer for the drone, reduces the flight path adjustment caused by obstacle avoidance and collision risks, and improves the flight efficiency of the drone and the completion speed of collaborative operations.

[0034] 3. When the present invention solves the collision risk through path adjustment, it provides a solution for adjusting the speed and re-planning the path of the UAV, so as to cope with the complex and changeable flight environment, ensure the smooth execution of the mission, and maintain effective flight scheduling control even in high-density flight or emergency situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0036] Figure 1 It is a method flow chart of steps S1 to S3 in a method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operations according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0039] Reference Figure 1 A method for dispatching and controlling a UAV for multi-machine collaborative operation includes steps S1 to S3, which are specifically as follows:

[0040] S1: Obtain the three-dimensional spatial data of the area to be flown and the location information of the UAV and obstacles, determine the flight path points of the UAV, and obtain the initial flight path.

[0041] Divide the three-dimensional space data, determine the flight area of ​​the drone according to the drone's flight altitude limit, obtain the operation coordinates and starting point coordinates of the drone, and mark obstacle information in the three-dimensional space based on the flight area;

[0042] Exemplarily, the three-dimensional spatial data includes but is not limited to: terrain height, building height, natural landmarks; the flight area includes: a flyable area and a non-flyable area; obstacles include but are not limited to: buildings, towers, wires, trees and flying birds;

[0043] Among them, one UAV corresponds to one operation coordinate and a starting point coordinate, and the path planning method is used to obtain the flight path points of the UAV from the starting point coordinate to the operation coordinate.

[0044] That is to say, the flight path points of a UAV from the starting point coordinates to the operating coordinates constitute the flight path.

[0045] Further analysis shows that the flight speed of drones may be inconsistent during flight, and the disturbance radius requirements for adjacent drones are different. If they are too close, the drones are flying through rotors, which can easily generate turbulence, causing unstable flight of nearby drones and accidents. If the disturbance radius remains consistent, the speed of the drone will change during obstacle avoidance, resulting in changes in the disturbance radius during normal flight. If the drones are always flying at the maximum disturbance radius, the efficiency of the drone swarm’s collaborative flight will be affected. Therefore, the specific steps for obtaining the drones that have collided are as follows:

[0046] S2: Use the optimization method and set the objective function to obtain the UAVs with collision risks, iterate the optimization to minimize the objective function, stop the iteration after reaching the preset number of iterations, and when the objective function is minimized and is less than or equal to the preset threshold, there is an optimal solution, output the first flight path planning, and complete the UAV flight scheduling during unmanned collaboration.

[0047] In this embodiment, the preset number of iterations is 100 and the preset threshold is 900, which can be adjusted according to actual scenarios.

[0048] Set the objective function, including:

[0049] Taking any UAV as the target, determine the flight path points of the target, calculate the minimum distance points between the flight path of the target UAV and the flight paths of other UAVs, and use the flight simulation data of the same type of the target to obtain the disturbance radius;

[0050] It is further explained that the simulation method is a well-known technology in the art and will not be described in detail.

[0051] A step function is used. When the minimum spacing point is less than the safety threshold, the value is 1. Otherwise, the value is 0. The preset hyperparameters are used as weights to obtain the penalty term for collision risk. The difference between the penalty term and the disturbance radius is used to set the objective function.

[0052] Specifically, the objective function satisfies the following relationship:

[0053] ;

[0054] In the formula, represents the objective function, represents a step function, It represents the minimum Euclidean distance between the drone and other drone flight path points. represents the safety threshold, represents the hyperparameter, It represents the minimum value of the disturbance radius corresponding to the flight speed of all UAVs in the new path planning result.

[0055] That is, the minimum value of the disturbance radius The larger the value, the faster the corresponding drone will fly, the greater the interference will be, and the larger the corresponding disturbance radius will be. The larger the value, the more it meets the flight expectations. The minimum spacing point is calculated as the minimum Euclidean distance between the drone and other drone flight path points. The safety threshold , can be adjusted according to actual conditions; among them, Represents a hyperparameter. In this embodiment , which can be adjusted according to the actual situation to prevent collisions from occurring during iterative solutions, thereby avoiding the risk of collisions when planning a new flight path.

[0056] Output the first flight path plan, including:

[0057] According to the set objective function, the drones with collision risks in the flight space are obtained, and a set of collision drones is constructed. The disturbance radius and safety threshold are determined according to the flight speed of the drones, and a safety buffer zone is created for each drone. The safety buffer zone is used as an obstacle to generate variable obstacle points. Based on the variable obstacle points, a path planning algorithm is used to correct the initial flight path for the drones with collision risks, and the first flight path plan is output.

