Near space unmanned aerial vehicle launching trajectory optimization method and device, equipment and storage medium

Abstract

The invention discloses a near space unmanned aerial vehicle launch trajectory optimization method, device and equipment and a storage medium, and the method comprises the steps: determining a take-off point and a target launch point of an unmanned aerial vehicle according to a launch task when the launch task is received; constructing a motion model of the unmanned aerial vehicle, and constructing a target function corresponding to the launching trajectory of the unmanned aerial vehicle and a plurality of constraint conditions based on the motion model of the unmanned aerial vehicle; constructing a putting trajectory planning problem model based on the objective function and a plurality of constraint conditions; based on the take-off point, the target delivery point and the delivery trajectory planning problem model, performing optimization solution on the delivery trajectory to obtain an optimal delivery trajectory; the unmanned aerial vehicle is controlled to be launched in the near space according to the optimal launch trajectory, and the optimal launch trajectory is optimized and solved under the target function corresponding to the launch trajectory of the unmanned aerial vehicle and multiple constraint conditions, so that efficient trajectory optimization of the unmanned aerial vehicle in the near space under the multiple constraint conditions is realized; and the launching efficiency of the unmanned aerial vehicle and the task execution success rate can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of drone trajectory optimization, and in particular to a method, device, equipment, and storage medium for optimizing the delivery trajectory of a near-space drone. Background Art

[0002] With the rapid development of drone technology, near-space UAVs (N-Space UAVs) are increasingly being used in military, scientific research, emergency rescue, environmental monitoring, and other fields. Near-space UAVs typically fly between the ground and the edge of the atmosphere, facing complex environments and variable weather conditions. This places higher demands on UAV trajectory planning and optimization.

[0003] Most traditional trajectory optimization methods only consider a single objective function or relatively simplified constraints, resulting in poor trajectory optimization efficiency and effect. They cannot meet the needs of drone deployment in complex environments, which in turn affects the efficiency and safety of drone mission execution. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, equipment and storage medium for optimizing the delivery trajectory of near-space drones, aiming to solve the technical problem that traditional trajectory optimization methods have poor trajectory optimization efficiency and effect, cannot meet the delivery needs of drones in complex environments, and thus affect the efficiency and safety of drone mission execution.

[0005] To achieve the above objectives, the present application proposes a method for optimizing the delivery trajectory of a near-space UAV, which comprises:

[0006] Upon receiving a delivery mission, determining the take-off point and target delivery point of the drone according to the delivery mission;

[0007] Constructing a motion model of the UAV, and constructing an objective function and multiple constraints corresponding to the UAV's delivery trajectory based on the UAV's motion model;

[0008] Constructing a delivery trajectory planning problem model based on the objective function and the plurality of constraints;

[0009] Optimizing and solving the delivery trajectory based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain an optimal delivery trajectory;

[0010] Control the drone to deliver the payload in near space according to the optimal delivery trajectory.

[0011] In one embodiment, the step of constructing a motion model of the drone and constructing an objective function and multiple constraints corresponding to the drone's delivery trajectory based on the motion model of the drone includes:

[0012] Construct the UAV motion model based on the UAV's dynamic characteristics and kinematic equations;

[0013] determining flight parameters of the UAV based on the motion model of the UAV;

[0014] Constructing a plurality of constraints based on the flight parameters of the UAV, wherein the constraints include speed constraints, acceleration constraints, no-fly zone constraints, obstacle avoidance constraints, flight area boundary constraints, battery energy limits, and mission time limits;

[0015] With the goal of minimizing the total flight time, energy consumption, path length, and trajectory smoothness, the objective function corresponding to the UAV delivery trajectory is constructed. The formula of the objective function is:

[0016]

[0017] Among them, J is the objective function, α1, α2, α3 and α4 are weight coefficients used to balance the relative importance of each goal, t0 is the take-off time, t f is the task completion time, P(t) is the power consumption at time t, is the speed of the UAV at time t, A(t) is the acceleration of the UAV at time t, Indicates the change in acceleration.

[0018] In one embodiment, the delivery trajectory planning problem model is:

[0019]

[0020] A min ≤A(t)≤A max

[0021]

[0022] ||p(t)-O i ||≥d safe

[0023] p(t)∈Flight Area

[0024] E(t)≤E max

[0025] T arrive ≤T dealine

[0026] Among them, v min is the minimum speed limit of the drone, v max is the maximum speed limit of the drone, A minis the minimum acceleration limit of the drone, A max is the maximum acceleration limit of the UAV, p(t) is the position of the UAV at time t, No-flyzone is the no-fly zone, O i is the position of the i-th obstacle, d safe is the safety distance, Flight Area is the flight area, E(t) is the remaining battery energy of the drone at time t, and E max is the maximum energy limit of the drone battery, T arrive is the time it takes for the UAV to arrive at the target delivery point, T dealine The time deadline for the task.

[0027] In one embodiment, optimizing and solving the delivery trajectory based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain the optimal delivery trajectory includes:

[0028] Performing path planning based on the take-off point and the target delivery point to generate an initial delivery trajectory;

[0029] Optimizing the initial delivery trajectory through the delivery trajectory planning problem model to obtain multiple candidate delivery trajectories;

[0030] Evaluate multiple candidate delivery trajectories and obtain evaluation results;

[0031] An optimal delivery trajectory is selected from the plurality of candidate delivery trajectories according to the evaluation result, wherein the optimal delivery trajectory minimizes the objective function while satisfying all constraints.

