A nonlinear multi-objective mission planning method and device for unmanned aerial vehicle

By constructing objective functions and constraints and iteratively updating the current point, the problem of high computational volume and easy to fall into local optimal solutions in nonlinear multi-objective planning is solved, and efficient multi-objective task planning is achieved.

CN118586680BActive Publication Date: 2024-11-26SUZHOU LINGKONG INTELLIGENT EQUIP TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411066990.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-26
Estimated Expiration
2044-08-06

AI Technical Summary

Technical Problem

The existing nonlinear multi-objective planning methods have a large amount of calculation and are prone to fall into local optimal solutions, making it difficult to achieve multi-objective tasks with a small amount of calculation.

Method used

By establishing the objective functions and constraints of the target task, building neighborhoods and iteratively performing search steps, using scheduling strategies to update the current point until the termination condition is reached, avoiding local optimal solutions, and improving computing efficiency and globality of planning results.

Benefits of technology

It effectively solves the problem of large amount of calculation, avoids falling into local optimal solutions, and improves the computing efficiency and globality of the results of multi-objective task planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118586680B_ABST
    Figure CN118586680B_ABST
Patent Text Reader

Abstract

The present application discloses a nonlinear multi-objective task planning method and device for unmanned aerial vehicles, the method comprising: establishing the objective function and constraint conditions of the target task, and setting the initial solution of the objective function; constructing a neighborhood according to the objective function and constraint conditions; determining the current point corresponding to the initial solution according to the objective function and constraint conditions, and iteratively executing the search step according to the scheduling strategy until the termination condition is reached to obtain the optimization result; planning the target task according to the optimization result; wherein the search step comprises: determining the values ​​of all spatial points in the current neighborhood of the current point based on the objective function, and evaluating them; updating the current point according to the evaluation result, and executing the search step. The method solves the problem that the existing nonlinear multi-objective planning methods have a large amount of calculation and are prone to fall into the local optimal solution. Therefore, multi-objective task planning can be realized with a smaller amount of calculation, and it can also avoid falling into the local optimal solution, thereby improving the globality of the planning results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of multi-objective planning, and in particular to a method and device for nonlinear multi-objective task planning of an unmanned aerial vehicle. Background Art

[0002] Multi-objective mission planning can decompose, organize, optimize and schedule complex tasks, and then generate a series of executable action sequences or control strategies, playing an important role in path planning, remote sensing observation and other fields. It usually needs to consider multiple goals, such as the time, energy consumption, and safety of the UAV to complete the task. How to balance these goals and generate an optimal solution that meets all the goals is a challenging problem.

[0003] In a multi-objective task planning system, there are multiple interrelated and mutually influential task objectives. The relationship between these objectives is not a simple linear relationship, but presents complex nonlinear characteristics.

[0004] The existing nonlinear multi-objective programming methods are mainly based on evolution (multi-objective genetic algorithm, multi-objective differential evolution algorithm, etc.) and heuristic search-based methods (Pareto frontier tracking method). Evolution-based algorithms have strong global search capabilities and are suitable for large-scale, high-dimensional nonlinear problems, but they are computationally intensive and prone to premature convergence and falling into local optimal solutions. Heuristic search-based algorithms are highly flexible and are also suitable for large-scale, high-dimensional nonlinear problems, but they require the establishment of a series of heuristic rules that conform to actual problems. These rules often lack theoretical guidance and need to rely on experience and trial and error. They are also computationally intensive and prone to falling into local optimal solutions. Summary of the invention

[0005] The embodiments of the present application provide a method and device for nonlinear multi-objective task planning of an unmanned aerial vehicle, thereby solving the problem that the existing nonlinear multi-objective planning methods have large computational complexity and are prone to falling into local optimal solutions.

[0006] In the first aspect, an embodiment of the present application provides a method for nonlinear multi-objective task planning of an unmanned aerial vehicle, comprising: establishing an objective function and constraints of a target task, and setting an initial solution of the objective function; constructing a neighborhood according to the objective function and the constraints; determining a current point corresponding to the initial solution according to the objective function and the constraints, and iteratively executing a search step according to a scheduling strategy until a termination condition is reached to obtain an optimization result; planning the target task according to the optimization result; wherein the search step comprises: determining the values ​​of all spatial points within the current neighborhood of the current point based on the objective function, and evaluating them; updating the current point according to the evaluation result, and executing the search step.

[0007] In combination with the first aspect, in a possible implementation method, establishing the objective function of the target task includes: determining a function type of the objective function according to task requirements; determining decision variables according to the target task; and constructing the objective function according to the function type and the decision variables.

