Unmanned aerial vehicle track planning method and system based on radio map in wind field environment

Abstract

The invention discloses an unmanned aerial vehicle (UAV) trajectory planning method and system based on a radio map in a wind field environment. The method comprises the following steps: acquiring radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; according to the radio map and the wind field vector model, a weighted directed graph is solved, and the weighted directed graph is used for storing energy consumption of each path; and initializing an unmanned aerial vehicle access sequence based on the weighted directed graph, and optimizing the initial unmanned aerial vehicle access sequence by adopting a genetic algorithm to obtain an optimal unmanned aerial vehicle access sequence. The access sequence of the unmanned aerial vehicles is initialized based on the weighted directed graph, and the initial access sequence of the unmanned aerial vehicles is optimized by adopting a genetic algorithm to obtain the optimal access sequence of the unmanned aerial vehicles. The task energy consumption of the unmanned aerial vehicle in the wind field environment can be obtained through the radio map and the wind field vector model, and then the distribution sequence and the unmanned aerial vehicle trajectory are reasonably set to improve the distribution efficiency on the premise that the communication quality of the unmanned aerial vehicle meets the requirement.

Description

Technical Field

[0001] The present invention belongs to the field of path planning, and particularly relates to a method and system for unmanned aerial vehicle (UAV) trajectory planning based on a radio map in a wind field environment. Background Art

[0002] As a key part of the low-altitude economy, UAVs have achieved technological penetration in multiple fields with their high mobility and flexible deployment capabilities. In recent years, against the backdrop of the surging express delivery volume driven by e-commerce, the urban last-mile logistics network is facing the dual challenges of energy efficiency optimization and spatio-temporal resource coordination. Compared with the traditional manual delivery mode, UAV systems exhibit comparative advantages such as low space occupancy ratio, controllable unit transportation cost, and vertical takeoff and landing flexibility; compared with ground unmanned vehicles, their airspace penetration ability can avoid the topological constraints of road traffic and achieve vertical crossing of complex terrains (such as waters, mountains, etc.), providing a new technical path for constructing the logistics network. Therefore, applying UAVs to the logistics industry has good prospects.

[0003] However, when a UAV is forced to adjust its flight altitude to maintain communication quality (such as crossing a signal attenuation area), it may simultaneously enter an adverse wind field area (such as a low-altitude turbulent layer), resulting in a decision conflict between communication guarantee and energy efficiency. Traditional methods, such as geometric planning methods based on straight lines or circles, planning methods based on TSP, etc., cannot solve the above conflicts, leading to low efficiency in communication resource allocation and trajectory optimization, as well as additional energy consumption of UAVs, which may trigger flight accidents. Summary of the Invention

[0004] To solve the above problems existing in the prior art, the present invention provides a method and system for UAV trajectory planning based on a radio map in a wind field environment. The technical problems to be solved by the present invention are achieved through the following technical solutions: A method for UAV trajectory planning based on a radio map in a wind field environment, comprising: Obtaining radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; Solving a weighted directed graph according to the radio map and the wind field vector model, wherein the weighted directed graph is used to store the energy consumption of each path; Initializing the UAV access order based on the weighted directed graph, and optimizing the initial UAV access order using a genetic algorithm to obtain the optimal UAV access order.

[0005] In a specific embodiment, the UAV initialization parameters include: hangar position, source user node set, destination user node set, UAV flight altitude range, UAV flight horizontal range, and UAV flight speed; Correspondingly, the wind vector model is: = + , where is the ground speed of the UAV, is the airspeed of the UAV relative to the air, is the wind speed, , is the wind speed of the absolute value, is the wind speed and the angle with the positive horizontal axis.

[0006] In a specific embodiment, solving the weighted directed graph according to the radio map and the wind field vector model includes: Obtaining the vertex set and edge set of the weighted directed graph to obtain the weight expression for the UAV to fly between any two points, where the weight is determined by the flight path and the UAV energy consumption corresponding to the flight path; Converting the solution of the weight into the solution of the mobile cost function; where the mobile cost function is determined by the UAV energy consumption and the UAV signal strength, the UAV energy consumption and the UAV signal strength are related to the flight time, and the flight time is related to the wind field vector model; Traversing each source user node set to obtain the solution of the mobile cost function that satisfies the preset conditions between any two points to obtain the minimum energy consumption path; Storing each of the minimum energy consumption paths to obtain a weighted directed graph.