[0058] It should be noted that by calculating the minimum distance between drones and identifying the drones that may collide, potential mid-air collisions can be prevented and avoided in advance, and all drones with collision risks can be gathered together to centrally process and optimize their flight paths, reducing the complexity of management and calculation.

[0059] Specifically, the safety buffer zone includes:

[0060] Taking any UAV as the target, each flight path point on the flight path of other normally flying UAVs other than the target is taken as the center of the circle, and the safety threshold is used as the radius to expand it, thus generating a safety buffer zone for each UAV.

[0061] In other words, treating the safety buffer zone as an obstacle actually defines an inviolable area for each drone in the flight space. These areas are regarded as obstacles in path planning, forcing drones to avoid these areas; based on the variable obstacle points, the initial flight path of the drone is adjusted to ensure that the path not only avoids physical obstacles, but also avoids the safety buffer zones of other drones, thereby reducing the risk of collision.

[0062] Further explanation: if there is no optimal solution, it means that there is still a high possibility of collision. Therefore, this solution chooses to prioritize the selection of drones that cannot find the optimal solution, and then waits for the drones that cannot find the optimal solution to perform secondary path planning. The specific steps are:

[0063] S3: In response to the absence of an optimal solution, the UAV without the optimal solution is marked as 0, and the UAV with the optimal solution is marked as 1. The objective function is corrected based on the UAV marked as 1 until a preset number of iterations is reached. In response to the objective function being minimized to be less than or equal to a preset threshold, the second flight path planning is output, thereby completing the UAV flight scheduling during unmanned collaboration.

[0064] The corrected objective function satisfies the following relationship:

[0065] ;

[0066] In the formula, represents the corrected objective function, represents the objective function, Indicates the number of drones marked as 1, Represents a hyperparameter.

[0067] That is, the hyperparameters , which can be adjusted according to the specific implementation scenario. The solution process and iteration stop condition are consistent with step S2.

[0068] It should be noted that the optimal solution output by the revised objective function can complete the UAV flight scheduling during unmanned collaboration, but for the UAV marked as 0, three path plannings are required. Among them, since a new effective flight path planning can no longer be achieved within the multi-UAV queue, the UAV marked as 0 needs to be adjusted to the outside of the multi-UAV queue for new flight path planning.

[0069] That is to say, after the second flight path planning, there are still drones with the ID 0. This may be because a new valid flight path planning cannot be implemented in the multi-drone queue. In addition, based on the second flight path planning, it also includes:

[0070] Get the normal section plane of the flight path corresponding to the UAV marked as 0, obtain the projection coordinates of the obstacles corresponding to the flight paths of other UAVs on the normal section plane, and obtain the projection data on the normal section plane, where the position of the projection data on the normal section plane is marked as A, and the position of the non-projection data is marked as B;

[0071] It should be noted that the normal plane can be understood as a plane tangent to the flight path. In actual operation, the tangent line can be obtained by calculating the derivative of the UAV's flight path, and then the normal plane can be obtained. In addition, the flight data of the UAV can be used to approximate the normal plane through numerical methods (such as finite element analysis), and then computer vision technology, such as stereo vision or deep learning, can be used to identify obstacles and automatically calculate their projections on the normal plane.

[0072] Perform convex hull detection on the projection data marked as A, and obtain the convex hull result as the normal section matrix for flight path planning of the drone from the inside to the outside of the multi-drone formation;

[0073] The refinement algorithm is used to obtain the center line of the normal section matrix, and the intersection of the center line and the boundary of the normal section matrix is ​​obtained as the expected position point outside the multi-UAV formation; the 2D path planning algorithm is used to obtain the path of the UAV from the coordinates of the normal section matrix to the operating coordinate point, and the path planning is completed.

[0074] It should be noted that the refinement algorithm and 2D path planning algorithm in the above steps are well-known technologies to those skilled in the art and will not be described in detail. In addition, the center line can be extracted through edge detection and morphological operations, and a sampling-based path planning method, such as RRT (rapidly explored random trees), can be used to obtain the path of the drone from the coordinates of the normal section matrix to the operating coordinate point.

[0075] Acquire the flight distance and flight time according to the second flight path planning, and acquire the normal section matrix at the continuous flight time intervals and the change amount of the normal section matrix at the continuous flight time intervals with the flight time as the interval;

[0076] In response to the change in the normal section matrix being less than a preset variable, it indicates that the flight path adjustment can be made from inside the multi-UAV formation to outside; otherwise, it indicates that the adjustment cannot be made.

[0077] Exemplarily, in this embodiment, the preset variable is 50, which can be adjusted according to specific implementation conditions.

[0078] In addition, in another embodiment, the UAV marked as 0 can be decelerated until the distance between it and other UAVs reaches a preset control distance, and the flight paths of all the UAVs in front can be regarded as obstacles and the path planning can be re-performed.