[0008] In combination with the first aspect, in a possible implementation method, constructing a neighborhood based on the objective function and the constraints includes: determining the value range of the decision variable based on the constraints; constructing a search space with the decision variable as a dimension and its value range as a range; determining the variable distance between each spatial point in the search space; the spatial points whose variable distance satisfies the distance threshold constitute a neighborhood.

[0009] In combination with the first aspect, in a possible implementation manner, the objective function is as follows:

[0010] ; In the formula, represents the comprehensive objective function, represents the maximum objective function, represents the cumulative objective function, represents the decision variable, n represents the total duration of the route, represents the priority factor, It represents the ratio of the current time from the start time to time i to the total time of the route. represents the current unit energy consumption at time i, It represents the ratio of the current energy consumption at time i to the total energy consumption from the starting point to the current point.

[0011] In combination with the first aspect, in a possible implementation, the decision variables include current speed, current time, current energy consumption and current flight distance.

[0012] In combination with the first aspect, in a possible implementation manner, the constraint condition is as follows:

[0013] , ; In the formula, S is the absolute constraint condition, is a relative constraint condition, Indicates the current speed at time i, and Represents the minimum speed and maximum speed respectively. represents the current time at time i, Indicates the total duration of the task. represents the current energy consumption at time i, and Represent the minimum energy consumption and the maximum energy consumption respectively. Indicates the current flight distance at time i, Indicates the total distance of the route. represents the current unit energy consumption at time i, Represents the energy consumption coefficient.

[0014] In combination with the first aspect, in a possible implementation method, the scheduling strategy includes: executing an evaluation step; the evaluation step includes: determining the spatial point within the current neighborhood of the current point based on a distance threshold, and using the objective function to determine the values ​​of all the spatial points in the current neighborhood; evaluating the value of the spatial point, if the values ​​of the spatial points in the current neighborhood are all smaller than the current solution of the current point, updating the current point with the minimum value of the values ​​of the spatial points, and executing the evaluation step; if the values ​​of all the spatial points in the current neighborhood are greater than or equal to the current solution of the current point, increasing the distance threshold and iteratively executing the evaluation step until the current neighborhood is equal to the search space.

[0015] In combination with the first aspect, in a possible implementation, the termination condition includes: the scheduling strategy stops scheduling; and / or the search step reaches a preset number of iterations; and / or the adjacent current point meets the tolerance.

[0016] In the second aspect, an embodiment of the present application provides a nonlinear multi-objective task planning device for an unmanned aerial vehicle, comprising: an establishment module, used to establish the objective function and constraints of the target task, and set the initial solution of the objective function; a construction module, used to construct a neighborhood according to the objective function and the constraints; an iteration module, used to determine the current point corresponding to the initial solution according to the objective function and the constraints, and iteratively execute the search step according to the scheduling strategy until the termination condition is reached to obtain an optimization result; plan the target task according to the optimization result; wherein the search step comprises: determining the values ​​of all spatial points in the current neighborhood of the current point based on the objective function, and evaluating them; updating the current point according to the evaluation result, and executing the search step.

[0017] In a third aspect, an embodiment of the present application provides a device, comprising: a processor; a memory for storing processor-executable instructions; when the processor executes the executable instructions, it implements the method described in the first aspect or any possible implementation method of the first aspect.

[0018] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0019] The embodiment of the present application can plan the decision factors of the target task according to the task requirements through the objective function; the safety of the drone can be guaranteed as much as possible through the constraint conditions, and the calculation efficiency can be improved. The scheduling strategy can avoid falling into the local optimal solution when performing multi-objective optimization. It effectively solves the problem that the existing nonlinear multi-objective planning method has a large amount of calculation and is easy to fall into the local optimal solution. In addition, it can realize multi-objective task planning with a smaller amount of calculation, and can also avoid falling into the local optimal solution, and improve the globality of the planning results. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of a nonlinear multi-objective mission planning method for a UAV provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of a scheduling strategy provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of the structure of a nonlinear multi-objective mission planning device for an unmanned aerial vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The following describes some of the techniques involved in the embodiments of the present application to facilitate understanding, and they should be considered as merely exemplary. Therefore, it should be appreciated by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, some descriptions of well-known functions and structures are omitted in the following description.

[0026] Figure 1 The embodiment of the present application provides a nonlinear multi-objective mission planning method for unmanned aerial vehicles, including steps 101 to 107. Among them, Figure 1This is only an execution order shown in the embodiment of the present application, and does not represent the only execution order of a nonlinear multi-objective task planning method for a UAV. If the final result can be achieved, Figure 1 The steps shown may be performed in parallel or reversed.