[0007] In a specific embodiment, the mobile cost function is: ; where where E(v,t) represents the instantaneous energy consumption of the UAV, represents the airspeed of the UAV, represents the flight time of the UAV, represents the signal-to-noise ratio at the location of the UAV, represents whether the SNR value defining a certain place reaches the threshold allowing the UAV to pass, , indicating that the mission allows the UAV to pass, otherwise the UAV is not allowed to pass.

[0008] In a specific embodiment, initializing the UAV access order based on the weighted directed graph includes: Obtaining the source user node set and the destination user node set to obtain a number of UAV user groups, where each UAV user group includes a source user node and a destination user node; Set an initial policy to process each drone user group to obtain the original drone access order, where the original drone access order is the source user node and the destination user node in sequence; Determine whether the remaining payload margin of the drone satisfies continuous access to the next source user node. If so, calculate the full-segment energy consumption when continuously accessing the next source user node according to the weighted directed graph, and when the energy consumption when continuously accessing the next source user node is greater than the current energy consumption, use the drone access order corresponding to the current energy consumption as the initial drone access order.

[0009] In a specific embodiment, a genetic algorithm is used to optimize the initial drone access order to obtain the optimal drone access order, including: Generate an initial drone chromosome according to the initial drone access order; Use the tournament selection method to perform crossover, mutation, and replication operations on the initial drone chromosome to obtain offspring individuals; Iteratively calculate the fitness of each parent individual and offspring individual, and use the sequence order of the drone chromosome with the optimal fitness function as the optimal drone access order, where the fitness function is determined by the path energy consumption of the drone flying in the wind field.

[0010] The present invention also discloses a radio map-based drone trajectory planning system for a wind field environment, including: An initialization module for obtaining radio map initialization parameters and drone initialization parameters to generate a radio map and a wind vector model; A weighted directed graph generation module for solving a weighted directed graph according to the radio map and the wind field vector model, where the weighted directed graph is used to store the energy consumption of each path; A drone access order optimization module for initializing the drone access order based on the weighted directed graph and using a genetic algorithm to optimize the initial drone access order to obtain the optimal drone access order.

[0011] In a specific embodiment, the weighted directed graph generation module includes: A weight expression calculation unit for obtaining the vertex set and edge set of the weighted directed graph to obtain the weight expression for the drone to fly between any two points, where the weight is determined by the flight path and the drone energy consumption corresponding to the flight path; A mobile cost function solving unit for converting the solution of the weight into the solution of a mobile cost function; where the mobile cost function is determined by the drone energy consumption and the drone signal strength, the drone energy consumption and the drone signal strength are related to the flight time, and the flight time is related to the wind field vector model; The minimum energy consumption path calculation unit is used to traverse each source user node set to obtain the solution of the moving cost function that meets the preset conditions between any two points, so as to obtain the minimum energy consumption path; The weighted directed graph generation unit is used to store each of the minimum energy consumption paths to obtain a weighted directed graph.

[0012] In a specific embodiment, the UAV access order optimization module specifically includes: The UAV user group generation unit is used to obtain the source user node set and the destination user node set to obtain a number of UAV user groups, where each UAV user group includes a source user node and a destination user node; The original UAV access order processing unit is used to set an initial policy to process each UAV user group to obtain the original UAV access order, where the original UAV access order is the source user node and the destination user node in sequence; The initial UAV access order calculation unit is used to determine whether the remaining effective payload margin of the UAV meets the requirement of continuously accessing the next source user node. If so, it calculates the full-section energy consumption when continuously accessing the next source user node according to the weighted directed graph, and when the energy consumption when continuously accessing the next source user node is greater than the current energy consumption, it takes the UAV access order corresponding to the current energy consumption as the initial UAV access order.

[0013] In a specific embodiment, the UAV access order optimization module further includes: The chromosome initialization unit is used to generate an initial UAV chromosome according to the initial UAV access order; The offspring individual generation unit is used to perform crossover, mutation and replication operations on the initial UAV chromosome by using the tournament selection method to obtain offspring individuals; The optimal UAV access order optimization unit is used to iteratively calculate the fitness of each parent individual and offspring individual, and take the sequence order of the UAV chromosome with the optimal fitness function as the optimal UAV access order, where the fitness function is determined by the path energy consumption of the UAV flying in the wind field.