[0079] Exemplarily, in this embodiment, the preset control distance is 100m, which can be adjusted by the implementer according to the specific implementation scenario.

[0080] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0081] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation, characterized in that: include: Obtain the three-dimensional spatial data of the area to be flown and the location information of the drone and obstacles, determine the flight path points of the drone, and obtain the initial flight path; Using the optimization method and setting the objective function, obtaining the UAVs with collision risks, iteratively optimizing to minimize the objective function, stopping the iteration after reaching a preset number of iterations, and responding to the optimal solution when the objective function is minimized to be less than or equal to a preset threshold, outputting the first flight path planning, and completing the UAV flight scheduling during unmanned collaboration; On the contrary, when there is no optimal solution, the drone without the optimal solution is marked as 0, and the drone with the optimal solution is marked as 1. The objective function is corrected based on the drone marked as 1 until the preset number of iterations is reached. In response to the objective function being minimized to be less than or equal to the preset threshold, the second flight path planning is output, thereby completing the flight scheduling of drones in unmanned collaboration. Among them, the corrected objective function satisfies the following relationship: , where represents the corrected objective function, represents the objective function, Indicates the number of drones marked as 1, represents a hyperparameter.

2. The method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation according to claim 1, characterized in that: Determining the flight path point of the drone includes: Divide the three-dimensional space data, determine the flight area of ​​the drone according to the drone's flight altitude limit, obtain the operation coordinates and starting point coordinates of the drone, and mark obstacle information in the three-dimensional space based on the flight area; Among them, one of the drones corresponds to an operation coordinate and a starting point coordinate, and a path planning method is used to obtain the flight path points of the drone from the starting point coordinate to the operation coordinate.

3. The method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation according to claim 1, characterized in that: The setting of the objective function comprises: Taking any UAV as the target, determine the flight path points of the target, calculate the minimum distance points between the flight path of the target UAV and the flight paths of other UAVs, and use the flight simulation data of the same type of the target to obtain the disturbance radius; A step function is used, and the value is 1 when the minimum spacing point is less than the safety threshold, otherwise, the value is 0. The preset hyperparameters are used as weights to obtain the penalty term for collision risk, and the difference between the penalty term and the disturbance radius is used to set the objective function.

4. The method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation according to claim 1, characterized in that: The outputting of the first flight path planning comprises: According to the set objective function, UAVs with collision risks in the flight space are obtained, a collision UAV set is constructed, the disturbance radius and safety threshold are determined according to the flight speed of the UAV, and a safety buffer zone is created for each UAV. The safety buffer zone is used as an obstacle to generate variable obstacle points. Based on the variable obstacle points, a path planning algorithm is used to correct the initial flight path for the UAVs with collision risks, and the first flight path plan is output.

5. The method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation according to claim 4, characterized in that: The safety buffer zone includes: Taking any UAV as the target, each flight path point on the flight path of other normally flying UAVs other than the target is taken as the center of the circle, and the safety threshold is used as the radius to expand it, thus generating a safety buffer zone for each UAV.

6. The method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation according to claim 1, characterized in that: The outputting of the second flight path planning further includes: Obtain the normal section of the flight path corresponding to the UAV marked as 0, obtain the projection coordinates of the obstacles corresponding to the flight paths of other UAVs on their normal sections, and obtain the projection data on the normal section, wherein the position of the projection data on the normal section is marked as A, and the position of the non-projection data is marked as B; Perform convex hull detection on the projection data marked as A, and obtain the convex hull result as the normal section matrix for flight path planning of the drone from the inside to the outside of the multi-drone formation; The refinement algorithm is used to obtain the center line of the normal section matrix, and the intersection of the center line and the boundary of the normal section matrix is ​​obtained as the expected position point outside the multi-UAV formation; the 2D path planning algorithm is used to obtain the path of the UAV from the coordinates of the normal section matrix to the operating coordinate point, and the path planning is completed.

7. The method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation according to claim 1, characterized in that: Acquire the flight distance and the flight time according to the second flight path planning, and acquire the normal section matrix at the continuous flight time intervals and the change amount of the normal section matrix at the continuous flight time intervals with the flight time as the interval; In response to the change in the normal section matrix being less than a preset variable, it indicates that the flight path adjustment can be made from inside the multi-UAV formation to outside; otherwise, it indicates that the adjustment cannot be made.

8. The method for dispatching and controlling unmanned aerial vehicles for multi-machine collaborative operation according to claim 1, characterized in that: The outputting of the second flight path planning further includes: The drone marked as 0 is decelerated until the distance between it and other drones reaches the preset control distance. The flight paths of all drones in front are regarded as obstacles and the path is replanned.

Images