[0027] Step 101: Establish the objective function and constraints of the target task, and set the initial solution of the objective function. In the embodiment of the present application, the function type of the objective function is determined according to the complexity of the task. Among them, the function type includes a comprehensive objective function, an extreme objective function and a cumulative objective function. Specifically, the function type of the objective function is determined according to the task requirements. If the target task is more urgent and has a high time requirement, the cumulative objective function is used. If the target task requires reducing energy consumption, the extreme objective function is used. If the target task requires a balance between time consumption and energy consumption, the comprehensive objective function is used.

[0028] The decision variables are determined according to the target task. Specifically, the decision variables include the current speed, the current time, the current energy consumption and the current flight distance. The decision variables determined in this application are the variable parameters of the drone, that is, the parameters that can change during the flight of the drone.

[0029] Construct the objective function based on the function type and decision variables. Specifically, the objective function is as follows:

[0030] In the formula, represents the comprehensive objective function, represents the maximum objective function, represents the cumulative objective function, represents the decision variable, n represents the total duration of the route, represents the priority factor, which is A random number between It represents the ratio of the current time from the start time to time i to the total time of the route. represents the current unit energy consumption at time i, It represents the ratio of the current energy consumption at time i to the total energy consumption from the starting point to the current point.

[0031] It should be noted that the linear relationship of the objective function of this application is affected by the decision variables. If the current time and the current flight distance in the decision variables of this application are continuous, then its objective function is linear; if the current speed and current energy consumption are discontinuous and change irregularly, then its objective function is nonlinear.

[0032] In order to avoid meaningless solutions and enhance the stability of the objective function, constraints are set for the objective function as follows:

[0033] , In the formula, S is the absolute constraint condition, is a relative constraint condition, Indicates the current speed at time i, and Represents the minimum speed and maximum speed respectively. represents the current time at time i, Indicates the total duration of the task. represents the current energy consumption at time i, and Represent the minimum energy consumption and the maximum energy consumption respectively. Indicates the current flight distance at time i, Indicates the total distance of the route. represents the current unit energy consumption at time i, Represents the energy consumption coefficient.

[0034] Among them, here and It indicates the minimum and maximum speed of the UAV during the entire mission. Those skilled in the art should understand and It must be greater than the minimum speed in the UAV's own performance parameters, and must be less than the maximum speed in the UAV's own performance parameters. When used in comprehensive objective functions or cumulative objective functions, it refers to the maximum time predicted based on the current speed of the drone. When used for the maximum objective function, it is the task duration of the specified target task. and It represents the minimum and maximum energy consumption of the UAV during the entire mission. Those skilled in the art should understand and It must be greater than the minimum energy consumption in the drone’s own performance parameters, and must be less than the maximum energy consumption in the drone’s own performance parameters. It is used to characterize the linear relationship between energy consumption and speed under uniform flight conditions. The value of k is different for different types of drones, different speeds, different air pressures, different wind resistances or different loads. Here, it is set to 2.133 for example. Those skilled in the art can test the k value in an ideal environment, or calculate the k value based on the performance parameters of the drone. The method for determining the k value is not specifically limited here.

[0035] This application will be and as well as and Setting it as the maximum value in the entire target mission can exclude the endpoint values ​​in the UAV performance parameters, avoid unnecessary calculations, and ensure the flight safety of the UAV.

[0036] In addition, in order to ensure the flight safety of the UAV, those skilled in the art may also add the take-off weight, flight altitude or maximum range of the UAV as constraints.

[0037] The initial solution set for the objective function may be the time and energy consumption required for a drone to complete a mission determined by a technician in this field based on experience or historical data.

[0038] Step 102: Construct a neighborhood according to the objective function and the constraints. In an embodiment of the present application, the value range of the decision variable is determined according to the objective function and the constraints. The decision variable is used as a dimension and its value range is used as a range to construct a search space. Specifically, the value range of each decision variable is calculated according to the above constraints. The decision variable is used as a dimension and the search space is constructed with its value range as a range. Exemplarily, the present application has four decision variables, and the current speed, current energy consumption and current flight distance are used as the X-axis, Y-axis and Z-axis to construct a Cartesian coordinate system, and the current time is introduced into the Cartesian coordinate system to construct a four-dimensional space-time coordinate system to form a search space. In the search space, a series of spatial points are generated in the four-dimensional space-time coordinate system according to the value range of the decision variable, and each spatial point can be represented by a four-dimensional vector ( , , , ) is used to represent. Those skilled in the art will appreciate that It is the current time, which is relative to the take-off time.

