Evolutionary strategy-based energy-driven unmanned aerial vehicle trajectory optimization method and system

Abstract

The application provides an energy-driven unmanned aerial vehicle trajectory optimization method and system based on an evolutionary strategy, and relates to the technical field of unmanned aerial vehicles. The method comprises the following steps: defining total energy consumption and constraint violation functions of an unmanned aerial vehicle according to flight parameters of the unmanned aerial vehicle; constructing a fitness function according to the total energy consumption and the constraint violation functions; initializing a population to form an initial population; performing genetic operations on parent populations in the initial population by a hovering energy-saving strategy to generate a child population according to the fitness function; merging the child population and the parent populations to form a merged population; calculating the fitness of all individuals in the merged population and sorting the individuals in descending order according to the fitness; selecting a preset number of optimal individuals based on the result of the descending order to form a target population; outputting the target population as an optimal unmanned aerial vehicle energy consumption trajectory strategy until the fitness converges or a preset maximum number of generations is reached; and executing the optimal unmanned aerial vehicle energy consumption trajectory strategy.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a method and system for optimizing the trajectory of an energy-driven UAV based on an evolutionary strategy. Background Technology

[0002] In remote areas where vehicles are connected, insufficient ground communication coverage and difficulties in vehicle refueling hinder the efficient advancement of network services. Integrated air-ground networks provide crucial support for this. As mobile relay nodes in the air, drones need to provide road condition information, entertainment news, and emergency refueling services to vehicles traveling along spiraling freight routes or cross-valley logistics routes in complex terrains such as mountains and canyons. Their flight trajectories directly affect communication link quality, flight energy consumption, and mission service efficiency. Furthermore, they must dynamically adapt to vehicle trajectories to maintain stable service, placing higher demands on the flexibility of trajectory planning and energy consumption optimization capabilities.

[0003] In existing technologies, UAV trajectory planning algorithms have been applied in vehicle-to-everything (V2X) air-to-ground collaborative scenarios. These algorithms can achieve basic vehicle trajectory tracking through altitude calculation, building a communication bridge between vehicles and the ground network to ensure basic service transmission. Some algorithms possess conventional energy consumption calculation and trajectory adjustment functions, enabling them to complete predetermined flight planning tasks in simple terrain environments and meet the basic needs of air-to-ground collaboration in general scenarios.

[0004] However, the energy consumption assessment of existing technologies is singular, mostly calculating only the basic flight energy consumption, without comprehensively considering the energy consumption for smooth turning under complex terrain and the energy consumption for hovering in communication hotspots. This does not conform to the actual physical operation of UAVs. At the same time, traditional gradient-based algorithms are prone to getting trapped in local optima when facing high-dimensional, non-convex multi-constraint optimization problems, making it difficult to explore the global optimal trajectory. Summary of the Invention

[0005] To address the limitations of existing energy consumption assessment technologies, which often only calculate basic flight energy consumption without comprehensively considering energy consumption for smooth turning in complex terrain and hovering in communication hotspots, thus failing to reflect the actual physical operation of UAVs, and to address the technical issues that traditional gradient-based algorithms are prone to getting trapped in local optima when facing high-dimensional, non-convex, multi-constraint optimization problems, making it difficult to explore the globally optimal trajectory, this invention provides an energy-driven UAV trajectory optimization method and system based on an evolutionary strategy.

[0006] The technical solutions provided by the embodiments of the present invention are as follows: The first aspect of this invention provides a method for optimizing the trajectory of an energy-driven unmanned aerial vehicle based on an evolutionary strategy, comprising: S1: Obtain UAV flight parameters.

[0007] S2: Define the total energy consumption and constraint violation function of the UAV based on the UAV flight parameters.

[0008] S3: Construct a fitness function based on the total energy consumption of the drone and the constraint violation function.

[0009] S4: Initialize the population to form an initial population, where the initial individuals in the initial population are chromosomes of waypoints randomly generated in the solution space.

[0010] S5: Based on the fitness function, the parent population in the initial population is genetically manipulated using a hovering energy-saving strategy to generate the offspring population.

[0011] S6: Merge the offspring population and the parent population to form a merged population.

[0012] S7: Calculate the fitness of all individuals in the merged population and sort them in descending order according to their fitness.

[0013] S8: Based on the descending sorting results, select a preset number of optimal individuals to form the target population.

[0014] S9: Repeat steps S5 to S8 until the fitness converges or the preset maximum number of generations is reached, and output the target population as the optimal UAV energy consumption trajectory strategy.