[0032] In one embodiment, the initial delivery trajectory is optimized using the delivery trajectory planning problem model to obtain multiple candidate delivery trajectories, including:

[0033] Set the initial temperature, cooling rate and end temperature;

[0034] At the current temperature, the initial delivery trajectory is used as the current solution;

[0035] Calculating based on the objective function in the delivery trajectory planning problem model and the current solution to obtain a fitness value of the current solution;

[0036] Randomly generate a new solution in the neighborhood of the current solution and calculate the fitness value of the new solution;

[0037] If the fitness value of the new solution is better than the fitness value of the current solution, the new solution is accepted as the current solution;

[0038] If the fitness value of the new solution is not better than the fitness value of the current solution, the new solution is accepted as the current solution with a preset probability, where the acceptance probability decreases as the temperature decreases;

[0039] The steps of randomly generating a new solution in the neighborhood of the current solution and calculating the fitness value of the new solution are re-executed until the number of iterations at the current temperature is reached or the current solution has not been improved within a certain number of times, the current temperature is lowered, the lowered temperature is used as the current temperature, and the step of using the initial delivery trajectory as the current solution at the current temperature is re-executed until the current temperature is lowered below the termination temperature, and multiple candidate delivery trajectories are output.

[0040] In one embodiment, the evaluating of the plurality of candidate delivery trajectories to obtain the evaluation result includes:

[0041] Simulate multiple candidate delivery trajectories to obtain performance data for each candidate delivery trajectory in an actual flight environment;

[0042] Calculating the objective function value corresponding to each candidate delivery trajectory based on the performance data;

[0043] Based on the objective function value and the satisfaction of the constraint conditions, each candidate delivery trajectory is scored to obtain an evaluation result, wherein a candidate delivery trajectory with a higher score indicates better performance in the actual flight environment.

[0044] In one embodiment, after controlling the drone to be delivered in near space according to the optimal delivery trajectory, the method further includes:

[0045] Obtain the real-time position and speed of the drone as well as the reference position and speed of the corresponding point on the optimal trajectory;

[0046] Determine a position deviation and a speed deviation according to the real-time position, the real-time speed, the reference position, and the reference speed;

[0047] The position deviation and the speed deviation are used as inputs of a PID controller, and a control instruction is output to adjust the flight state of the UAV so that the UAV flies along the optimal trajectory. The parameters of the PID controller include a proportional coefficient Kp, an integral coefficient Ki, and a differential coefficient Kd. The flight state of the UAV is controlled by adjusting the proportional coefficient Kp, the integral coefficient Ki, and the differential coefficient Kd. The proportional coefficient Kp is used to control the influence of the current deviation on the control instruction, the integral coefficient Ki is used to eliminate static deviation, and the differential coefficient Kd is used to predict the change trend of the future deviation and make adjustments in advance.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a near-space UAV delivery trajectory optimization device, the near-space UAV delivery trajectory optimization device comprising:

[0049] A determination module is used to determine the take-off point and target delivery point of the UAV according to the delivery task when receiving the delivery task;

[0050] A construction module is used to construct a motion model of the UAV, and to construct an objective function and multiple constraints corresponding to the UAV's delivery trajectory based on the UAV's motion model;

[0051] The construction module is further used to construct a delivery trajectory planning problem model based on the objective function and the plurality of constraints;

[0052] A solution module, configured to optimize and solve the delivery trajectory based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain an optimal delivery trajectory;

[0053] The control module is used to control the drone to be released in near space according to the optimal release trajectory.

[0054] In addition, to achieve the above-mentioned purpose, the present application also proposes a near-space UAV delivery trajectory optimization device, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the near-space UAV delivery trajectory optimization method as described above.

[0055] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the near-space UAV delivery trajectory optimization method as described above are implemented.

[0056] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the near-space UAV delivery trajectory optimization method as described above.

[0057] One or more technical solutions proposed in this application, when receiving a delivery mission, determine the take-off point and target delivery point of the UAV according to the delivery mission; construct a motion model of the UAV, and construct an objective function and multiple constraints corresponding to the delivery trajectory of the UAV based on the motion model of the UAV; construct a delivery trajectory planning problem model based on the objective function and multiple constraints; optimize and solve the delivery trajectory based on the take-off point, the target delivery point and the delivery trajectory planning problem model to obtain the optimal delivery trajectory; control the UAV to deliver in near-space according to the optimal delivery trajectory. In the above manner, by optimizing and solving the optimal delivery trajectory under the objective function corresponding to the delivery trajectory of the UAV and multiple constraints, efficient trajectory optimization of the UAV in near-space under multiple constraints is achieved, thereby improving the delivery efficiency of the UAV and the success rate of mission execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0059] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0060] Figure 1 A flowchart illustrating a first embodiment of a method for optimizing the trajectory of a near-space drone delivery system is provided.

[0061] Figure 2 A flow chart illustrating a second embodiment of the method for optimizing the trajectory of a near-space drone delivery system.

[0062] Figure 3 This is a schematic diagram of the module structure of the near-space UAV delivery trajectory optimization device according to an embodiment of the present application;

[0063] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the near-space UAV launch trajectory optimization device in the embodiment of the present application.

[0064] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0066] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0067] The main solution of the embodiment of the present application is: when receiving a delivery task, determining the take-off point and target delivery point of the drone according to the delivery task; constructing a motion model of the drone, and constructing an objective function and multiple constraints corresponding to the delivery trajectory of the drone based on the motion model of the drone; constructing a delivery trajectory planning problem model based on the objective function and the multiple constraints; optimizing and solving the delivery trajectory based on the take-off point, the target delivery point and the delivery trajectory planning problem model to obtain the optimal delivery trajectory; controlling the drone to deliver in the near space according to the optimal delivery trajectory.