[0014] The beneficial effects of the present invention: The method for planning the trajectory of an unmanned aerial vehicle (UAV) based on a radio map in a wind field environment according to the present invention includes: obtaining radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; solving a weighted directed graph according to the radio map and the wind field vector model, wherein the weighted directed graph is used to store the energy consumption of each path; initializing the UAV access order based on the weighted directed graph, and optimizing the initial UAV access order by using a genetic algorithm to obtain the optimal UAV access order. In this way, the energy consumption of the UAV task in the wind field environment can be obtained through the radio map and the wind field vector model, and then the delivery order and the UAV trajectory can be reasonably set to improve the delivery efficiency on the premise that the communication quality of the UAV meets the requirements.

[0015] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flowchart of a method for planning the trajectory of an unmanned aerial vehicle (UAV) based on a radio map in a wind field environment provided by an embodiment of the present invention; Figure 2 is a block diagram of a system module for planning the trajectory of an unmanned aerial vehicle (UAV) based on a radio map in a wind field environment provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The present invention will be further described in detail below with reference to specific embodiments, but the embodiments of the present invention are not limited thereto.

[0018] Embodiment 1 Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for planning the trajectory of an unmanned aerial vehicle (UAV) based on a radio map in a wind field environment provided by an embodiment of the present invention, and includes: S1. Obtain radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; The radio map initialization parameters mainly include the discretization accuracy , the number of base stations m, and the measured data ; the UAV initialization parameters mainly include: the location of the hangar , the set of source user nodes , the set of destination user nodes , the UAV flight altitude range , the UAV flight horizontal range W×W, and the UAV flight speed ; Correspondingly, the wind vector model is: = + , where is the ground speed of the UAV, is the relative airspeed of the UAV, is the wind speed, , is the wind speed of the absolute value, is the wind speed and the angle between the positive horizontal axis.

[0019] S2. Solve the weighted directed graph according to the radio map and the wind field vector model, wherein the weighted directed graph is used to store the energy consumption of each path; In a specific embodiment, solving the weighted directed graph according to the radio map and the wind field vector model includes: S21. Obtain the vertex set and edge set of the weighted directed graph to obtain the weight expression for the UAV to fly between any two points, wherein the weight is determined by the flight path and the UAV energy consumption corresponding to the flight path; It should be noted that the weighted directed graph is a mathematical model used to describe the directional and weighted relationships. It consists of a set of vertices (nodes) and a set of directed edges (arcs). Each edge has a specific direction, pointing from one vertex to another. In addition, each edge is attached with a numerical weight, which is usually used to represent a certain quantitative relationship between two vertices, such as time, cost or distance, etc. In this embodiment, the vertex set of the weighted directed graph is expressed as: where and respectively represent the starting point and the ending point.

[0020] The edge set can be expressed as: The weight of each edge can be given by the following formula: , where represents and the distance between, represents the energy consumed per unit time when the UAV flies along the edge , the above formula shows that the weight when the UAV flies along the edge is not equal to the weight when flying along the edge .

[0021] S22. Convert the solution of the weight into the solution of the movement cost function; wherein, the movement cost function is determined by the UAV energy consumption and the UAV signal strength, the UAV energy consumption and the UAV signal strength are related to the flight time, and the flight time is related to the wind field vector model; <H To filter out the flight paths that meet the communication requirements, a function is defined in this embodiment: In this embodiment, the movement cost is defined as: , where E(v,t) represents the instantaneous energy consumption of the UAV, represents the airspeed of the UAV, represents the flight time of the UAV, represents the signal-to-noise ratio at the location of the UAV, represents determining whether the SNR value at a certain location reaches the threshold allowing the UAV to pass, , indicating that the mission allows the UAV to pass, otherwise it does not allow the UAV to pass.

[0022] This indicates that at time t, if the signal strength at the location of the UAV is less than the threshold , then the movement cost at this location is regarded as infinite, meaning the UAV is not allowed to pass through here.

[0023] And under the influence of the wind field, there is: The distance between any two points is known, so .