[0039] Determine the variable distance between each spatial point in the search space. The spatial points whose variable distance meets the distance threshold constitute the neighborhood. Specifically, the calculation formula of the variable distance is as follows:

[0040] . In the formula, D represents the variable distance, Represents the balance coefficient, and its value is , represents the time difference between two spatial points, , and Represents the difference between two spatial points on the X-axis, Y-axis and Z-axis respectively. All spatial points within the distance threshold of a spatial point constitute the neighborhood of the spatial point. The distance threshold is exemplarily set to rice.

[0041] Step 103: Determine the current point corresponding to the initial solution according to the objective function and the constraints. Specifically, the initial solution set in step 101 is used to reversely calculate the values ​​of the decision variables that meet the constraints using the objective function, and then the values ​​of one set of decision variables are used as the current point.

[0042] Step 104: Determine the values ​​of all spatial points in the current neighborhood of the current point based on the objective function and evaluate them. In the embodiment of the present application, the current neighborhood of the current point is determined, and the values ​​of all spatial points in the current neighborhood are calculated using the objective function. The values ​​of each calculated spatial point are evaluated and sorted to obtain an evaluation result.

[0043] Step 105: Determine whether the iteration reaches the termination condition. In the embodiment of the present application, the termination condition includes: the scheduling strategy stops scheduling. And / or the search step reaches a preset number of iterations. And / or the adjacent current point meets the tolerance. Among them, the preset number of iterations is exemplarily set to 500 times. The adjacent current point meets the tolerance, which means that the searched current point has stabilized and is close to the best optimization result or has reached the expected optimization result.

[0044] If the iteration does not reach the termination condition, step 106 is executed, and steps 104 to 105 are executed according to the scheduling strategy. If the iteration reaches the termination condition, step 107 is executed.

[0045] Among them, the scheduling strategy is as follows Figure 2 As shown, it includes steps 201 to 207, which are specifically as follows.

[0046] Step 201: Determine the spatial points within the current neighborhood of the current point based on the distance threshold. Specifically, all spatial points within the distance threshold range of the current point constitute the current neighborhood of the current point.

[0047] Step 202: Determine the values ​​of all spatial points in the current neighborhood using the objective function.

[0048] Step 203: Evaluate the value of the space point. Specifically, the value of each space point calculated in step 202 is evaluated and sorted to obtain an evaluation result.

[0049] Step 204: Determine whether there is a spatial point with a value smaller than the current solution of the current point in the current neighborhood. Specifically, if there is a spatial point with a value smaller than the current solution of the current point in the current neighborhood, it means that the current point is not the optimal point in the current neighborhood, and continue searching in the current neighborhood and execute step 205.

[0050] If there is no spatial point with a value of the current solution smaller than the current point in the current neighborhood, it means that the current point is the optimal point in the current neighborhood, and step 206 to step 207 are executed.

[0051] Step 205: Update the current point with the minimum value among the values ​​of the spatial points. Specifically, take the spatial point with the minimum value in the current neighborhood as the current point, and continue to execute steps 201 to 204.

[0052] Step 206: Determine whether the current neighborhood is equal to the search space. Specifically, determine whether the range of the current neighborhood determined based on the current distance threshold is equal to the range of the search space. If the range of the current neighborhood determined based on the current distance threshold is equal to the range of the search space, it means that the maximum range of the solution of the objective function has been searched, and the optimal value in the search space can be obtained. Otherwise, execute step 207.

[0053] Step 207: Increase the distance threshold. In the embodiment of the present application, when performing the first search, an optimal point (the spatial point corresponding to the minimum value) can be found in each neighborhood. If there is no spatial point with a value smaller than the current solution of the current point in the neighborhood, the current neighborhood has been searched, and the distance threshold is increased to expand the neighborhood range of each spatial point for a second search. For example, the distance threshold increased here is rice.

[0054] In addition, in order to improve the search efficiency, after each search of a current neighborhood, the non-optimal spatial points in each current neighborhood are removed. In the second search, it is based on the optimal solution of each neighborhood in the first search, which greatly reduces the amount of calculation.

[0055] Step 106: Update the current point according to the evaluation result. Specifically, the spatial point corresponding to the minimum value among the values ​​of the spatial points is used as the current point, and then steps 104 to 105 are executed based on the scheduling strategy.