[0068] Most traditional trajectory optimization methods only consider a single objective function or relatively simplified constraints, resulting in poor trajectory optimization efficiency and effect. They cannot meet the needs of drone deployment in complex environments, which in turn affects the efficiency and safety of drone mission execution.

[0069] This application provides a solution that optimizes and solves the optimal delivery trajectory under the objective function corresponding to the delivery trajectory of the drone and multiple constraints, thereby achieving efficient trajectory optimization of near-space drones under multiple constraints, thereby improving the delivery efficiency of drones and the success rate of mission execution.

[0070] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions, a near-space drone delivery trajectory optimization device, etc. The following uses the near-space drone delivery trajectory optimization device as an example to illustrate this embodiment and the following embodiments.

[0071] Based on this, the embodiment of the present application provides a method for optimizing the delivery trajectory of a near-space drone, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the near-space UAV delivery trajectory optimization method of the present application.

[0072] In this embodiment, the method for optimizing the delivery trajectory of a near-space UAV includes steps S10 to S50:

[0073] Step S10: When a delivery task is received, the take-off point and target delivery point of the UAV are determined according to the delivery task.

[0074] It should be noted that the drones in this embodiment are used for near-space exploration, for example, for high-altitude reconnaissance, environmental monitoring, and other missions. The takeoff point and target drop point can be set based on the specific requirements of the drop mission. For example, in some cases, the takeoff point may be a fixed airport or launch platform, while the target drop point may be a specific area that requires exploration or monitoring.

[0075] It should be understood that a delivery mission refers to a task that requires a drone to deliver a payload (such as detection equipment, supplies, etc.) from a take-off point to a target delivery point along a specific trajectory. After receiving the delivery mission, the drone's take-off point and target delivery point are determined based on the specific requirements of the mission, such as the type of payload to be delivered, the accuracy requirements for delivery, the time window for delivery, etc. The take-off point is the location where the drone begins to take off, and the target delivery point is the location where the drone needs to deliver the payload. The take-off point and target delivery point will serve as the starting and end points of the trajectory optimization, constraining the drone's flight trajectory.

[0076] Step S20: constructing a motion model of the UAV, and constructing an objective function and multiple constraints corresponding to the UAV's delivery trajectory based on the UAV's motion model.

[0077] It's important to note that a drone's motion model is a mathematical model that describes its motion in space, taking into account various factors such as its speed, acceleration, position, and attitude. When constructing a drone's motion model, appropriate model parameters and form are selected based on the drone's dynamic and kinematic characteristics, combined with the specific requirements of the delivery mission.

[0078] It should be understood that the objective function, used to measure the quality of a delivery trajectory, is related to factors such as the drone's flight distance, flight time, energy consumption, and delivery accuracy. Constraints, on the other hand, restrict the drone's flight trajectory and include, but are not limited to, its altitude, speed range, attitude restrictions, and no-fly zones. These constraints ensure that the drone does not violate physical laws or safety regulations during flight, while also guaranteeing the successful completion of the delivery mission.

[0079] In a feasible embodiment, step S20 may include: constructing a motion model of the UAV based on the dynamic characteristics and kinematic equations of the UAV; determining the flight parameters of the UAV based on the motion model of the UAV; constructing multiple constraints based on the flight parameters of the UAV, wherein the constraints include speed constraints, acceleration constraints, no-fly zone constraints, obstacle avoidance constraints, flight area boundary constraints, battery energy limitations, and mission time limits; and constructing an objective function corresponding to the UAV's delivery trajectory with the goals of minimizing total flight time, minimizing energy consumption, minimizing path length, and trajectory smoothness.

[0080] It should be noted that the dynamic characteristics of a drone include factors such as mass, inertia, thrust, and resistance, while the kinematic equations describe the changing laws of the drone's motion state, such as position, velocity, and acceleration in space. By combining the dynamic characteristics and kinematic equations, a mathematical model that can accurately reflect the laws of drone motion can be constructed.

[0081] It's understood that a drone's flight parameters are crucial data describing its flight state, including but not limited to position, velocity, acceleration, and attitude angle. These parameters form the basis for constructing the drone's motion model and constraints, and are a key input for subsequent trajectory optimization. Once the drone's flight parameters are determined, a series of constraints can be constructed based on the specific requirements of the delivery mission and the drone's performance characteristics.

[0082] The constraints in this embodiment include speed constraints, acceleration constraints, no-fly zone constraints, obstacle avoidance constraints, flight area boundary constraints, battery energy limits, and mission time limits.

[0083] Speed ​​constraints are used to ensure that the UAV remains within a feasible speed range during flight, avoiding control problems or excessive energy consumption due to too low or too high speeds. The speed constraints are: v min is the minimum speed limit of the drone, v max is the maximum speed limit of the drone, is the speed of the UAV at time t.

[0084] Acceleration constraints are used to ensure that the drone's movement is smooth during flight, avoiding sudden acceleration or deceleration. The acceleration constraints are: A min ≤A(t)≤A max , A min is the minimum acceleration limit of the drone, A max is the maximum acceleration limit of the UAV, and A(t) is the acceleration of the UAV at time t.

[0085] No-fly zone constraints are used to ensure that drones avoid entering restricted flight areas, such as military no-fly zones and the airspace around airports, to ensure the legality and safety of flights. No-fly zone constraints are: p(t) is the position of the drone at time t. No-fly zone is a no-fly zone.

