Traffic control system based on drone operation safety

Abstract

The present invention relates to a traffic control system based on the safety of unmanned aerial vehicle operation, and relates to the field of unmanned aerial vehicle traffic control, including: a route dispersion analysis module; a flight information reading module; an obstacle coverage acquisition module, which is used to predict flight obstacle information and obtain the obstacle coverage of a predetermined time zone; a flight plan optimization module, which is used to take avoiding obstacle coverage and satisfying flight safety barriers as optimization constraints, and use a task execution evaluation function to perform overall optimization of flight parameters of multiple unmanned aerial vehicles based on route dispersion and task priority, generate an optimal flight plan, and execute flight tasks in a predetermined time zone. The present invention can solve the technical problems that the existing methods lack an effective multi-unmanned aerial vehicle collaborative management mechanism, resulting in low efficiency of unmanned aerial vehicle task execution and poor flight safety. It can significantly improve the operating efficiency of unmanned aerial vehicles and realize efficient task execution of multi-unmanned aerial vehicle collaborative operations on the premise of ensuring the flight safety of unmanned aerial vehicles.

Description

Technical Field

[0001] The present invention relates to the field of drone traffic control, and in particular to a traffic control system based on drone operation safety. Background Art

[0002] With the rapid development of drone technology, drones are increasingly used in logistics distribution, emergency rescue, environmental monitoring, agricultural inspections and other fields. However, the complex airspace management requirements brought about by the coordinated flight of multiple drones have also brought huge technical challenges to the existing drone traffic control system. When multiple drones perform tasks at the same time, the flight environment in the airspace becomes more dynamic and complex. Traditional static route planning and simple obstacle avoidance methods can no longer cope with complex coordinated flight requirements, and there are major technical bottlenecks. Summary of the invention

[0003] The present invention aims to solve the technical problem that existing UAV traffic control methods lack an effective multi-UAV collaborative management mechanism, resulting in low UAV mission execution efficiency and poor flight safety, and provides a traffic control system based on UAV operation safety to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a traffic control system based on the safety of UAV operation, the system includes a traffic control platform, the traffic control platform and the UAV control terminal are in communication connection, including: a route dispersion analysis module, which is used to read the number of UAVs and the scheduled flight route set in the target airspace in real time within the traffic control platform, if the number of UAVs is greater than a predetermined scalar, perform three-dimensional mapping and dispersion analysis on the scheduled flight route set to obtain route dispersion; a flight information reading module, which is used to read the flight obstacle information of the target airspace and the flight characteristic information of the UAV if the route dispersion is less than the expected dispersion index, wherein the flight characteristic information includes mission priority and A flight safety barrier; an obstacle coverage acquisition module, used to predict the flight obstacle information through an obstacle movement predictor to obtain the obstacle coverage in a predetermined time zone; a flight plan optimization module, used to take avoiding the obstacle coverage and satisfying the flight safety barrier as optimization constraints, use a task execution evaluation function, based on the route discreteness and task priority, perform overall optimization of the flight parameters of multiple UAVs, and generate an optimal flight plan, wherein the optimal flight plan includes multiple optimal flight parameters; a flight mission execution module, used to map and transmit the multiple optimal flight parameters to the control terminals of the multiple UAVs to execute the flight mission in the predetermined time zone.

[0006] In a second aspect, the present invention further provides an electronic device, comprising:

[0007] At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the traffic control system based on the safety of drone operation as described in any one of the first aspects above.

[0008] In a third aspect, a computer-readable storage medium stores a computer program, and when the computer program is executed, the traffic control system based on the safety of drone operation as described in any one of the first aspects above is implemented.

[0009] The beneficial effects of the present invention are as follows: by reading the number of drones and a set of scheduled flight routes in the target airspace in real time in a traffic control platform, if the number of drones is greater than a predetermined scalar, performing three-dimensional mapping and discreteness analysis on the set of scheduled flight routes to obtain route discreteness; if the route discreteness is less than an expected discrete index, reading the flight obstacle information of the target airspace and the flight feature information of the drones, wherein the flight feature information includes mission priority and flight safety barriers; predicting the flight obstacle information through an obstacle movement predictor to obtain the obstacle coverage range of a predetermined time zone; taking avoiding the obstacle coverage range and satisfying the flight safety barriers as optimization constraints, utilizing The task execution evaluation function performs overall optimization of the flight parameters of multiple UAVs based on the route discreteness and task priority to generate an optimal flight plan, wherein the optimal flight plan includes multiple optimal flight parameters; the multiple optimal flight parameters are mapped and transmitted to the control terminals of the multiple UAVs to execute the flight mission in the predetermined time zone; that is, potential obstacles can be effectively avoided by predicting the movement trajectory of obstacles. At the same time, the optimal flight plan is determined by overall optimization of the flight parameters of multiple UAVs, which can significantly improve the operating efficiency of UAVs in the airspace while ensuring the flight safety of UAVs, thereby realizing efficient task execution of collaborative operations of multiple UAVs. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of the structure of a traffic control system based on the safety of UAV operation provided by the present invention;