[0056] Step 107: Get the optimization result, and plan the target task according to the optimization result. Specifically, set the decision variables of the target task according to the obtained optimization result, and get the optimal solution that meets the task requirements. That is, by balancing the current speed and the current energy consumption, get the optimal solution that meets the task requirements (reduce time consumption, reduce energy consumption, or balance time consumption and energy consumption).

[0057] Although the present application provides method operation steps such as embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in this embodiment is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the method shown in this embodiment or the accompanying drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0058] like Figure 3 As shown, the embodiment of the present application also provides a nonlinear multi-objective task planning device 300 for a drone. The device includes: an establishment module 301, a construction module 302 and an iteration module 303, as follows.

[0059] Establishing module 301 is used to establish the objective function and constraints of the target task, and set the initial solution of the objective function. Establishing module 301 is specifically used to determine the function type of the objective function according to the complexity of the task. Among them, the function type includes a comprehensive objective function, a maximum objective function and a cumulative objective function. Specifically, the function type of the objective function is determined according to the task requirements. If the target task is more urgent and has a high time requirement, the cumulative objective function is used. If the target task requires reducing energy consumption, the maximum objective function is used. If the target task requires a balance between time consumption and energy consumption, the comprehensive objective function is used.

[0060] The decision variables are determined according to the target task. Specifically, the decision variables include the current speed, the current time, the current energy consumption and the current flight distance. The decision variables determined in this application are the variable parameters of the drone, that is, the parameters that can change during the flight of the drone.

[0061] Construct the objective function based on the function type and decision variables. Specifically, the objective function is as follows:

[0062] In the formula, represents the comprehensive objective function, represents the maximum objective function, represents the cumulative objective function, represents the decision variable, n represents the total duration of the route, represents the priority factor, which is A random number between It represents the ratio of the current time from the start time to time i to the total time of the route. represents the current unit energy consumption at time i, It represents the ratio of the current energy consumption at time i to the total energy consumption from the starting point to the current point.

[0063] It should be noted that the linear relationship of the objective function of this application is affected by the decision variables. If the current time and the current flight distance in the decision variables of this application are continuous, then its objective function is linear; if the current speed and current energy consumption are discontinuous and change irregularly, then its objective function is nonlinear.

[0064] In order to avoid meaningless solutions and enhance the stability of the objective function, constraints are set for the objective function as follows:

[0065] , In the formula, S is the absolute constraint condition, is a relative constraint condition, Indicates the current speed at time i, and Represents the minimum speed and maximum speed respectively. represents the current time at time i, Indicates the total duration of the task. represents the current energy consumption at time i, and Represent the minimum energy consumption and the maximum energy consumption respectively. Indicates the current flight distance at time i, Indicates the total distance of the route. represents the current unit energy consumption at time i, Represents the energy consumption coefficient.

[0066] Among them, here and It indicates the minimum and maximum speed of the UAV during the entire mission. Those skilled in the art should understand and It must be greater than the minimum speed in the UAV's own performance parameters, and must be less than the maximum speed in the UAV's own performance parameters. When used in comprehensive objective functions or cumulative objective functions, it refers to the maximum time predicted based on the current speed of the drone. When used for the maximum objective function, it is the task duration of the specified target task. and It represents the minimum and maximum energy consumption of the UAV during the entire mission. Those skilled in the art should understand and It must be greater than the minimum energy consumption in the drone’s own performance parameters, and must be less than the maximum energy consumption in the drone’s own performance parameters. It is used to characterize the linear relationship between energy consumption and speed under uniform flight conditions. The value of k is different for different types of drones, different speeds, different air pressures, different wind resistances or different loads. Here, it is set to 2.133 for example. Those skilled in the art can test the k value in an ideal environment, or calculate the k value based on the performance parameters of the drone. The method for determining the k value is not specifically limited here.

[0067] This application will be and as well as and Setting it as the maximum value in the entire target mission can exclude the endpoint values ​​in the UAV performance parameters, avoid unnecessary calculations, and ensure the flight safety of the UAV.

[0068] In addition, in order to ensure the flight safety of the UAV, those skilled in the art may also add the take-off weight, flight altitude or maximum range of the UAV as constraints.

[0069] The initial solution set for the objective function may be the time and energy consumption required for a drone to complete a mission determined by a technician in this field based on experience or historical data.