[0015] S10: Execute the optimal UAV energy consumption trajectory strategy.

[0016] A second aspect of the present invention provides an energy-driven unmanned aerial vehicle trajectory optimization system based on an evolutionary strategy, comprising: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the energy-driven unmanned aerial vehicle trajectory optimization method based on an evolutionary strategy as described in the first aspect.

[0017] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the energy-driven unmanned aerial vehicle trajectory optimization method based on an evolutionary strategy as described in the first aspect.

[0018] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, a fitness function is constructed based on the total energy consumption of the UAV and the constraint violation function. It comprehensively considers the energy consumption of smooth turning under complex terrain and the energy consumption of hovering in communication hotspots, and can evaluate energy consumption from multiple dimensions. At the same time, by repeating the iterative process until the fitness converges or reaches the preset maximum number of generations, the global optimal trajectory can be explored, overcoming the limitations of traditional gradient algorithms. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an energy-driven UAV trajectory optimization method based on an evolutionary strategy, provided as an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of an energy-driven unmanned aerial vehicle trajectory optimization system based on an evolutionary strategy, provided as an embodiment of the present invention. Detailed Implementation

[0022] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0023] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0024] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0025] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0026] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0027] Reference manual attached Figure 1 The diagram shows a flowchart of an energy-driven UAV trajectory optimization method based on an evolutionary strategy provided by an embodiment of the present invention.

[0028] This invention provides a method for optimizing the trajectory of an energy-driven unmanned aerial vehicle (UAV) based on an evolutionary strategy. This method can be implemented by an energy-driven UAV trajectory optimization device based on an evolutionary strategy, which can be a terminal or a server. The processing flow of the energy-driven UAV trajectory optimization method based on an evolutionary strategy may include the following steps: S1: Obtain UAV flight parameters.

[0029] S2: Define the total energy consumption and constraint violation function of the UAV based on the UAV flight parameters.

[0030] Optionally, the total energy consumption of the drone can be calculated as follows: ; ; ; ; in, E base This indicates the basic energy consumption of the drone. w ip Indicates the induced power coefficient. m Indicates the quality of the drone. g Represents gravitational acceleration. r Indicates air density, R p This indicates the radius of the drone's propeller. w pp Indicates the parasitic drag coefficient. v Indicates the flight speed of the drone. t Represents the integral variable. E smooth This indicates the energy consumption for smooth turning of the drone. F Indicates the trajectory of the drone. w s This represents the weighting factor for smooth cornering. N seg Indicates the number of trajectory segments. i a Indicates the first a The angle between adjacent trajectory segments E hover This indicates the hovering energy consumption of the drone. p hover This indicates the hovering power of the drone. t hover This indicates the total hovering time of the drone. E total This indicates the total power consumption of the drone. t Indicates the time.

[0031] The basic energy consumption of drones mainly consists of inductive energy consumption and parasitic energy consumption to overcome gravity and air resistance.

[0032] Among them, the constraint violation function is the core quantitative tool to ensure the compliance of UAV trajectory. It is specifically designed for the safety and communication needs of air-ground collaborative scenarios in remote areas. It covers three types of constraints: safe altitude, safe distance between UAVs, and basic communication rate between UAVs and vehicles. It forms a corresponding function expression by quantifying the degree to which the trajectory scheme deviates from the requirements of each constraint. When the function value is negative, it indicates that the current trajectory of the UAV meets the requirements of that type of constraint. Otherwise, it indicates that there is a violation. Finally, it is incorporated into the construction of the fitness function together with the total energy consumption of the UAV.

[0033] It should be noted that the energy consumption during smooth cornering is introduced. E smooth To encourage a smooth trajectory, hovering energy consumption is introduced. E hover To adapt to the dynamic characteristics of terrain conditions and vehicle trajectories.

[0034] Optionally, the formula for calculating the constraint violation function is as follows: ; ; ; in, CV h Indicates the safe altitude. F Indicates the trajectory of the drone. h safe This indicates the safe altitude for the drone; "min" means taking the minimum value. z i Indicates the first i Flight altitude of each trajectory segment i =1,2,…, N seg , N seg Indicates the number of trajectory segments. CV d Indicates safe distance. d safe Indicates the safe distance between drones. d s Indicates the instantaneous distance between drones. CV R Indicates the basic communication rate. R base This indicates the basic rate of communication between the drone and the vehicle. R This indicates the instantaneous rate of communication between the drone and the vehicle.