[0011] Figure 2 A schematic diagram of a process for obtaining route dispersion in a traffic control system based on the safety of UAV operation provided by the present invention;

[0012] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention;

[0013] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0014] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0015] Route dispersion analysis module 01, flight information reading module 02, obstacle coverage acquisition module 03, flight plan optimization module 04, flight mission execution module 05, electronic device 500, memory 510, processor 520, first computer program 511, computer readable storage medium 600, second computer program 611. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0018] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0019] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a traffic control system based on the safety of drone operation. The system includes a traffic control platform, and the traffic control platform is communicatively connected with the drone control terminal, including:

[0020] The route dispersion analysis module 01 is used to read the number of drones and the scheduled flight route set in the target airspace in real time within the traffic control platform. If the number of drones is greater than a predetermined scalar, three-dimensional mapping and dispersion analysis are performed on the scheduled flight route set to obtain the route dispersion.

[0021] Specifically, an embodiment of the present invention provides a traffic control system based on the safety of drone operation, which aims to achieve safe coordinated flight and efficient task execution of drones in complex airspace. The system includes a traffic control platform, which is communicated with the control terminals of multiple drones to ensure real-time information sharing and dynamic path optimization and adjustment. Among them, the traffic control platform serves as the core control unit of the system, and realizes coordinated management and path optimization of multiple drones by real-time receiving, processing and analyzing the flight data and airspace environment information of the drones; the drone control terminal is communicated with the traffic control platform to execute platform instructions to ensure that the drone can perform tasks quickly and safely according to the guidance of the traffic control platform.

[0022] In the traffic control platform, the number of drones and the scheduled flight route set in the target airspace are read in real time. The traffic control platform will regularly monitor the status information of drones in the target airspace, including the current position, flight direction and mission status of each drone, and obtain the scheduled flight route set of each drone, and record the path coordinates of all drones' planned flights. Then the platform will compare the number of drones obtained with the predetermined scalar (safe flight number threshold). When the number of drones in the airspace exceeds the threshold, the system will consider that the current airspace density is high, which may cause flight safety hazards, and further route dispersion analysis is required. Then, the platform performs three-dimensional spatial mapping on the scheduled flight route set of all drones, and displays the routes in a three-dimensional coordinate system to reflect the distribution of routes at different heights and directions. Further, based on the three-dimensional mapping, the platform analyzes the dispersion of the route set, evaluates the spatial distribution of each route, and obtains the route dispersion. The larger the dispersion, the more uniform the route, the smaller the collision probability, and the higher the flight safety.

[0023] In one embodiment, Figure 2 As shown, the present invention also includes:

[0024] A three-dimensional mapping space of the target area is constructed, and the scheduled flight route set is respectively arranged in the three-dimensional mapping space; in the three-dimensional mapping space, the relative distances of any two scheduled flight routes in the scheduled flight route set are respectively calculated, and the total relative distance is obtained by summing them up; and the route discreteness is obtained according to the total relative distance mapping using a distance-discrepancy comparison table, wherein the route discreteness is positively correlated with the total relative distance.

[0025] Specifically, first, a three-dimensional mapping space of the target area is constructed, that is, the target area is divided according to a three-dimensional coordinate system, and the range and resolution of the coordinate axis are defined to accurately represent the flight path of the UAV at different heights and directions. Then, the predetermined flight route set is input into the three-dimensional mapping space for distribution, and the flight route of each UAV is located, including the flight altitude, position coordinates and direction of each route. Then, in the three-dimensional mapping space, for any two predetermined flight routes in the route set, the relative distance in space is calculated. For example, for two routes, their key path points (such as starting point, end point, intermediate node) can be selected for distance measurement, and the relative distances of all route pairs in the route set are further calculated one by one, and these distances are summed to obtain the total relative distance.

[0026] Construct a distance-dispersion comparison table, which corresponds to the dispersion value according to different total relative distances. The data in the table can be obtained through empirical data or simulation experiments to reflect the route discreteness under different relative distances. Then, according to the calculated total relative distance, the corresponding dispersion value is found in the distance-dispersion comparison table, and the route discreteness is mapped. The route discreteness is positively correlated with the total relative distance, that is, the larger the total relative distance, the larger the route discreteness, the more uniform the route distribution, and the higher the flight safety. By decomposing the complex multi-route spatial distribution problem into three-dimensional mapping, relative distance calculation, and comparison table mapping steps for discreteness calculation, efficient and accurate discreteness evaluation can be achieved, and the convenience and efficiency of discreteness calculation can be improved.