[0070] The construction module 302 is used to construct a neighborhood according to the objective function and the constraints. The construction module 302 is specifically used to determine the value range of the decision variable according to the objective function and the constraints. The decision variable is used as the dimension and the value range is used as the scope to construct the search space. Specifically, the value range of each decision variable is calculated according to the above constraints. The decision variable is used as the dimension and the value range is used to construct the search space. Exemplarily, the present application has four decision variables, and the current speed, current energy consumption and current flight distance are used as the X-axis, Y-axis and Z-axis to construct a Cartesian coordinate system, and the current time is introduced into the Cartesian coordinate system to construct a four-dimensional space-time coordinate system to form a search space. In the search space, a series of spatial points are generated in the four-dimensional space-time coordinate system according to the value range of the decision variable, and each spatial point can be represented by a four-dimensional vector ( , , , ) is used to represent. Those skilled in the art will appreciate that It is the current time, which is relative to the take-off time.

[0071] Determine the variable distance between each spatial point in the search space. The spatial points whose variable distance meets the distance threshold constitute the neighborhood. Specifically, the calculation formula of the variable distance is as follows:

[0072] . In the formula, D represents the variable distance, Represents the balance coefficient, and its value is , represents the time difference between two spatial points, , and Represents the difference between two spatial points on the X-axis, Y-axis and Z-axis respectively. All spatial points within the distance threshold of a spatial point constitute the neighborhood of the spatial point. The distance threshold is exemplarily set to rice.

[0073] The iteration module 303 is used to determine the current point corresponding to the initial solution according to the objective function and the constraints, and iteratively execute the search step according to the scheduling strategy until the termination condition is reached to obtain the optimization result. Plan the target task according to the optimization result. Among them, the search step includes: determining the values ​​of all spatial points in the current neighborhood of the current point based on the objective function, and evaluating them. Update the current point according to the evaluation result, and execute the search step. The iteration module 303 is specifically used to reversely calculate the values ​​of the decision variables that meet the constraints according to the set initial solution using the objective function, and then use the value of one set of decision variables as the current point.

[0074] Based on the objective function, the values ​​of all spatial points in the current neighborhood of the current point are determined and evaluated. In an embodiment of the present application, the current neighborhood of the current point is determined, and the values ​​of all spatial points in the current neighborhood are calculated using the objective function. The values ​​of each calculated spatial point are evaluated and sorted to obtain an evaluation result.

[0075] Determine whether the iteration reaches the termination condition. In the embodiment of the present application, the termination condition includes: the scheduling strategy stops scheduling. And / or the search step reaches a preset number of iterations. And / or the adjacent current point meets the tolerance. Among them, the preset number of iterations is exemplarily set to 500. The adjacent current point meets the tolerance, which means that the searched current point has stabilized and is close to the optimal optimization result or has reached the expected optimization result.

[0076] If the iteration does not reach the termination condition, the current point is updated according to the evaluation result, and the values ​​of all spatial points in the current neighborhood of the current point are determined again based on the objective function according to the scheduling strategy, and they are evaluated to determine whether the iteration reaches the termination condition. If the iteration reaches the termination condition, the optimization result is obtained, and the target task is planned according to the optimization result.

[0077] Among them, the scheduling strategy is as follows Figure 2 As shown, the details are as follows.

[0078] Based on the distance threshold, the spatial points within the current neighborhood of the current point are determined. Specifically, all spatial points within the distance threshold range of the current point constitute the current neighborhood of the current point.

[0079] The objective function is used to determine the values ​​of all spatial points in the current neighborhood.

[0080] Evaluate the value of the spatial point. Specifically, evaluate and sort the calculated value of each spatial point to obtain an evaluation result.

[0081] Determine whether there is a spatial point with a value smaller than the current solution of the current point in the current neighborhood. Specifically, if there is a spatial point with a value smaller than the current solution of the current point in the current neighborhood, it means that the current point is not the optimal point in the current neighborhood. Continue searching in the current neighborhood and update the current point with the minimum value of the spatial point values.

[0082] If there is no spatial point with a value smaller than the current solution of the current point in the current neighborhood, it means that the current point is the optimal point in the current neighborhood, and it is determined whether the current neighborhood is equal to the search space and the distance threshold is increased.

[0083] Update the current point with the minimum value among the values ​​of the spatial points. Specifically, take the spatial point with the minimum value in the current neighborhood as the current point and continue to execute from the beginning.

[0084] Determine whether the current neighborhood is equal to the search space. Specifically, determine whether the range of the current neighborhood determined based on the current distance threshold is equal to the range of the search space. If the range of the current neighborhood determined based on the current distance threshold is equal to the range of the search space, it means that the maximum range of the solution of the objective function has been searched, and the optimal value in the search space can be obtained. Otherwise, increase the distance threshold.