[0035] In this embodiment of the invention, the total energy consumption calculation comprehensively considers basic energy consumption (including inductive and parasitic energy consumption), smooth turning energy consumption, and hovering energy consumption. It not only fully covers the basic energy consumption of the UAV in overcoming gravity and air resistance, but also guides the generation of a smoother trajectory through smooth turning energy consumption to reduce additional energy consumption. Hovering energy consumption is used to adapt to the dwell requirements of complex terrain and vehicle dynamic trajectory, making the energy consumption assessment more in line with the actual physical operation scenario. The constraint violation function specifically quantifies the compliance degree of three core constraints: safe altitude, inter-machine spacing, and communication rate, providing a clear judgment standard for the safety of trajectory scheme and communication stability.

[0036] S3: Construct a fitness function based on the total energy consumption of the drone and the constraint violation function.

[0037] Among them, the fitness function is the core judgment criterion for guiding the evolution and optimization of UAV trajectory. It is constructed to closely integrate the needs of air-ground collaborative scenarios in remote areas, and integrates the total energy consumption of UAVs and the constraint violation function. The function expression is formed by quantitatively integrating "energy consumption minimization" and "constraint compliance".

[0038] Optionally, the fitness function is as follows: ; in, F Represents the fitness function. F Indicates the trajectory of the drone. E total This indicates the total power consumption of the drone. CV h / d / R Indicates the constraint violation function, CV h Indicates the safe altitude. CV d Indicates safe distance. CV R This indicates the basic communication rate.

[0039] In this embodiment of the invention, the optimization objective of "minimizing energy consumption" and the basic requirement of "constraint compliance" are precisely quantified and integrated to form a unified and scenario-appropriate trajectory scheme judgment standard. This ensures that optimization always focuses on the core requirement of low energy consumption by directly linking total energy consumption, and clarifies the compliance boundaries of safety and communication by incorporating constraint violation functions. Furthermore, the weight ratio of total energy consumption and the constraint violation penalty coefficient are adapted to the flight characteristics of complex terrain in remote areas.

[0040] S4: Initialize the population to form an initial population, where the initial individuals in the initial population are chromosomes of waypoints randomly generated in the solution space.

[0041] It should be noted that the solution space is randomly generated by... N seg Chromosomes of each waypoint F p , N pop The initial population consists of 1 chromosome.

[0042] The initial population is specifically as follows: ; in, Indicates the initial population. F p Represents the first in the initial population p Individual, p =1,2,…, N pop , N pop This indicates the initial population size.

[0043] In this embodiment of the invention, chromosomes containing waypoints are randomly generated within the solution space as initial individuals, so as to... N pop The initial population, composed of individuals, can fully cover the potential solution space of the UAV trajectory, ensuring a rich diversity of trajectory schemes in the initial stage and effectively avoiding the optimization process from falling into local optima too early due to the limitations of the initial solution. At the same time, each initial individual is composed of waypoint chromosomes as the core, which is highly adaptable to subsequent genetic operations (crossover, mutation) and hovering energy-saving strategies, and can be directly used as the basic material for iterative optimization.

[0044] S5: Based on the fitness function, the parent population in the initial population is genetically manipulated using a hovering energy-saving strategy to generate the offspring population.

[0045] Among them, the hovering energy-saving strategy randomly selects a continuous waypoint of length L in the trajectory after the mutation operation in the offspring population generation stage, and sets its coordinates to the same point to form a hovering state. This can not only avoid the additional energy consumption caused by the UAV frequently adjusting its trajectory, but also specifically adapt to the dwell service needs of communication hotspot areas. It echoes the comprehensive energy consumption model that includes hovering energy consumption, and helps to reduce the total energy consumption of UAVs by exploring energy-saving dwell modes, while providing a better energy consumption assessment basis for the fitness function.

[0046] Genetic manipulation specifically includes selection, crossover, and mutation.

[0047] Optionally, the calculation method for the hovering energy-saving strategy is as follows: ; in, wp j Indicates the first j Coordinates of the waypoints wp l Indicates the firstl The coordinates of the hovering point j Indicates the index of a waypoint. l Indicates the starting index of the hover segment. L h Indicates the length of the hover segment.

[0048] In one possible implementation, S5 specifically includes sub-steps S501 to S505: S501: Based on the fitness function, the individuals with the highest fitness are selected through a tournament selection method to serve as the parent population.