[0027] The flight information reading module 02 is used to read the flight obstacle information of the target airspace and the flight characteristic information of the UAV if the route discreteness is less than the expected discreteness index, wherein the flight characteristic information includes the mission priority and the flight safety barrier.

[0028] Specifically, when the route discreteness is less than the expected discreteness index, indicating that the routes of drones in the current airspace are too dense and there is a potential collision risk, the flight obstacle information of the target airspace and the flight characteristic information of multiple drones are read, wherein the flight obstacle information includes the position, speed, size and direction of obstacles, such as flying birds; the flight characteristic information includes mission priority and flight safety barrier. Mission priority refers to the mission priority information of each drone, which is used to determine its priority in airspace management. For example, high-priority tasks (such as emergency rescue and distribution of important materials) should be allocated the best path and resources first to ensure the smooth completion of the mission; the flight safety barrier refers to the flight safety barrier of each drone (i.e., the safety range of the drone), which represents the safety space required for it during flight. The safety barrier is a protection range used to ensure that there is no interference from other objects within the range to prevent the risk of collision due to too close flight paths or obstacles. The flight safety barrier can be used to adjust the relative distance and path between drones to ensure that each drone operates within a safe range.

[0029] The obstacle coverage range acquisition module 03 is used to predict the flight obstacle information through an obstacle movement predictor to obtain the obstacle coverage range of a predetermined time zone.

[0030] In one embodiment, the present invention further comprises:

[0031] Acquire flight obstacle information and flight environment information, wherein the flight obstacle information includes obstacle type, current position, flight speed and flight direction, and the flight environment information includes wind force and wind direction; input the obstacle type, current position, flight speed, flight direction wind force and wind direction into the obstacle movement predictor, perform obstacle movement trajectory prediction in a predetermined time zone, and output the obstacle coverage range, wherein the obstacle movement predictor is constructed based on a long short-term memory network.

[0032] Specifically, flight obstacle information and flight environment information are obtained, wherein the flight obstacle information includes obstacle type (flying birds, etc.), current position (such as latitude and longitude and altitude), flight speed and flight direction; the flight environment information includes wind force and wind direction; the flight environment information is used to describe the meteorological conditions in the airspace, which have a significant impact on the movement trajectory of obstacles. The magnitude of the wind speed directly affects the movement speed of the obstacle. For example, in a high wind speed environment, lightweight or suspended obstacles (such as flying birds, unmanned balloons, etc.) are more easily driven by wind, resulting in rapid movement or irregular deviation; the wind direction determines the force direction of the obstacle, and the trajectory change of the obstacle will have a directional deviation with different wind directions, for example, the speed increases with the wind and slows down against the wind.

[0033] Firstly, an obstacle movement predictor is constructed based on a long short-term memory network, wherein the obstacle movement predictor includes an input layer, an LSTM layer, a fully connected layer and an output layer. The input layer is used to input the time series into the LSTM model, and the input features include obstacle type, current position, flight speed, flight direction, wind force and wind direction; the LSTM layer is used to capture the movement law of obstacles, and multi-layer LSTM units can be used to improve the memory capacity and prediction accuracy of the model. Each LSTM unit can memorize the obstacle state at the previous moment and predict the position at the next moment in combination with the input at the current moment; a fully connected layer is added after the LSTM layer to map the output of the LSTM to the future position coordinates (such as longitude, latitude and altitude); the output layer is used to output the prediction results and generate the movement trajectory of the obstacle in the future time zone, including a series of predicted position points. Then, historical obstacle motion data is used for training, including the motion trajectories of different types of obstacles under different environmental conditions. These historical data can help the model learn the movement patterns of obstacles under specific conditions. Appropriate loss functions (such as mean square error) and optimizers (such as Adam optimizer) are selected to minimize the prediction error, so that the model outputs more accurate obstacle position predictions. A trained obstacle movement predictor is obtained.

[0034] Finally, the obstacle type, current position, flight speed, wind force and direction in the flight direction are input into the obstacle movement predictor to predict the obstacle movement trajectory in the predetermined time zone. The model generates the obstacle trajectory in the future time zone based on the real-time input and the learned motion pattern. These trajectory points form the expected movement path of the obstacle in the future time zone; further, based on the predicted trajectory points, the obstacle coverage is generated. The coverage can be determined based on the obstacle size, speed and prediction uncertainty, and is used for safe obstacle avoidance decisions of the drone. By constructing an obstacle movement predictor based on the long short-term memory network, it is possible to accurately predict the future obstacle trajectory, provide accurate obstacle coverage, and provide reliable obstacle avoidance information for the drone's path planning, effectively improving flight safety and mission efficiency.