[0085] Increase the distance threshold. In the embodiment of the present application, when performing the first search, an optimal point (the spatial point corresponding to the minimum value) can be found in each neighborhood. If there is no spatial point with a value smaller than the current solution of the current point in the neighborhood, the current neighborhood has been searched, and the distance threshold is increased to expand the neighborhood range of each spatial point for a second search. For example, the distance threshold increased here is rice.

[0086] In addition, in order to improve the search efficiency, after each search of a current neighborhood, the non-optimal spatial points in each current neighborhood are removed. In the second search, it is based on the optimal solution of each neighborhood in the first search, which greatly reduces the amount of calculation.

[0087] Update the current point according to the evaluation result. Specifically, take the spatial point corresponding to the minimum value among the spatial point values ​​as the current point, and then determine the values ​​of all spatial points in the current neighborhood of the current point based on the objective function based on the scheduling strategy, evaluate them, and determine whether the iteration reaches the termination condition.

[0088] The optimization result is obtained, and the target task is planned according to the optimization result. Specifically, the decision variables of the target task are set according to the obtained optimization result, and the optimal solution that meets the task requirements is obtained. That is, by balancing the current speed and the current energy consumption, the optimal solution that meets the task requirements (reducing time consumption, reducing energy consumption, or balancing time consumption and energy consumption) is obtained.

[0089] Some modules in the apparatus described in the present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0090] The devices or modules described in the above application embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described in various modules according to their functions. When implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware. Of course, the module that implements a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0091] The methods, devices or modules described in this application can be implemented in the form of computer-readable program codes. The controller can be implemented in any appropriate manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) that can be executed by the (micro)processor, logic gates, switches, application-specific integrated circuits (English: Application Specific Integrated Circuit; Abbreviation: ASIC), programmable logic controllers and embedded microcontrollers. Examples of controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program codes, the controller can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers and embedded microcontrollers by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included in it for implementing various functions can also be regarded as structures within the hardware component. Or even, the means for realizing various functions may be regarded as both a software module for realizing the method and a structure within a hardware component.

[0092] An embodiment of the present application further provides a device, comprising: a processor; a memory for storing processor executable instructions; when the processor executes the executable instructions, the method described in the embodiment of the present application is implemented.

[0093] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist independently, or two or more modules may be integrated into one module.

[0094] The above storage media include but are not limited to random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD) or memory card. The memory can be used to store computer program instructions.

[0095] It can be seen from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary hardware. Based on this understanding, the technical solution of the present application can be essentially or partly reflected in the prior art in the form of a software product, or it can be reflected in the implementation process of data migration. The computer software product can be stored in a storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0096] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. All or part of this application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, mobile communication terminals, multi-processor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0097] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some or all of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present application.

Claims

1. A nonlinear multi-objective mission planning method for unmanned aerial vehicles, characterized in that: include: Establish the objective function and constraints of the target task, and set the initial solution of the objective function; wherein the objective function is as follows: ; In the formula, represents the comprehensive objective function, represents the maximum objective function, represents the cumulative objective function, represents the decision variable, n represents the total duration of the route, represents the priority factor, It represents the ratio of the current time from the start time to time i to the total time of the route. represents the current unit energy consumption at time i, Represents the ratio of the current energy consumption at time i to the total energy consumption from the starting point to the current point; The constraints are as follows: , ; In the formula, S is the absolute constraint condition, is a relative constraint condition, Indicates the current speed at time i, and Represents the minimum speed and maximum speed respectively. represents the current time at time i, Indicates the total duration of the task. represents the current energy consumption at time i, and Represent the minimum energy consumption and the maximum energy consumption respectively. Indicates the current flight distance at time i, Indicates the total distance of the route. represents the current unit energy consumption at time i, represents the energy consumption coefficient; Constructing a neighborhood according to the objective function and the constraint condition includes: Determine the value range of the decision variable according to the constraint condition; construct a search space with the decision variable as the dimension and its value range as the range; wherein the decision variable includes the current speed, the current energy consumption, the current flight distance and the current time; construct a Cartesian coordinate system with the current speed, the current energy consumption and the current flight distance as the X-axis, the Y-axis and the Z-axis respectively, and introduce the current time into the Cartesian coordinate system to construct a four-dimensional space-time coordinate system to form a search space; in the search space, generate space points in the four-dimensional space-time coordinate system according to the value range of the decision variable; determine the variable distance between each of the space points in the search space; the space points whose variable distance meets the distance threshold constitute the neighborhood; Determine the current point corresponding to the initial solution according to the objective function and the constraint condition, and iterate the search step according to the scheduling strategy until the termination condition is reached to obtain an optimization result; Planning the target task according to the optimization result; Wherein, the searching step comprises: Determine the values ​​of all spatial points within the current neighborhood of the current point based on the objective function and evaluate them; Update the current point according to the evaluation result, and execute the search step; The scheduling strategy includes: Perform an evaluation step; the evaluation step includes: Determine the spatial points within a current neighborhood of the current point based on a distance threshold, and determine the values ​​of all the spatial points within the current neighborhood using the objective function; Evaluate the value of the spatial point, if the values ​​of the spatial points in the current neighborhood are all smaller than the current solution of the current point, update the current point with the minimum value of the values ​​of the spatial points, and perform the evaluation step once; If the values ​​of all the spatial points in the current neighborhood are greater than or equal to the current solution of the current point, the distance threshold is increased and the evaluation step is iteratively performed until the current neighborhood is equal to the search space.