[0024] To ensure that the UAV can start from the starting point , traverse all cruise points and finally fly to the end point , and will not traverse itself, the following constraints are also required: .

[0025] S23. Traverse each source user node set to obtain the solutions of the movement cost function between any two points that meet the preset conditions to obtain the minimum energy consumption path; S24. Store each of the minimum energy consumption paths to obtain a weighted directed graph.

[0026] S3. Initialize the UAV access order based on the weighted directed graph, and use the genetic algorithm to optimize the initial UAV access order to obtain the optimal UAV access order.

[0027] In a specific implementation manner, initializing the UAV access order based on the weighted directed graph includes: S31. Obtain the source user node set and the destination user node set to obtain several UAV user groups, where each UAV user group includes a source user node and a destination user node; In this embodiment, the source user node refers to the drone pick-up node, and the destination user node refers to the drone delivery node. The source user node and the destination user node appear in pairs. In some examples, it may also include a drone hangar, that is, the initial node before the drone picks up goods and the final node after the drone delivers all the goods.

[0028] S32. Set an initial policy to process each drone user group to obtain the original drone access order, where the original drone access order is the source user node and the destination user node in sequence. Specifically, the initial policy can be, for example, for each group of drone users, first shield the source user node, randomly select a node from the unshielded destination user nodes as the next access node, and shield it. If the selected node is a destination user node, at the same time lift the shielding of its paired source user node, and repeat the above steps until all destination user nodes are shielded, completing the construction of the drone access sequence. Finally, add the initial node before the drone picks up goods and the final node after the drone delivers all the goods to the head and tail of the feasible sequence of the drone respectively, and then splice all these sequences to form the chromosome of the drone PDP (pick-up-delivery-pick-up).

[0029] S33. Determine whether the remaining effective payload margin of the drone meets the requirement for continuously accessing the next source user node. If so, calculate the full-segment energy consumption when continuously accessing the next source user node according to the weighted directed graph, and when the energy consumption when continuously accessing the next source user node is greater than the current energy consumption, take the drone access order corresponding to the current energy consumption as the initial drone access order.

[0030] It should be noted that in the UAV logistics task planning, the energy efficiency paradox caused by the payload constraint needs special attention: after the UAV completes the first pick-up, the remaining effective payload margin only allows for a single additional pick-up operation, and then it must immediately enter the delivery phase to avoid exceeding the maximum payload threshold. If the remaining effective payload margin is relatively sufficient, it can choose to contact for pick-up and then make continuous deliveries. Of course, due to the limitation of the payload margin, the number of pick-ups contacted or continuous deliveries may be more or less, and preferably, at least three steps of judgment can be embedded. If the continuous operation mode of "pick-up - pick-up - delivery" is adopted, it can be represented as PPD. Of course, whether the continuous delivery method is the optimal method still needs to be judged by energy consumption. If it is determined that the continuous operation mode is not the optimal mode, the original plan is still adopted. Specifically, it also includes a load upper limit detection step. For a determined UAV access order, calculate the real-time load of the UAV at each access point. At the same time, considering that there will be a certain redundancy in the cargo-carrying capacity in the actual UAV design, it is stipulated that when the UAV picks up goods, if the goods carried by the UAV at this time exceed the set load upper limit, the delivery point paired with this pick-up point is advanced to after this pick-up point.

[0031] In a specific embodiment, a genetic algorithm is used to optimize the initial UAV access order to obtain the optimal UAV access order, including: S34. Generate an initial UAV chromosome according to the initial UAV access order; that is, similar to the aforementioned PDP....PDP.