[0086] The obstacle avoidance constraint is used to ensure that the UAV maintains a safe distance from surrounding obstacles during flight to avoid collision. The obstacle avoidance constraint is: ||p(t)-O i ||≥d safe , O i is the position of the i-th obstacle, dsafe The safety distance indicates the minimum distance that must be maintained between the drone and obstacles.

[0087] The flight area boundary constraint is used to ensure that the UAV does not fly out of the predetermined flight area, avoid entering unsafe areas or violating flight regulations. The flight area boundary constraint is: p(t)∈FlightArea, where FlightArea is the flight area, which is the allowed area for UAV flight. That is, all flight trajectories must be within this area.

[0088] The battery energy limit is used to ensure that the battery energy of the drone does not exceed the maximum battery capacity, avoiding the risk of battery overload, resulting in battery damage or power exhaustion. It is also used to ensure flight time and range. The battery energy limit is: E(t)≤E max , E(t) is the remaining battery energy of the drone at time t, E max The maximum energy limit of the drone battery.

[0089] The mission time limit is used to ensure that the UAV completes the mission within the specified time and avoids mission timeout. The mission time limit is: T arrive ≤T dealine , T arrive is the time it takes for the UAV to arrive at the target delivery point, T dealine The time deadline for the task.

[0090] It should be understood that the objective function in this embodiment is a comprehensive evaluation index with the goals of minimizing total flight time, minimizing energy consumption, minimizing path length, and trajectory smoothness. By solving the optimal solution of the objective function, a drone delivery trajectory that satisfies all constraints and has optimal performance can be obtained. The formula of the objective function is:

[0091]

[0092] Among them, J is the objective function, α1, α2, α3 and α4 are weight coefficients used to balance the relative importance of each goal, t0 is the take-off time, t f is the task completion time, P(t) is the power consumption at time t, is the speed of the UAV at time t, A(t) is the acceleration of the UAV at time t, Indicates the change in acceleration.

[0093] Step S30: Constructing a delivery trajectory planning problem model based on the objective function and the plurality of constraints.

[0094] As you can understand, the delivery trajectory planning model is a complex optimization problem, requiring the search for a drone flight trajectory that optimizes the objective function while satisfying all constraints. The delivery trajectory planning model integrates all relevant information, including the drone's takeoff point, target delivery point, motion model, objective function, and constraints, into a complete optimization problem. Solving this problem yields a delivery trajectory that meets mission requirements.

[0095] The delivery trajectory planning problem model is:

[0096]

[0097] A min ≤A(t)≤A max

[0098]

[0099] ||p(t)-O i ||≥d safe

[0100] p(t)∈Flight Area

[0101] E(t)≤E max

[0102] T arrive ≤T dealine

[0103] Among them, v min is the minimum speed limit of the drone, v max is the maximum speed limit of the drone, A min is the minimum acceleration limit of the drone, A max is the maximum acceleration limit of the UAV, p(t) is the position of the UAV at time t, No-flyzone is the no-fly zone, O i is the position of the i-th obstacle, d safe is the safety distance, Flight Area is the flight area, E(t) is the remaining battery energy of the drone at time t, and E max is the maximum energy limit of the drone battery, T arrive is the time it takes for the UAV to arrive at the target delivery point, T dealine The time deadline for the task.

[0104] Step S40: Optimizing and solving the delivery trajectory based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain an optimal delivery trajectory.

[0105] It should be noted that a preset optimization algorithm is used to solve the delivery trajectory planning problem model to obtain the optimal delivery trajectory for the drone. The optimization algorithm can be a genetic algorithm, a particle swarm optimization algorithm, a simulated annealing algorithm, etc. This embodiment uses the simulated annealing algorithm as an example. By running the optimization algorithm, a drone delivery trajectory that achieves the optimal value of the objective function can be found while satisfying all constraints.

[0106] It's understandable that the optimal delivery trajectory must satisfy all constraints and achieve the optimal value of the objective function. This optimal delivery trajectory not only ensures the drone can complete its delivery mission safely and legally, but also maximizes flight efficiency and performance. In practical applications, this optimal delivery trajectory can serve as input to the drone's flight control system, guiding the drone to fly and deliver according to a predetermined trajectory. This approach enables precise control and optimization of the drone's delivery trajectory, improving its mission execution capability and efficiency.

[0107] Step S50: Control the UAV to deliver the payload in the near space according to the optimal delivery trajectory.

[0108] It should be noted that near-space refers to the air space within a certain altitude range. In this embodiment, near-space refers to the airspace between 20 and 100 kilometers from the ground.

[0109] It's understood that when controlling a drone to deliver a payload along an optimal trajectory, it will fly along the calculated optimal trajectory based on pre-set flight parameters and constraints. During flight, the drone monitors its flight status in real time, including speed, acceleration, position, remaining battery life, and other information, to ensure safety and stability. Simultaneously, the drone will deliver the payload at the appropriate location and time based on mission requirements to achieve the intended mission objectives. This approach enables precise control and optimization of the drone's delivery trajectory, improving its mission execution capabilities and efficiency.

[0110] In a feasible embodiment, after step S20, it also includes: obtaining the real-time position, real-time speed and the reference position and reference speed of the corresponding point on the optimal trajectory of the UAV; determining the position deviation and the speed deviation according to the real-time position, the real-time speed, the reference position and the reference speed; using the position deviation and the speed deviation as inputs of the PID controller, and outputting a control instruction to adjust the flight state of the UAV so that the UAV flies along the optimal trajectory, wherein the parameters of the PID controller include a proportional coefficient Kp, an integral coefficient Ki and a differential coefficient Kd, and the flight state of the UAV is controlled by adjusting the proportional coefficient Kp, the integral coefficient Ki and the differential coefficient Kd, the proportional coefficient Kp is used to control the influence of the current deviation on the control instruction, the integral coefficient Ki is used to eliminate the static deviation, and the differential coefficient Kd is used to predict the changing trend of the future deviation and make adjustments in advance.