[0035] The flight plan optimization module 04 is used to take avoiding the obstacle coverage range and satisfying the flight safety barrier as optimization constraints, use the task execution evaluation function, based on the route discreteness and task priority, perform overall optimization of the flight parameters of multiple UAVs, and generate an optimal flight plan, wherein the optimal flight plan includes multiple optimal flight parameters.

[0036] In one embodiment, the present invention further comprises:

[0037] Acquire multiple flight parameter adjustment spaces of multiple UAVs, wherein the flight parameter adjustment space includes a route parameter adjustment space and a speed parameter adjustment space, the route parameters include a waypoint sequence and a flight altitude, and the speed parameters include a horizontal flight speed, a vertical flight speed and a flight acceleration; simulate and construct a UAV flight simulation space, and in the flight simulation space, take avoiding the obstacle coverage range and satisfying the flight safety barrier as optimization constraints, use a task execution evaluation function, based on the route discreteness and task priority, and according to the multiple flight parameter adjustment spaces, perform overall optimization of the flight parameters of the multiple UAVs, and output the optimal flight plan.

[0038] Specifically, first, multiple flight parameter adjustment spaces of multiple drones are obtained, wherein the flight parameter adjustment space includes a route parameter adjustment space and a speed parameter adjustment space, the route parameters include a waypoint sequence and a flight altitude, the speed parameters include a horizontal flight speed, a vertical flight speed and a flight acceleration, and the route parameter adjustment space is used to adjust the flight path of the drone, including the waypoint sequence and the flight altitude. This space can flexibly modify the flight route and altitude of the drone to avoid obstacles, reduce route conflicts and ensure safety; the speed parameter adjustment space is used to control the flight speed and acceleration of the drone, ensuring that the drone can quickly respond and adjust the speed according to the mission requirements and the flight environment, and improve flight efficiency and stability.

[0039] A simulation space is created to represent the flight area of ​​the UAV with a virtual three-dimensional coordinate system, including information such as the type, location, and size of obstacles, to simulate the real environment in the airspace; and in the simulation space, the obstacle coverage is generated according to the prediction results of the motion trajectory of the obstacle, and the coverage area is dynamically updated, so that the UAV can avoid potential obstacles more accurately in flight path planning; at the same time, a flight safety barrier (i.e., a safety range) is set for each UAV to ensure that when the UAV flies in the simulation space, no other objects or UAVs will enter within the respective safety barrier range to reduce the risk of collision. Then, in the flight simulation space, avoiding the obstacle coverage range and satisfying the flight safety barrier are optimization constraints, that is, the flight path of the UAV must avoid entering the obstacle coverage range. If the path inevitably passes through the obstacle area, the flight altitude, speed, or route must be adjusted in advance; at the same time, no other UAVs or objects should interfere within the flight safety barrier range of each UAV to ensure flight stability and safety; using the task execution evaluation function, based on the route discreteness and task priority, the space is adjusted according to the multiple flight parameters, and the overall optimization of the flight parameters of multiple UAVs is performed to output the optimal flight plan.

[0040] In one embodiment, the present invention further comprises:

[0041] Setting an optimization step length based on the route dispersion, wherein the optimization step length is positively correlated with the route dispersion;

[0042] Specifically, in an embodiment of the present invention, in order to achieve efficient multi-UAV collaborative flight optimization, the optimization step length is set based on the route discreteness, and the positive correlation between the route discreteness and the optimization step length is used to achieve more flexible parameter adjustment and path optimization. Among them, the optimization step length means that when adjusting flight parameters and optimizing paths, the amplitude of each adjustment, such as the offset of the route, the increase or decrease range of the flight altitude, the amplitude of the speed adjustment, etc., are all determined by the optimization step length, and the optimization step length is positively correlated with the route discreteness, that is, the larger the route discreteness, the more uniform the route distribution, the safer the airspace, and a larger step length can be used for optimization; when the discreteness is small, a smaller step length is used to more finely optimize the route and parameter configuration.

[0043] Based on the task priorities, a task execution evaluation function is constructed with the purpose of optimizing the overall flight efficiency and route dispersion;

[0044] In one embodiment, the present invention further comprises:

[0045] The expression of the task execution evaluation function is: ;in, is the flight fitness of the ith flight plan, is the flight efficiency weight, is the route dispersion weight, is the distance weight of the nth UAV, is positively correlated with the task priority, is the number of drones, is the simulated flight distance of the nth UAV in the ith flight plan, is the simulated route dispersion of the ith flight plan.