[0049] Among them, the tournament selection method is a selection operation used to select high-quality individuals from the current population, specifically adapted to the characteristics of multi-constraint, high-dimensional solution space in UAV trajectory optimization scenarios. The specific process starts from the... g In each generation of the population, the size of each random sampling is T n candidate subset T k By comparing the fitness function values ​​(a quantitative indicator that combines energy consumption and constraint compliance) of each individual in the subset, the individual with the optimal fitness (the smallest value) is selected; this process is repeated. N r Next, finally obtained N r A mating pool is formed by high-quality individuals. Through random sampling and local competition, both high-quality genes in the population can be preserved and individual diversity can be maintained, avoiding the optimization process from getting trapped in local optima too early, and ensuring that the drone trajectory scheme evolves towards global low energy consumption and high compliance.

[0050] It should be noted that the tournament selection method was used from the first... g Initial population p g Individuals with high fitness, especially those with low energy consumption and minimal or no violation of constraints, are selected as the parent population.

[0051] Furthermore, from the first g Initial population p g Randomly selected from T N From each individual, the one with the highest fitness is selected and placed into the mating pool, and this process is repeated. N r Next, specifically: ; ; in, p g Indicates the first g Initial population, S(p g ) indicates that the tournament selection operation is performed from the first g A collection of high-quality individuals selected from the population. Indicates the first k The tournament selected the first Individual, The index represents the individual, and argmax represents the function for finding the maximum value. T k Indicates the first k The subset of candidate individuals for the next tournament, F( F i ) represents an individual F i The fitness function value, N r Indicates the number of times the selection operation was performed. N pop Indicates the initial population size. T N This indicates the number of individuals in the initial population.

[0052] S502: Perform a simulated binary crossover operation on the parent population to generate offspring individuals.

[0053] In one possible implementation, the simulated binary crossover operation on the parent population is specifically performed as follows: ; ; ; in, β Indicates the cross coefficient. u Represents uniformly random numbers. or c Indicates the cross-distribution index. p c Indicates the crossover probability. c 1 Indicates the first generation individual. p 1 Represents the first parent individual. p 2 Indicates the second parent individual. c 2 This refers to the second-generation offspring.

[0054] S503: Perform gene-by-gene polynomial mutation on offspring individuals to obtain mutated offspring individuals.

[0055] In one possible implementation, the gene-by-gene polynomial mutation operation on offspring individuals is specifically performed as follows: ; ; in, c m This represents the offspring individuals to be mutated. F i Indicates the first i Individual gene values, Δ i Indicates the first i One mutation amount, r i Indicates the first i Each mutation determines a random number. p m This represents the probability of mutation in offspring individuals. r This indicates the calculation of random numbers based on the variance. or m This represents the distribution index of individual variation in offspring.

[0056] S504: Select the trajectory of a preset length of individual from the mutated offspring as continuous waypoints.

[0057] Those skilled in the art can set the preset length according to actual needs, and the present invention does not limit this.

[0058] S505: By using a hovering energy-saving strategy, the coordinates of consecutive waypoints are set to the same point to form a hovering state, thus obtaining the offspring population.

[0059] In this embodiment of the invention, by using the fitness function as a guide, a hovering energy-saving strategy is integrated with a complete genetic operation process to generate the offspring population, bringing multi-dimensional advantages. From the perspective of genetic operations, the tournament selection method selects high-fitness parent individuals through local competition, which not only retains high-quality genes with low energy consumption and high compliance, but also maintains population diversity to avoid local optima; simulated binary crossover promotes the fusion of excellent parental traits through parameter recombination, while polynomial mutation introduces appropriate variation to explore new trajectory spaces. Both work together to improve the solution space coverage and optimization potential of the offspring population. The hovering energy-saving strategy sets consecutive waypoints to the same point after mutation to form a hovering state, which not only reduces the extra energy consumption of frequent trajectory adjustments, but also accurately adapts to the dwell requirements of communication hotspot areas, echoing the comprehensive energy consumption model.

[0060] S6: Merge the offspring population and the parent population to form a merged population.

[0061] S7: Calculate the fitness of all individuals in the merged population and sort them in descending order according to their fitness.

[0062] In this embodiment of the invention, the fitness of all individuals in the merged population is calculated and sorted in descending order. On the one hand, the evaluation and sorting are carried out based on a unified fitness function to ensure that the criteria for judging the quality of all individuals are consistent, avoiding screening bias caused by differences in evaluation dimensions. Moreover, the descending order can intuitively highlight high-fitness (low energy consumption, high compliance) high-quality individuals. On the other hand, the sorting results provide a clear and efficient basis for the subsequent screening of the next generation of populations, which can quickly identify core advantageous individuals, ensuring the stable inheritance of high-quality genes and eliminating redundant individuals with poor fitness, thereby improving the efficiency and targeting of iterative optimization.