[0111] It should be noted that by comparing the drone's real-time position and speed with the reference position and speed of the corresponding point on the optimal trajectory, the drone's position deviation and speed deviation can be accurately calculated. The position deviation and speed deviation reflect the difference between the drone's current flight state and the predetermined optimal trajectory.

[0112] It can be understood that by using position deviation and velocity deviation as inputs to the PID controller, the PID controller can calculate the corresponding control instructions based on this deviation information to adjust the drone's flight state. The parameters of the PID controller include the proportional coefficient Kp, the integral coefficient Ki, and the differential coefficient Kd. The proportional coefficient Kp determines the degree to which the current deviation affects the control instructions, allowing the drone to quickly respond to deviations and adjust its flight state; the integral coefficient Ki is used to eliminate static deviations, ensuring that the drone can fly stably along the optimal trajectory for a long time; the differential coefficient Kd predicts the future deviation trend and makes adjustments in advance, further enhancing the stability and accuracy of the control.

[0113] It's worth noting that the precise control of the PID controller allows the drone to fly along the optimal trajectory, ensuring the successful completion of the delivery mission. During flight, the drone continuously monitors and adjusts its flight state to adapt to various complex environments and mission requirements. This precise control and optimization method not only improves the drone's flight efficiency and performance, but also enhances its mission execution capabilities and adaptability.

[0114] This embodiment provides a method for optimizing the delivery trajectory of a near-space drone. When a delivery mission is received, the take-off point and target delivery point of the drone are determined according to the delivery mission; a motion model of the drone is constructed, and based on the motion model of the drone, an objective function and multiple constraints corresponding to the delivery trajectory of the drone are constructed; a delivery trajectory planning problem model is constructed based on the objective function and the multiple constraints; the delivery trajectory is optimized and solved based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain an optimal delivery trajectory; and the drone is controlled to be delivered in near-space according to the optimal delivery trajectory. In the above manner, by optimizing and solving the optimal delivery trajectory under the objective function corresponding to the delivery trajectory of the drone and multiple constraints, efficient trajectory optimization of the near-space drone under multiple constraints is achieved, thereby improving the delivery efficiency of the drone and the success rate of mission execution.

[0115] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 , step S40 includes steps S401 to S404:

[0116] Step S401: performing path planning based on the take-off point and the target delivery point to generate an initial delivery trajectory.

[0117] It should be noted that the Dijkstra algorithm or A* algorithm can be used for path planning based on the take-off point and the target delivery point. Combined with the flight environment and mission requirements of the UAV, the shortest path or optimal path from the take-off point to the target delivery point can be calculated as the initial delivery trajectory.

[0118] Step S402: Optimizing the initial delivery trajectory through the delivery trajectory planning problem model to obtain multiple candidate delivery trajectories.

[0119] It should be noted that in this embodiment, a simulated annealing algorithm is used to iteratively optimize the initial delivery trajectory to find the global optimal solution. By simulating the physical annealing process, the simulated annealing algorithm can effectively search for the global optimal solution in the solution space and avoid falling into the local optimum. In each iteration, the algorithm will accept a solution that is worse than the current solution with a certain probability, thereby having the opportunity to jump out of the local optimal area and continue searching for the global optimal solution. Through multiple iterations, the algorithm will gradually converge to the global optimal solution or a better solution close to the global optimal solution, thereby obtaining the optimal delivery trajectory. This optimization method not only improves the accuracy and efficiency of the delivery trajectory, but also enhances the adaptability and robustness of the UAV in various complex environments and mission requirements.

[0120] In a feasible embodiment, step S402 may include: setting an initial temperature, and setting a cooling rate and a termination temperature; at the current temperature, taking the initial delivery trajectory as the current solution; performing calculations based on the objective function in the delivery trajectory planning problem model and the current solution to obtain a fitness value of the current solution; randomly generating a new solution within the neighborhood of the current solution and calculating the fitness value of the new solution; if the fitness value of the new solution is better than the fitness value of the current solution, accepting the new solution as the current solution; if the fitness value of the new solution is not better than the fitness value of the current solution, accepting the new solution as the current solution with a preset probability, wherein the acceptance probability decreases as the temperature decreases; re-executing the steps of randomly generating a new solution within the neighborhood of the current solution and calculating the fitness value of the new solution until the number of iterations at the current temperature is reached or the current solution has not improved within a certain number of times, reducing the current temperature, taking the reduced temperature as the current temperature and re-executing the step of taking the initial delivery trajectory as the current solution at the current temperature until the current temperature is reduced below the termination temperature, and outputting multiple candidate delivery trajectories.

[0121] It's important to note that the initial temperature determines the simulated annealing algorithm's initial search range and exploration capabilities. A higher initial temperature means the algorithm can tolerate larger variations in the solution space at the beginning, giving it the opportunity to explore more potential global optimal solutions. However, an excessively high initial temperature can also slow the algorithm's convergence and increase computational time. Conversely, a lower initial temperature can limit the algorithm's search range and increase the risk of falling into a local optimum. Therefore, when choosing an initial temperature, a balance needs to be struck between search range and convergence speed to ensure that the algorithm can find the global optimal solution, or a better solution close to the global optimal solution, within a reasonable timeframe.