[0046] Specifically, a task execution evaluation function is constructed, which is used to comprehensively consider task priority, flight efficiency and route dispersion to obtain the optimal flight parameter combination, thereby meeting the needs of different tasks and optimizing airspace management. In the task execution evaluation function, is the flight fitness of the ith flight plan, where the higher the fitness, the more the plan meets the optimization goal, that is, the better the overall flight effect; is the flight efficiency weight, which is used to measure the importance of flight efficiency in the entire optimization. The larger the weight, the higher the priority of flight efficiency. is the route dispersion weight, which is used to measure the importance of route dispersion in optimization. A larger weight means a higher requirement for the uniformity of route distribution; is the distance weight of the nth UAV, It is positively correlated with the mission priority, that is, the higher the mission priority, the greater the distance weight, so as to ensure that the UAV mission with high priority is given priority; is the number of drones, is the simulated flight distance of the nth UAV in the ith flight plan, where the longer the simulated flight distance in the same time, the higher the flight efficiency; is the simulated route dispersion of the ith flight plan, which is used to represent the route distribution of the UAV in the plan. The larger the dispersion, the more uniform the route distribution and the lower the collision risk.

[0047] Randomly generate a plurality of initial flight plans in the plurality of flight parameter adjustment spaces, input the plurality of initial flight plans into the flight simulation space to execute the flight simulation of the predetermined time zone, and output a plurality of simulated flight distance sets and a plurality of simulated flight route sets; perform route dispersion analysis on the plurality of simulated flight route sets to determine a plurality of simulated route dispersions, and perform flight fitness evaluation on the plurality of simulated flight distance sets and the plurality of simulated route dispersions using the task execution evaluation function to determine a plurality of flight fitnesses;

[0048] Specifically, in the flight parameter adjustment space, a random number generator is used to generate multiple initial flight plans for each drone, each of which contains complete flight paths, speed and acceleration parameters. For example, in the route parameter adjustment space, a set of waypoint sequences is randomly selected, each waypoint is a three-dimensional coordinate (including longitude, latitude and altitude) to ensure that the path is valid within the airspace. The waypoint sequence can be generated based on the starting point, the end point and a series of intermediate points to meet the mission area coverage requirements; in the flight altitude adjustment space, a flight altitude is randomly assigned to each drone. Different altitude layers help reduce route crossings and improve the vertical distribution uniformity of the airspace; within the adjustment range of horizontal flight speed and vertical flight speed, a speed value is randomly generated for each drone. The random distribution of speed can ensure the relative speed difference between drones, which helps to reduce congestion; in the acceleration adjustment space, the acceleration value is randomly selected. The setting of acceleration enables the drone to flexibly respond to changes in the flight environment, especially in obstacle avoidance and speed adjustment. Through the randomization method, multiple different initial flight plans are generated for each drone, and then the initial flight plans of each drone are combined into different overall flight plans to obtain multiple initial flight plans.

[0049] Then, the multiple initial flight plans are input into the flight simulation space to perform the flight simulation of the predetermined time zone, that is, in the flight simulation space, the flight situation of each initial plan in the predetermined time zone is simulated, and each plan generates a corresponding flight trajectory and flight distance during the flight simulation process, and obtains multiple simulated flight distance sets and multiple simulated flight route sets. Then, the route dispersion analysis is performed on the multiple simulated flight route sets, that is, a three-dimensional dispersion analysis is performed on each simulated flight route set, and the distribution uniformity between the UAV routes is calculated. The route dispersion is used to evaluate the relative distance and distribution between the routes. A larger dispersion value indicates that the routes are evenly distributed, and the risk of collision and interference is low, and multiple simulated route dispersions are determined. Finally, the task execution evaluation function is used to evaluate the flight fitness of the multiple simulated flight distance sets and the multiple simulated route dispersions, and multiple flight fitnesses are determined.

[0050] Based on the multiple flight fitnesses, overall optimization of flight parameters is performed according to the optimization step length, and the optimal flight plan is output.

[0051] In one embodiment, the present invention further comprises:

[0052] The initial flight plan is set as the initial solution. Based on the multiple flight fitnesses, the multiple initial solutions are arranged in descending order of fitness to generate an initial solution sequence; the first Q solutions of the initial solution sequence are set as optimal solutions, and the remaining P solutions are set as inferior solutions, wherein P is an integer multiple of Q and P is much larger than Q; the P inferior solutions are randomly clustered with the Q optimal solutions to determine Q solution thresholds, wherein the number of inferior solutions in each solution threshold is the same; within the Q solution thresholds, the optimal solution is used as the optimization direction, and the inferior solution is adjusted according to the optimization step length to obtain Q updated solution thresholds, wherein if the updated inferior solution does not satisfy the multiple flight parameter adjustment spaces, the current update is not performed; based on the Q updated solution thresholds, the overall optimization of the flight parameters continues to be performed until convergence, and the optimal flight plan is output.