[0063] S8: Based on the descending sorting results, select a preset number of optimal individuals to form the target population.

[0064] Those skilled in the art can set the preset quantity according to actual needs, and the present invention does not limit this.

[0065] In this embodiment of the invention, a preset number of optimal individuals are selected to form a target population, which can accurately lock the core high-quality individuals with low energy consumption and high constraint compliance in each iteration, ensuring the stable inheritance of the excellent genes of the previous generation population and avoiding the loss of high-quality trajectory schemes in the iteration.

[0066] S9: Repeat steps S5 to S8 until the fitness converges or the preset maximum number of generations is reached, and output the target population as the optimal UAV energy consumption trajectory strategy.

[0067] Those skilled in the art can set the maximum number of algebras according to actual needs, and this invention does not limit that.

[0068] In this embodiment of the invention, multiple iterations allow the population to continuously undergo a closed loop of "high-quality selection - gene recombination - mutation exploration - energy-saving adaptation - optimal retention," continuously accumulating excellent characteristics of low energy consumption and high constraint compliance, driving the trajectory scheme to gradually approach the global optimum, effectively compensating for the limitations of local optima that may exist in a single optimization; setting dual termination conditions of "fitness convergence" and "preset maximum number of generations" ensures both the optimization effect (a stable optimal solution has been obtained at convergence) and flexible control of computational costs (avoiding infinite iteration), adapting to the balance requirements of optimization accuracy and efficiency in different scenarios.

[0069] S10: Execute the optimal UAV energy consumption trajectory strategy.

[0070] Reference manual attached Figure 2 The diagram shows a schematic of the structure of an energy-driven UAV trajectory optimization system based on an evolutionary strategy provided by the present invention.

[0071] The present invention also provides an energy-driven UAV trajectory optimization system 20 based on an evolutionary strategy, applied to the above-mentioned energy-driven UAV trajectory optimization method based on an evolutionary strategy, comprising: Processor 201.

[0072] The memory 202 stores computer-readable instructions, which, when executed by the processor 201, implement the energy-driven UAV trajectory optimization method based on an evolutionary strategy as described in the method embodiment.

[0073] The energy-driven UAV trajectory optimization system 20 based on evolutionary strategy provided by the present invention can execute the above-mentioned energy-driven UAV trajectory optimization method based on evolutionary strategy and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0074] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0075] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0076] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0077] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0078] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0079] It should be understood that, in various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0080] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0081] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0082] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0083] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0085] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0086] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the energy-driven UAV trajectory optimization method based on an evolutionary strategy as described in the method embodiment.

[0087] The present invention provides a computer-readable storage medium that can implement the steps and effects of the energy-driven UAV trajectory optimization method based on the evolutionary strategy described in the above method embodiments. To avoid repetition, the present invention will not repeat the details.

[0088] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0089] The following points need to be explained: (1) The accompanying drawings of the embodiments of the present invention only involve the structures involved in the embodiments of the present invention. Other structures can refer to the general design.

[0090] (2) For clarity, the thickness of layers or regions is enlarged or reduced in the drawings used to describe embodiments of the invention, i.e., these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element or there may be intermediate elements.

[0091] (3) Where there is no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0092] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for optimizing the trajectory of an energy-driven unmanned aerial vehicle based on an evolutionary strategy, characterized in that, include: S1: Obtain UAV flight parameters; S2: Define the total energy consumption and constraint violation function of the UAV based on the UAV flight parameters; S3: Construct a fitness function based on the total energy consumption of the UAV and the constraint violation function; S4: Initialize the population to form an initial population, wherein the initial individuals in the initial population are chromosomes of waypoints randomly generated in the solution space; S5: Based on the fitness function, genetic operations are performed on the parent population in the initial population using a hovering energy-saving strategy to generate the offspring population; S6: Merge the offspring population and the parent population to form a merged population; S7: Calculate the fitness of all individuals in the merged population, and sort the individuals in descending order according to the fitness. S8: Based on the descending sorting results, select a preset number of optimal individuals to form the target population; S9: Repeat steps S5 to S8 until the fitness converges or reaches the preset maximum number of generations, and output the target population as the optimal UAV energy consumption trajectory strategy. S10: Execute the optimal UAV energy consumption trajectory strategy.