[0122] The cooling rate determines how quickly the algorithm cools down during the search process. A slower cooling rate means the algorithm has more opportunities to iterate at each temperature, increasing the likelihood of finding the global optimal solution. However, an excessively slow cooling rate can also cause the algorithm to converge too slowly, increasing computational time unnecessarily. Conversely, a faster cooling rate may accelerate convergence, but it may also cause the algorithm to converge to a local optimal solution prematurely. Therefore, when choosing the cooling rate, a trade-off between search depth and convergence speed must be considered.

[0123] It is worth noting that calculating the fitness value of the current solution is a key step in evaluating the quality of the current solution in the delivery trajectory planning problem model. The lower the fitness value, the better the performance of the current solution in the model, that is, the closer the delivery trajectory is to the global optimal solution. When calculating the fitness value, it is necessary to consider the objective function and multiple constraints to ensure that the resulting delivery trajectory not only meets the task requirements but also remains efficient and stable in complex environments. Through continuous iteration and optimization, it gradually converges to the solution with the lowest fitness value, thereby obtaining multiple candidate delivery trajectories. In this process, the unique mechanism of the simulated annealing algorithm enables the algorithm to flexibly search in the solution space, avoiding falling into local optimality, thereby ensuring that the final delivery trajectory is highly accurate and efficient.

[0124] Step S403: Evaluate multiple candidate delivery trajectories to obtain evaluation results.

[0125] It's important to note that after obtaining multiple candidate delivery trajectories, each needs to be evaluated to determine its feasibility and performance in practical applications. This evaluation process can comprehensively consider multiple factors, such as trajectory length, flight time, energy consumption, safety, and mission success rate. By constructing an evaluation index system, each candidate trajectory is quantitatively scored, resulting in objective evaluation results.

[0126] In a feasible implementation, step S403 may include: simulating multiple candidate delivery trajectories to obtain performance data of each candidate delivery trajectory in an actual flight environment; calculating the objective function value corresponding to each candidate delivery trajectory based on the performance data; scoring each candidate delivery trajectory based on the objective function value and the satisfaction of the constraint conditions to obtain an evaluation result, wherein a candidate delivery trajectory with a higher score indicates better performance in an actual flight environment.

[0127] It's important to note that by simulating the drone's movements in an actual flight environment, we can intuitively understand the pros and cons of each candidate trajectory. During the simulation process, we need to consider parameters such as the drone's flight speed, altitude, and attitude, as well as factors such as wind, airflow, and obstacles in the flight environment to ensure the accuracy and reliability of the simulation results.

[0128] It's understandable that by calculating the objective function value corresponding to each candidate trajectory, its performance in actual flight can be quantitatively evaluated. During the scoring process, in addition to considering the objective function value, it's also necessary to comprehensively consider whether the constraint conditions are met, such as whether the trajectory meets the drone's flight restrictions and whether it maintains a safe distance from other flying objects, to ensure that the final selected delivery trajectory is both efficient and safe.

[0129] Specifically, scoring each candidate delivery trajectory can be achieved by constructing an evaluation model. This evaluation model can be based on machine learning methods such as support vector machines (SVMs), random forests, or neural networks. By training on a large amount of historical data, a mapping relationship between candidate trajectories and evaluation results is established. During the training process, candidate trajectories with known performance can be used as training samples, their features extracted as input, and the corresponding evaluation results as output. The accuracy of the evaluation is improved by continuously optimizing the model parameters. After training is complete, the newly obtained candidate trajectories can be input into the evaluation model to quickly obtain their evaluation results, greatly improving the efficiency and practicality of trajectory optimization.

[0130] Step S404: selecting an optimal delivery trajectory from the plurality of candidate delivery trajectories according to the evaluation result, wherein the optimal delivery trajectory minimizes the objective function while satisfying all constraints.

[0131] It should be noted that the optimal delivery trajectory must not only minimize the objective function while satisfying all constraints, but also demonstrate high stability and reliability in actual flight environments. When selecting the optimal delivery trajectory, it is necessary to comprehensively consider the evaluation results, the drone's performance parameters, and the actual flight environment to ensure that the final trajectory meets theoretical requirements and can achieve the best results in practical applications.

[0132] Specifically, the evaluation results of candidate trajectories can be compared to select the one with the highest score as the optimal delivery trajectory. If multiple trajectories have similar scores, further analysis is needed to determine their differences and strengths. Factors such as trajectory smoothness, flight time stability, and energy efficiency should be considered to ensure the final selected trajectory has the best overall performance.

[0133] In this embodiment, a delivery trajectory planning problem model is constructed and the initial delivery trajectory is optimized using a simulated annealing algorithm to obtain multiple candidate delivery trajectories. Trajectory evaluation is performed through simulation and quantitative scoring. Based on the evaluation results, the trajectory with the highest score is selected as the optimal delivery trajectory, effectively improving the accuracy and efficiency of the delivery trajectory.

[0134] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the near-space UAV delivery trajectory optimization method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0135] This application also provides a near-space UAV delivery trajectory optimization device, please refer to Figure 3 , the near-space UAV delivery trajectory optimization device includes:

[0136] The determination module 10 is used to determine the take-off point and target delivery point of the UAV according to the delivery task when receiving the delivery task.

[0137] The construction module 20 is used to construct a motion model of the UAV, and to construct an objective function and multiple constraints corresponding to the delivery trajectory of the UAV based on the motion model of the UAV.

[0138] The construction module 20 is further configured to construct a delivery trajectory planning problem model based on the objective function and the plurality of constraints.

[0139] The solution module 30 is used to optimize and solve the delivery trajectory based on the take-off point, the target delivery point and the delivery trajectory planning problem model to obtain the optimal delivery trajectory.