[0053] Specifically, first, the initial flight plan is set as the initial solution. Based on the multiple flight fitnesses, the multiple initial solutions are arranged from large to small according to the fitness, that is, the higher the fitness of the solution, the higher the ranking in the sequence, and the initial solution sequence is constructed. Then, the first Q solutions with high fitness ranking in the initial solution sequence are set as optimal solutions. The optimal solution is the solution with higher fitness at present, which is usually more in line with the optimization goals such as task efficiency, route discreteness and task priority; the remaining P solutions in the initial solution sequence are set as inferior solutions, that is, solutions with lower fitness. The inferior solution part is used to retain a certain diversity of solution space as the improvement object in the subsequent optimization process, where P is an integer multiple of Q, and P is much larger than Q. By dividing the initial solution sequence into two parts, the optimal solution and the inferior solution, the system can more efficiently focus on the optimization of high fitness solutions while retaining a certain solution space to maintain diversity.

[0054] Then, the P inferior solutions are randomly clustered with Q superior solutions, that is, the P inferior solutions are randomly assigned to the Q superior solutions to form Q solution thresholds, so that the number of inferior solutions in each solution threshold is the same, and each solution threshold contains one superior solution and several inferior solutions. Then, within the Q solution thresholds, the superior solution is used as the optimization direction, and the inferior solutions are adjusted according to the optimization step length to obtain Q updated solution thresholds, that is, in each solution threshold, the flight parameters of the superior solution are used as the target direction, and the parameters of the inferior solution are adjusted to gradually approach the direction of the superior solution; according to the set optimization step length, each inferior solution within the solution threshold is slightly adjusted. The adjustment content includes flight parameters such as flight path, speed, acceleration, etc.; in the adjusted solution threshold, the parameters of the inferior solution are closer to the direction of the optimal solution, and the inferior solution within each solution threshold has been improved in the direction of optimization; wherein, each time the inferior solution is adjusted, check whether the updated inferior solution meets the constraints of the flight parameter adjustment space (such as path range, speed limit, etc.). If the adjusted inferior solution does not meet the constraints of the parameter space, cancel the update and keep the original inferior solution parameter value unchanged. This rule ensures that the inferior solution will not exceed the flight restriction conditions due to adjustment, ensuring the legality and safety of the solution. Finally, based on the Q updated solution thresholds, continue to perform the overall optimization of the flight parameters until convergence, and output the optimal flight plan.

[0055] In one embodiment, the present invention further comprises:

[0056] Identify the Q update solution thresholds, and if within the same update solution threshold, the fitness of the inferior solution is greater than the fitness of the superior solution, replace the superior solution with the inferior solution, wherein the fitness of the updated inferior solution is calculated using the task execution evaluation function; continue to perform iterative optimization of the flight parameters until a predetermined number of optimizations is reached, output Q current update solution thresholds, select the solution threshold with the largest overall fitness among the Q current update solution thresholds as the optimal solution threshold, and select the superior solution of the optimal solution threshold as the optimal flight plan.

[0057] Specifically, first, the fitness of the updated inferior solution is calculated using the task execution evaluation function to obtain the fitness of multiple updated inferior solutions; then the Q update solution thresholds are identified, and the fitness of the inferior solution and the optimal solution are compared within the same update solution threshold. If the fitness of a certain inferior solution is higher than that of the optimal solution, the current optimal solution is replaced and the inferior solution is used as the new optimal solution. Then, using the same method, in the new updated solution threshold, with the current optimal solution as the direction, continue to fine-tune and optimize the inferior solution according to the optimization step size, so that the inferior solution is closer to the optimal solution; after each iteration, recalculate the fitness of all inferior solutions in the updated solution threshold to evaluate the adjustment effect and ensure that the inferior solution gradually converges to the optimal solution; repeat the above iterative adjustment process until the predetermined number of optimization searches is reached to ensure that a better solution is obtained within a limited number of iterations; output Q current updated solution thresholds, each solution threshold contains the final adjusted optimal solution and inferior solution; for each current updated solution threshold, calculate its overall fitness value to determine which solution threshold has the highest fitness; then select the solution threshold with the largest overall fitness among the Q current updated solution thresholds as the optimal solution threshold, and select the optimal solution of the optimal solution threshold as the optimal flight plan.