[0032] The tournament selection method is used to perform crossover, mutation, and replication operations on the initial UAV chromosomes to obtain offspring individuals. Specifically, an appropriate number of individuals are selected from the population, and crossover, mutation, and replication operations are respectively carried out to generate offspring individuals. In terms of the crossover operation, since a chromosome contains the access sequences of two UAVs, the crossover operation can be divided into intra-segment crossover and inter-segment crossover. Intra-segment crossover can be understood as the exchange of access points between two UAVs. Due to the pairing relationship, when performing the crossover operation, each UAV randomly selects a pair of pickup and delivery points for exchange, and the rest remains unchanged. Subsequently, for inter-segment crossover, order-based crossover (OBX) is adopted. To avoid conflicts, first determine the position of the separator, then randomly select one of the two parent individuals selected by the tournament selection operator as parent individual 1, mask the delivery nodes and all nodes corresponding to the separator position, and randomly select multiple crossover points from the unmasked pickup nodes to obtain the positions of their paired nodes. The pickup and delivery pairs that need to perform the crossover operation are placed in offspring individual 1 in the order of parent individual 1. After removing the cross-linked genes, the remaining genes are inserted in the order of parent individual 2. Exchange parent individual 1 and parent individual 2, and repeat this operation to obtain offspring individual 2. The mutation operation simulates the gene mutation process in the biological world, aiming to increase perturbation by generating chromosomes that do not currently exist, preventing the genetic algorithm from prematurely falling into a local optimal solution during the optimization process. Herein, the concept of intra-segment crossover in the sub-market is mentioned. For a chromosome, two pairs of pickup and delivery pairs are randomly selected for exchange without considering whether they are in the access sequence of the same UAV. At the same time, in this embodiment, a neighborhood search method is used to further avoid local convergence. For the "elite individual" with the highest fitness in the population, to demonstrate the concept of "survival of the fittest" in the theory of evolution, when performing the replication operation, its chromosome is replicated to obtain an offspring individual. This operation ensures that the individual genes with excellent traits in the population can be continued. During the iterative process of the genetic algorithm, high-quality genes are continuously passed on to the next generation, maintaining a relatively high genetic diversity of fitness in the population. By directly replicating the chromosomes of the elite individuals, the offspring individuals are provided with a relatively high adaptability foundation from the beginning, which helps the entire population to evolve towards a better solution. At the same time, this simple and direct replication method, while ensuring the algorithm efficiency, also strengthens the screening and retention mechanism of dominant genes in the genetic algorithm, provides high-quality genetic materials for the crossover and mutation operations, enables the new individuals generated by subsequent crossover and mutation to explore and optimize at a higher starting point, and promotes the population to continuously approach the global optimal solution in the search space.

[0033] S25. Iteratively calculate the fitness of each parent individual and offspring individual, and use the sequence order corresponding to the UAV chromosome that optimizes the fitness function as the optimal UAV access order, where the fitness function is determined by the path energy consumption of the UAV flying in the wind field. For example, by merging the offspring population and the parent population, calculate the fitness, and eliminate the last 50% of the individuals to control the population size. At the same time, after performing the above operations, calculate the fitness of the offspring individuals. When its fitness is lower than the worst individual in the parent population, it will be marked as an invalid solution, and then repeat the above operations until its fitness is higher than the worst individual. At this time, a genetic process is completed. Repeat the above operations until the iteration is completed to obtain the multi-UAV access order and the initial trajectory.

[0034] The method for UAV trajectory planning based on radio map in the wind field environment of this embodiment includes: obtaining radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; solving a weighted directed graph according to the radio map and the wind field vector model, where the weighted directed graph is used to store the energy consumption of each path; initializing the UAV access order based on the weighted directed graph, and using a genetic algorithm to optimize the initial UAV access order to obtain the optimal UAV access order. In this way, through the radio map and the wind field vector model, the UAV mission energy consumption in the wind field environment can be obtained, and then the delivery order and the UAV trajectory can be reasonably set to improve the delivery efficiency on the premise that the UAV communication quality meets the requirements.

[0035] Please continue to refer to Figure 2 , and the present invention also discloses a UAV trajectory planning system based on radio map in the wind field environment, including: An initialization module, configured to obtain radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; A weighted directed graph generation module, configured to solve a weighted directed graph according to the radio map and the wind field vector model, where the weighted directed graph is used to store the energy consumption of each path; A UAV access order optimization module, which initializes the UAV access order based on the weighted directed graph and uses a genetic algorithm to optimize the initial UAV access order to obtain the optimal UAV access order.