[0140] The control module 40 is used to control the UAV to deliver the payload in the near space according to the optimal delivery trajectory.

[0141] The near-space drone delivery trajectory optimization device provided by this application adopts the near-space drone delivery trajectory optimization method of the above-mentioned embodiment, which can solve the technical problem that traditional trajectory optimization methods have poor trajectory optimization efficiency and effect, cannot meet the needs of drone delivery in complex environments, and thus affect the efficiency and safety of drone mission execution. Compared with the existing technology, the beneficial effects of the near-space drone delivery trajectory optimization device provided by this application are the same as the beneficial effects of the near-space drone delivery trajectory optimization method provided by the above-mentioned embodiment, and the other technical features of the near-space drone delivery trajectory optimization device are the same as the features disclosed in the above-mentioned embodiment method, and are not further described here.

[0142] The present application provides a device for optimizing the delivery trajectory of a near-space drone. The device for optimizing the delivery trajectory of a near-space drone includes: at least one processor; and 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 near-space drone delivery trajectory optimization method of the above-mentioned embodiment one.

[0143] Reference below Figure 4, which shows a schematic structural diagram of a device for optimizing the delivery trajectory of a near-space drone suitable for implementing an embodiment of the present application. The device for optimizing the delivery trajectory of a near-space drone in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The near-space drone delivery trajectory optimization device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present application.

[0144] like Figure 4 As shown, the delivery trajectory optimization device for near-space drones may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 into RAM (Random Access Memory) 1004. Various programs and data required for the operation of the delivery trajectory optimization device for near-space drones are also stored in RAM 1004. The processing device 1001, ROM 1002 and RAM 1004 are connected to each other via a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, an LCD (Liquid Crystal Display), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 can allow the near-space drone delivery trajectory optimization device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a near-space drone delivery trajectory optimization device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.

[0145] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0146] The near-space drone delivery trajectory optimization device provided by this application utilizes the near-space drone delivery trajectory optimization method of the above-mentioned embodiment, which can solve the technical problem that traditional trajectory optimization methods have poor trajectory optimization efficiency and effectiveness, cannot meet the needs of drone delivery in complex environments, and thus affect the efficiency and safety of drone mission execution. Compared with the existing technology, the beneficial effects of the near-space drone delivery trajectory optimization device provided by this application are the same as the beneficial effects of the near-space drone delivery trajectory optimization method provided by the above-mentioned embodiment, and the other technical features of the near-space drone delivery trajectory optimization device are the same as the features disclosed in the previous embodiment method, and are not further described here.

[0147] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0148] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0149] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the near-space UAV delivery trajectory optimization method in the above-mentioned embodiment.

[0150] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0151] The above-mentioned computer-readable storage medium can be included in the delivery trajectory optimization device of the near-space drone; or it can exist independently without being assembled into the delivery trajectory optimization device of the near-space drone.

[0152] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the near-space UAV delivery trajectory optimization device, the near-space UAV delivery trajectory optimization device enables the following: when receiving a delivery task, determine the take-off point and target delivery point of the UAV according to the delivery task; construct a motion model of the UAV, and construct an objective function and multiple constraints corresponding to the UAV delivery trajectory based on the UAV motion model; construct a delivery trajectory planning problem model based on the objective function and the multiple constraints; optimize and solve the delivery trajectory based on the take-off point, the target delivery point and the delivery trajectory planning problem model to obtain the optimal delivery trajectory; and control the UAV to deliver in near space according to the optimal delivery trajectory.

[0153] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0154] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0155] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0156] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., a computer program) for executing the above-mentioned near-space drone delivery trajectory optimization method. This can solve the technical problem that traditional trajectory optimization methods have poor trajectory optimization efficiency and effectiveness, cannot meet the needs of drone delivery in complex environments, and thus affect the efficiency and safety of drone mission execution. Compared with the existing technology, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the near-space drone delivery trajectory optimization method provided in the above-mentioned embodiment, and will not be repeated here.

[0157] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned near-space UAV delivery trajectory optimization method.

[0158] The computer program product provided in this application addresses the technical issues of traditional trajectory optimization methods, which suffer from poor efficiency and effectiveness, fail to meet the requirements for drone deployment in complex environments, and thus impact the efficiency and safety of drone mission execution. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the near-space drone delivery trajectory optimization method provided in the aforementioned embodiments, and are not further elaborated here.

[0159] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for optimizing the delivery trajectory of a near-space UAV, characterized in that: The method comprises: Upon receiving a delivery mission, determining the take-off point and target delivery point of the drone according to the delivery mission; Constructing a motion model of the UAV, and constructing an objective function and multiple constraints corresponding to the UAV's delivery trajectory based on the UAV's motion model; Constructing a delivery trajectory planning problem model based on the objective function and the plurality of constraints; Optimizing and solving the delivery trajectory based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain an optimal delivery trajectory; Control the drone to deliver the payload in near space according to the optimal delivery trajectory.

2. The method according to claim 1, wherein The method of constructing a motion model of the drone and constructing an objective function and multiple constraints corresponding to the drone's delivery trajectory based on the motion model of the drone includes: Construct the UAV motion model based on the UAV's dynamic characteristics and kinematic equations; determining flight parameters of the UAV based on the motion model of the UAV; Constructing a plurality of constraints based on the flight parameters of the UAV, wherein the constraints include speed constraints, acceleration constraints, no-fly zone constraints, obstacle avoidance constraints, flight area boundary constraints, battery energy limits, and mission time limits; With the goal of minimizing the total flight time, energy consumption, path length, and trajectory smoothness, the objective function corresponding to the UAV delivery trajectory is constructed. The formula of the objective function is: Among them, J is the objective function, α1, α2, α3 and α4 are weight coefficients used to balance the relative importance of each goal, t0 is the take-off time, t f is the task completion time, P(t) is the power consumption at time t, is the speed of the UAV at time t, A(t) is the acceleration of the UAV at time t, Indicates the change in acceleration.