[0058] The flight mission execution module 05 is used to transmit the multiple optimal flight parameter mappings to the control terminals of the multiple UAVs to execute the flight mission in the predetermined time zone.

[0059] Specifically, the optimal flight plan includes multiple optimal flight parameters, and then the multiple optimal flight parameters are mapped and transmitted to the control terminals of the multiple UAVs, that is, for the independent control terminal of each UAV, the corresponding optimal flight parameters are transmitted to the terminal to ensure that each UAV can receive personalized flight parameters that meet its mission requirements; finally, according to the optimal flight parameters, the multiple UAVs are controlled to perform the flight mission in the predetermined time zone.

[0060] The traffic control system based on the safety of drone operation provided by the embodiment of the present invention has at least the following technical effects:

[0061] The number of drones and the scheduled flight route set in the target airspace are read in real time in the traffic control platform. If the number of drones is greater than the predetermined scalar, the scheduled flight route set is subjected to three-dimensional mapping and discreteness analysis to obtain the route discreteness; if the route discreteness is less than the expected discreteness index, the flight obstacle information of the target airspace and the flight feature information of the drones are read, wherein the flight feature information includes the mission priority and the flight safety barrier; the flight obstacle information is predicted by the obstacle movement predictor to obtain the obstacle coverage range of the predetermined time zone; with avoiding the obstacle coverage range and satisfying the flight safety barrier as the optimization constraints, the task execution evaluation is used to calculate the flight obstacle information. A cost function is used to perform overall optimization of flight parameters of multiple UAVs based on the route discreteness and task priority to generate an optimal flight plan, wherein the optimal flight plan includes multiple optimal flight parameters; the multiple optimal flight parameters are mapped and transmitted to the control terminals of the multiple UAVs to perform the flight mission in the predetermined time zone; that is, potential obstacles can be effectively avoided by predicting the movement trajectory of obstacles. At the same time, the optimal flight plan can be determined by overall optimization of flight parameters of multiple UAVs, which can significantly improve the operating efficiency of UAVs in the airspace under the premise of ensuring the flight safety of UAVs, thereby realizing efficient task execution of collaborative operations of multiple UAVs.

[0062] For example 2, please refer to Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, it is used to implement the traffic control system based on drone operation safety described in the above-mentioned embodiment 1.

[0063] For example 3, please refer to Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, it is used to implement the traffic control system based on drone operation safety described in the above-mentioned embodiment 1.

[0064] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0065] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce 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.

[0067] 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.

[0068] 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.

[0069] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0070] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A traffic control system based on the safety of drone operation, characterized in that: The system includes a traffic control platform, which is communicatively connected to a drone control terminal, including: The route dispersion analysis module is used to read the number of drones and the scheduled flight route set in the target airspace in real time in the traffic control platform. If the number of drones is greater than a predetermined scalar, the scheduled flight route set is subjected to three-dimensional mapping and dispersion analysis to obtain the route dispersion; A flight information reading module, used for reading the flight obstacle information of the target airspace and the flight characteristic information of the UAV if the route discreteness is less than the expected discreteness index, wherein the flight characteristic information includes the mission priority and the flight safety barrier; An obstacle coverage range acquisition module is used to predict the flight obstacle information through an obstacle movement predictor to obtain the obstacle coverage range of a predetermined time zone; A flight plan optimization module is used to perform overall optimization of flight parameters of multiple UAVs based on the route discreteness and task priority, taking avoiding the obstacle coverage range and satisfying the flight safety barrier as optimization constraints, and generating an optimal flight plan by using a task execution evaluation function, wherein the optimal flight plan includes multiple optimal flight parameters; A flight mission execution module, used for transmitting the plurality of optimal flight parameter mappings to the control terminals of the plurality of UAVs to execute the flight mission in the predetermined time zone; The optimization constraints of avoiding the obstacle coverage and satisfying the flight safety barrier are used, and the task execution evaluation function is used to perform overall optimization of the flight parameters of multiple UAVs based on the route discreteness and task priority to generate the optimal flight plan, including: Acquire multiple flight parameter adjustment spaces of multiple drones, wherein the flight parameter adjustment space includes a route parameter adjustment space and a speed parameter adjustment space, the route parameter includes a waypoint sequence and a flight altitude, and the speed parameter includes a horizontal flight speed, a vertical flight speed, and a flight acceleration; Simulate and construct a UAV flight simulation space, and in the flight simulation space, take avoiding the obstacle coverage and satisfying the flight safety barrier as optimization constraints, use a task execution evaluation function, based on the route discreteness and task priority, adjust the space according to the multiple flight parameters, perform overall optimization of the flight parameters of multiple UAVs, and output the optimal flight plan; Among them, using the task execution evaluation function, based on the route discreteness and task priority, and according to the multiple flight parameter adjustment spaces, performing overall optimization of the flight parameters of multiple UAVs, includes: Setting an optimization step length based on the route dispersion, wherein the optimization step length is positively correlated with the route dispersion; Based on the task priorities, a task execution evaluation function is constructed with the purpose of optimizing the overall flight efficiency and route dispersion; Randomly generate a plurality of initial flight plans in the plurality of flight parameter adjustment spaces, input the plurality of initial flight plans into the flight simulation space to execute the flight simulation of the predetermined time zone, and output a plurality of simulated flight distance sets and a plurality of simulated flight route sets; Performing route dispersion analysis on the multiple simulated flight route sets to determine multiple simulated route dispersions, and performing flight fitness evaluation on the multiple simulated flight distance sets and multiple simulated route dispersions using the task execution evaluation function to determine multiple flight fitnesses; Based on the multiple flight fitnesses, overall optimization of flight parameters is performed according to the optimization step length, and the optimal flight plan is output.