[0036] In a specific embodiment, the weighted directed graph generation module includes: A weight expression calculation unit, configured to obtain the vertex set and edge set of the weighted directed graph to obtain the weight expression for the UAV to fly between any two points, where the weight is determined by the flight path and the UAV energy consumption corresponding to the flight path; A mobile cost function solving unit is used to convert the solution of the weight into the solution of a mobile cost function. Wherein, the mobile cost function is determined by the energy consumption of the UAV and the signal strength of the UAV. The energy consumption of the UAV and the signal strength of the UAV are related to the flight time, and the flight time is related to the wind field vector model. A minimum energy consumption path calculation unit is used to traverse each source user node set to obtain the solution of the mobile cost function that meets the preset conditions between any two points to obtain the minimum energy consumption path. A weighted directed graph generation unit is used to store each of the minimum energy consumption paths to obtain a weighted directed graph.

[0037] In a specific embodiment, the UAV access order optimization module specifically includes: A UAV user group generation unit is used to obtain a source user node set and a destination user node set to obtain a number of UAV user groups. Wherein, each UAV user group includes a source user node and a destination user node. An original UAV access order processing unit is used to set an initial policy to process each UAV user group to obtain an original UAV access order. Wherein, the original UAV access order is the source user node and the destination user node in sequence. An initial UAV access order calculation unit is used to determine whether the remaining effective payload margin of the UAV meets the requirement of continuously accessing the next source user node. If so, it calculates the total energy consumption when continuously accessing the next source user node according to the weighted directed graph, and when the energy consumption when continuously accessing the next source user node is greater than the current energy consumption, it takes the UAV access order corresponding to the current energy consumption as the initial UAV access order.

[0038] In a specific embodiment, the UAV access order optimization module further includes: A chromosome initialization unit is used to generate an initial UAV chromosome according to the initial UAV access order. A child individual generation unit is used to perform crossover, mutation and replication operations on the initial UAV chromosome by using the tournament selection method to obtain child individuals. An optimal UAV access order optimization unit is used to iteratively calculate the fitness of each parent individual and child individual, and take the sequence order corresponding to the UAV chromosome with the optimal fitness function as the optimal UAV access order. Wherein, the fitness function is determined by the path energy consumption of the UAV flying in the wind field.

[0039] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification.

[0040] Although the present application has been described herein in connection with various embodiments, however, in the process of implementing the claimed present application, those skilled in the art can understand and achieve other variations of the disclosed embodiments by viewing the accompanying drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality. A single processor or other unit can implement several functions recited in the claims. Certain measures are recited in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0041] The above content is a further detailed description of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention pertains, without departing from the concept of the present invention, several simple deductions or substitutions can be made, and all should be regarded as belonging to the protection scope of the present invention.

Claims

1. A UAV trajectory planning method based on radio maps in a wind environment, characterized in that: including: Obtain radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; Solve a weighted directed graph according to the radio map and the wind field vector model, where the weighted directed graph is used to store the energy consumption of each path; Initialize the UAV access order based on the weighted directed graph, and optimize the initial UAV access order using a genetic algorithm to obtain the optimal UAV access order.

2. The method for planning the trajectory of an unmanned aerial vehicle based on a radio map in a wind field environment according to claim 1, wherein, The UAV initialization parameters include: hangar position, source user node set, destination user node set, UAV flight altitude range, UAV flight horizontal range, and UAV flight speed; Correspondingly, the wind vector model is as follows: = + , where is the ground speed of the UAV, is the airspeed of the UAV relative to the air, is the wind speed, , is the wind speed of the absolute value, is the wind speed and the angle between the positive horizontal axis.

3. The method for UAV trajectory planning based on radio map in a wind field environment according to claim 1, characterized in that Solving the weighted directed graph according to the radio map and the wind field vector model includes: Obtain the vertex set and edge set of the weighted directed graph to obtain the weight expression for the UAV to fly between any two points, where the weight is determined by the flight path and the UAV energy consumption corresponding to the flight path; Convert the solution of the weight into the solution of a mobile cost function; where the mobile cost function is determined by the UAV energy consumption and the UAV signal strength, the UAV energy consumption and the UAV signal strength are related to the flight time, and the flight time is related to the wind field vector model; Traverse each source user node set to obtain the solution of the mobile cost function that satisfies the preset conditions between any two points to obtain the minimum energy consumption path; Store each of the minimum energy consumption paths to obtain a weighted directed graph.