3. The method according to claim 1, wherein The delivery trajectory planning problem model is: A min ≤A(t)≤A max ||p(t)-O i ||≥d safe p(t)∈Flight Area E(t)≤E max T arrive ≤T dealine Among them, v min is the minimum speed limit of the drone, v max is the maximum speed limit of the drone, A min is the minimum acceleration limit of the drone, A max is the maximum acceleration limit of the UAV, p(t) is the position of the UAV at time t, No-fly zone is the no-fly zone, O i is the position of the i-th obstacle, d safe is the safety distance, Flight Area is the flight area, E(t) is the remaining battery energy of the drone at time t, and E max is the maximum energy limit of the drone battery, T arrive is the time it takes for the UAV to arrive at the target delivery point, T dealine The time deadline for the task.

4. The method according to claim 1, wherein The optimizing and solving the delivery trajectory based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain the optimal delivery trajectory includes: Performing path planning based on the take-off point and the target delivery point to generate an initial delivery trajectory; Optimizing the initial delivery trajectory through the delivery trajectory planning problem model to obtain multiple candidate delivery trajectories; Evaluate multiple candidate delivery trajectories and obtain evaluation results; An optimal delivery trajectory is selected from the plurality of candidate delivery trajectories according to the evaluation result, wherein the optimal delivery trajectory minimizes the objective function while satisfying all constraints.

5. The method according to claim 4, wherein The initial delivery trajectory is optimized by the delivery trajectory planning problem model to obtain multiple candidate delivery trajectories, including: Set the initial temperature, cooling rate and end temperature; At the current temperature, the initial delivery trajectory is used as the current solution; Calculating based on the objective function in the delivery trajectory planning problem model and the current solution to obtain a fitness value of the current solution; Randomly generate a new solution in the neighborhood of the current solution and calculate the fitness value of the new solution; If the fitness value of the new solution is better than the fitness value of the current solution, the new solution is accepted as the current solution; If the fitness value of the new solution is not better than the fitness value of the current solution, the new solution is accepted as the current solution with a preset probability, where the acceptance probability decreases as the temperature decreases; The steps of randomly generating a new solution in the neighborhood of the current solution and calculating the fitness value of the new solution are re-executed until the number of iterations at the current temperature is reached or the current solution has not been improved within a certain number of times, the current temperature is lowered, the lowered temperature is used as the current temperature, and the step of using the initial delivery trajectory as the current solution at the current temperature is re-executed until the current temperature is lowered below the termination temperature, and multiple candidate delivery trajectories are output.

6. The method according to claim 4, wherein The evaluation of multiple candidate delivery trajectories to obtain evaluation results includes: Simulate multiple candidate delivery trajectories to obtain performance data for each candidate delivery trajectory in an actual flight environment; Calculating the objective function value corresponding to each candidate delivery trajectory based on the performance data; Based on the objective function value and the satisfaction of the constraint conditions, each candidate delivery trajectory is scored to obtain an evaluation result, wherein a candidate delivery trajectory with a higher score indicates better performance in the actual flight environment.

7. The method according to claim 1, wherein After the drone is controlled to be released in the near space according to the optimal release trajectory, the method further includes: Obtain the real-time position and speed of the drone as well as the reference position and speed of the corresponding point on the optimal trajectory; Determine a position deviation and a speed deviation according to the real-time position, the real-time speed, the reference position, and the reference speed; The position deviation and the speed deviation are used as inputs of a PID controller, and a control instruction is output to adjust the flight state of the UAV so that the UAV flies along the optimal trajectory. The parameters of the PID controller include a proportional coefficient Kp, an integral coefficient Ki, and a differential coefficient Kd. The flight state of the UAV is controlled by adjusting the proportional coefficient Kp, the integral coefficient Ki, and the differential coefficient Kd. The proportional coefficient Kp is used to control the influence of the current deviation on the control instruction, the integral coefficient Ki is used to eliminate static deviation, and the differential coefficient Kd is used to predict the change trend of the future deviation and make adjustments in advance.

8. A near-space UAV delivery trajectory optimization device, characterized in that: The near-space UAV delivery trajectory optimization device includes: A determination module is used to determine the take-off point and target delivery point of the UAV according to the delivery task when receiving the delivery task; A construction module is used to construct a motion model of the UAV, and to construct an objective function and multiple constraints corresponding to the UAV's delivery trajectory based on the UAV's motion model; The construction module is further used to construct a delivery trajectory planning problem model based on the objective function and the plurality of constraints; A solution module, configured to optimize and solve the delivery trajectory based on the take-off point, the target delivery point, and the delivery trajectory planning problem model to obtain an optimal delivery trajectory; The control module is used to control the drone to be released in near space according to the optimal release trajectory.

9. A near-space UAV delivery trajectory optimization device, characterized in that: The near-space UAV delivery trajectory optimization device includes: a memory, a processor, and a near-space UAV delivery trajectory optimization program stored in the memory and executable on the processor. The near-space UAV delivery trajectory optimization program is configured to implement the near-space UAV delivery trajectory optimization method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a near-space UAV delivery trajectory optimization program, which, when executed by the processor, implements the near-space UAV delivery trajectory optimization method according to any one of claims 1 to 7.

Images