2. The energy-driven UAV trajectory optimization method based on evolutionary strategy according to claim 1, characterized in that, The calculation method for the total energy consumption of the drone is as follows: ； ； ； ； in, E base This indicates the basic energy consumption of the drone. w ip Indicates the induced power coefficient. m Indicates the quality of the drone. g Represents gravitational acceleration. ρ Indicates air density, R p This indicates the radius of the drone's propeller. w pp Indicates the parasitic drag coefficient. v Indicates the flight speed of the drone. τ Represents the integral variable. E smooth This indicates the energy consumption for smooth turning of the drone. Φ Indicates the trajectory of the drone. w s This represents the weighting factor for smooth cornering. N seg Indicates the number of trajectory segments. θ a Indicates the first a The angle between adjacent trajectory segments E hover This indicates the hovering energy consumption of the drone. p hover This indicates the hovering power of the drone. t hover This indicates the total hovering time of the drone. E total This indicates the total power consumption of the drone. t Indicates the time.

3. The energy-driven UAV trajectory optimization method based on evolutionary strategy according to claim 1, characterized in that, The specific formula for calculating the constraint violation function is as follows: ； ； ； in, CV h Indicates the safe altitude. Φ Indicates the trajectory of the drone. h safe This indicates the safe altitude for the drone; "min" means taking the minimum value. z i Indicates the first i Flight altitude of each trajectory segment i =1,2,…, N seg , N seg Indicates the number of trajectory segments. CV d Indicates safe distance. d safe Indicates the safe distance between drones. d s Indicates the instantaneous distance between drones. CV R Indicates the basic communication rate. R base This indicates the basic rate of communication between the drone and the vehicle. R This indicates the instantaneous rate of communication between the drone and the vehicle.

4. The energy-driven UAV trajectory optimization method based on evolutionary strategy according to claim 1, characterized in that, The fitness function is specifically: ； in, F Represents the fitness function. Φ Indicates the trajectory of the drone. E total This indicates the total power consumption of the drone. CV h / d / R Indicates the constraint violation function, CV h Indicates the safe altitude. CV d Indicates safe distance. CV R This indicates the basic communication rate.

5. The energy-driven UAV trajectory optimization method based on evolutionary strategy according to claim 1, characterized in that, S5 specifically includes: S501: Based on the fitness function, the individual with the highest fitness is selected as the parent population through a tournament selection method; S502: Perform a simulated binary crossover operation on the parent population to generate offspring individuals; S503: Perform gene-by-gene polynomial mutation on the offspring individuals to obtain mutated offspring individuals; S504: Select an individual trajectory of a preset length from the mutated offspring individuals as a continuous waypoint; S505: By using the hovering energy-saving strategy, the coordinates of the continuous waypoints are set to the same point to form a hovering state, and the offspring population is obtained.

6. The energy-driven UAV trajectory optimization method based on evolutionary strategy according to claim 5, characterized in that, The specific method for simulating binary crossover in the parent population is as follows: ； ； ； in, β Indicates the cross coefficient. u Represents uniformly random numbers. η c Indicates the cross-distribution index. p c Indicates the crossover probability. c 1 Indicates the first generation individual. p 1 Represents the first parent individual. p 2 Indicates the second parent individual. c 2 This refers to the second-generation offspring.

7. The energy-driven UAV trajectory optimization method based on an evolutionary strategy according to claim 5, characterized in that, The specific method for performing gene-by-gene polynomial mutation on the offspring individuals is as follows: ； ； in, c m This represents the offspring individuals to be mutated. Φ i Indicates the first i Individual gene values, Δ i Indicates the first i One mutation amount, r i Indicates the first i Each mutation determines a random number. p m This represents the probability of mutation in offspring individuals. r This indicates the calculation of random numbers based on the variance. η m This represents the distribution index of individual variation in offspring.

8. The energy-driven UAV trajectory optimization method based on evolutionary strategy according to claim 1, characterized in that, The calculation method for the hovering energy-saving strategy is as follows: ； in, wp j Indicates the first j Coordinates of the waypoints wp l Indicates the first l The coordinates of the hovering point j Indicates the index of a waypoint. l Indicates the starting index of the hover segment. L h Indicates the length of the hover segment.

9. A trajectory optimization system for energy-driven unmanned aerial vehicles based on an evolutionary strategy, characterized in that, include: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the energy-driven unmanned aerial vehicle trajectory optimization method based on an evolutionary strategy as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the energy-driven unmanned aerial vehicle trajectory optimization method based on an evolutionary strategy as described in any one of claims 1 to 8.

Images