2. The traffic control system based on the safety of drone operation according to claim 1 is characterized in that: Performing three-dimensional mapping and dispersion analysis on the predetermined flight route set to obtain route dispersion includes: Constructing a three-dimensional mapping space of the target area, and arranging the predetermined flight route sets in the three-dimensional mapping space respectively; In the three-dimensional mapping space, respectively calculating the relative distances between any two scheduled flight routes in the scheduled flight route set, and summing them up to obtain a total relative distance; The route dispersion is obtained according to the total relative distance mapping by using a distance-dispersion comparison table, wherein the route dispersion is positively correlated with the total relative distance.

3. The traffic control system based on the safety of drone operation according to claim 1 is characterized in that: The flight obstacle information is predicted by an obstacle movement predictor to obtain an obstacle coverage range in a predetermined time zone, including: Acquiring flight obstacle information and flight environment information, wherein the flight obstacle information includes obstacle type, current position, flight speed and flight direction, and the flight environment information includes wind force and wind direction; The obstacle type, current position, flight speed, flight direction wind force and wind direction are input into the obstacle movement predictor, obstacle movement trajectory prediction is performed in a predetermined time zone, and the obstacle coverage range is output, wherein the obstacle movement predictor is constructed based on a long short-term memory network.

4. The traffic control system based on the safety of drone operation according to claim 1 is characterized in that: The expression of the task execution evaluation function is: ； in, is the flight fitness of the ith flight plan, is the flight efficiency weight, is the route dispersion weight, is the distance weight of the nth UAV, is positively correlated with the task priority, is the number of drones, is the simulated flight distance of the nth UAV in the ith flight plan, is the simulated route dispersion of the ith flight plan.

5. The traffic control system based on the safety of drone operation according to claim 1 is characterized in that: Based on the multiple flight fitnesses, performing overall optimization of flight parameters according to the optimization step length, and outputting the optimal flight plan, including: The initial flight plan is set as an initial solution, and based on the multiple flight fitnesses, the multiple initial solutions are arranged in descending order of fitness to generate an initial solution sequence; The first Q solutions of the initial solution sequence are set as optimal solutions, and the remaining P solutions are set as inferior solutions, where P is an integer multiple of Q and P is much larger than Q; Randomly cluster P inferior solutions with Q superior solutions to determine Q solution thresholds, where the number of inferior solutions in each solution threshold is the same; Within the Q solution thresholds, taking the best solution as the optimization direction, adjusting the inferior solution according to the optimization step length, and obtaining Q updated solution thresholds, wherein if the updated inferior solution does not satisfy the multiple flight parameter adjustment spaces, then this update is not performed; Based on the Q updated solution thresholds, the overall optimization of the flight parameters is continued until convergence, and the optimal flight plan is output.

6. The traffic control system based on the safety of drone operation according to claim 5 is characterized in that: Based on the Q updated solution thresholds, the overall optimization of flight parameters is continued, including: Identify the Q update solution thresholds, and if within the same update solution threshold, the fitness of the inferior solution is greater than the fitness of the superior solution, replace the superior solution with the inferior solution, wherein the fitness of the updated inferior solution is calculated using the task execution evaluation function; Continue to perform iterative optimization of the flight parameters until a predetermined number of optimization times is reached, output Q current updated solution thresholds, select the solution threshold with the largest overall fitness among the Q current updated solution thresholds as the optimal solution threshold, and select the optimal solution of the optimal solution threshold as the optimal flight plan.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the traffic control system based on the safety of drone operation as described in any one of claims 1 to 6.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements a traffic control system based on drone operation safety as described in any one of claims 1 to 6.

Images