2. The method according to claim 1, characterized in that The objective function of establishing the target task includes: Determine the function type of the objective function according to task requirements; Determining decision variables according to the target task; The objective function is constructed according to the function type and the decision variables.

3. The method according to claim 2, characterized in that The decision variables include current speed, current time, current energy consumption and current flight distance.

4. The method according to claim 1, characterized in that The termination conditions include: The scheduling strategy stops scheduling; and / or The searching step reaches a preset number of iterations; and / or The neighboring current point satisfies the tolerance.

5. A nonlinear multi-objective mission planning device for an unmanned aerial vehicle, characterized in that: include: The module is used to establish the objective function and constraint conditions of the target task and set the initial solution of the objective function; wherein the objective function is as follows: ; In the formula, represents the comprehensive objective function, represents the maximum objective function, represents the cumulative objective function, represents the decision variable, n represents the total duration of the route, represents the priority factor, It represents the ratio of the current time from the start time to time i to the total time of the route. represents the current unit energy consumption at time i, Represents the ratio of the current energy consumption at time i to the total energy consumption from the starting point to the current point; The constraints are as follows: , ; In the formula, S is the absolute constraint condition, is a relative constraint condition, Indicates the current speed at time i, and Represents the minimum speed and maximum speed respectively. represents the current time at time i, Indicates the total duration of the task. represents the current energy consumption at time i, and Represent the minimum energy consumption and the maximum energy consumption respectively. Indicates the current flight distance at time i, Indicates the total distance of the route. represents the current unit energy consumption at time i, represents the energy consumption coefficient; A construction module, used to construct a neighborhood according to the objective function and the constraint conditions, comprising: Determine the value range of the decision variable according to the constraint condition; construct a search space with the decision variable as the dimension and its value range as the range; wherein the decision variable includes the current speed, the current energy consumption, the current flight distance and the current time; construct a Cartesian coordinate system with the current speed, the current energy consumption and the current flight distance as the X-axis, the Y-axis and the Z-axis respectively, and introduce the current time into the Cartesian coordinate system to construct a four-dimensional space-time coordinate system to form a search space; in the search space, generate space points in the four-dimensional space-time coordinate system according to the value range of the decision variable; determine the variable distance between each of the space points in the search space; the space points whose variable distance meets the distance threshold constitute the neighborhood; An iteration module, used to determine the current point corresponding to the initial solution according to the objective function and the constraint conditions, and iteratively execute the search step according to the scheduling strategy until the termination condition is reached to obtain an optimization result; Planning the target task according to the optimization result; Wherein, the searching step comprises: Determine the values ​​of all spatial points within the current neighborhood of the current point based on the objective function and evaluate them; Update the current point according to the evaluation result, and execute the search step; The scheduling strategy includes: Perform an evaluation step; the evaluation step includes: Determine the spatial points within a current neighborhood of the current point based on a distance threshold, and determine the values ​​of all the spatial points within the current neighborhood using the objective function; Evaluate the value of the spatial point, if the values ​​of the spatial points in the current neighborhood are all smaller than the current solution of the current point, update the current point with the minimum value of the values ​​of the spatial points, and perform the evaluation step once; If the values ​​of all the spatial points in the current neighborhood are greater than or equal to the current solution of the current point, the distance threshold is increased and the evaluation step is iteratively performed until the current neighborhood is equal to the search space.

6. A device for executing a nonlinear multi-objective mission planning method for an unmanned aerial vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; When the processor executes the executable instructions, the method according to any one of claims 1 to 4 is implemented.