4. The method for planning the trajectory of an unmanned aerial vehicle based on a radio map in a wind field environment according to claim 3, characterized in that The mobile cost function is as follows: ; Wherein, Among them, \(E(v, t)\) represents the instantaneous energy consumption of the UAV, represents the airspeed of the UAV, represents the flight time of the UAV, represents the signal-to-noise ratio at the location of the UAV, represents whether the SNR value defining a certain place reaches the threshold allowing the UAV to pass, , indicating that the mission allows the UAV to pass, otherwise the UAV is not allowed to pass.

5. The method for unmanned aerial vehicle trajectory planning based on radio map in a wind field environment according to claim 1, wherein, Initializing the UAV access order based on the weighted directed graph includes: Obtain the source user node set and the destination user node set to obtain a number of UAV user groups, where each UAV user group includes a source user node and a destination user node; Set an initial strategy to process each UAV user group to obtain the original UAV access order, where the original UAV access order is the source user node and the destination user node in sequence; Judge whether the remaining effective payload margin of the UAV satisfies continuous access to the next source user node. If so, calculate the full-segment energy consumption when continuously accessing the next source user node according to the weighted directed graph, and when the energy consumption when continuously accessing the next source user node is greater than the current energy consumption, use the UAV access order corresponding to the current energy consumption as the initial UAV access order.

6. The method for UAV trajectory planning based on radio map in a wind farm environment according to claim 1, characterized in that: Optimizing the initial UAV access order using a genetic algorithm to obtain the optimal UAV access order includes: Generate an initial UAV chromosome according to the initial UAV access order; Use the tournament selection method to perform crossover, mutation, and replication operations on the initial UAV chromosome to obtain offspring individuals; Iteratively calculate the fitness of each parent individual and offspring individual to use the sequence order corresponding to the UAV chromosome with the optimal fitness function as the optimal UAV access order, where the fitness function is determined by the path energy consumption of the UAV flying in the wind field.

7. A UAV trajectory planning system based on radio map for wind field environment, characterized in that, including: An initialization module for obtaining radio map initialization parameters and UAV initialization parameters to generate a radio map and a wind vector model; A weighted directed graph generation module for solving a weighted directed graph according to the radio map and the wind field vector model, where the weighted directed graph is used to store the energy consumption of each path; The UAV access order optimization module initializes the UAV access order based on the weighted directed graph, and optimizes the initial UAV access order using a genetic algorithm to obtain the optimal UAV access order.

8. The radio map-based UAV trajectory planning system for wind field environment according to claim 7, characterized in that, The weighted directed graph generation module includes: The weight expression calculation unit is used to obtain the vertex set and edge set of the weighted directed graph to obtain the weight expression for the UAV to fly between any two points. Among them, the weight is determined by the flight path and the UAV energy consumption corresponding to the flight path; The moving cost function solving unit is used to transform the solution of the weight into the solution of the moving cost function; among them, the moving cost function is determined by the UAV energy consumption and the UAV signal strength, the UAV energy consumption and the UAV signal strength are related to the flight time, and the flight time is related to the wind field vector model; The minimum energy consumption path calculation unit is used to traverse each source user node set to obtain the solution of the moving cost function that meets the preset conditions between any two points to obtain the minimum energy consumption path; The weighted directed graph generation unit is used to store each of the minimum energy consumption paths to obtain the weighted directed graph.

9. The UAV trajectory planning system based on radio map of wind field environment according to claim 7, characterized in that, The UAV access order optimization module specifically includes: The UAV user group generation unit is used to obtain the source user node set and the destination user node set to obtain a number of UAV user groups, where each UAV user group includes a source user node and a destination user node; The original UAV access order processing unit is used to set an initial strategy to process each UAV user group to obtain the original UAV access order, where the original UAV access order is the source user node and the destination user node in sequence; The initial UAV access order calculation unit is used to determine whether the remaining effective payload margin of the UAV meets the requirement of continuously accessing the next source user node. If so, it calculates the total energy consumption when continuously accessing the next source user node according to the weighted directed graph, and when the energy consumption when continuously accessing the next source user node is greater than the current energy consumption, it takes the UAV access order corresponding to the current energy consumption as the initial UAV access order.

10. The UAV trajectory planning system based on radio map of wind field environment according to claim 7, characterized in that, The UAV access order optimization module further includes: The chromosome initialization unit is used to generate an initial UAV chromosome according to the initial UAV access order; The offspring individual generation unit is used to perform crossover, mutation, and replication operations on the initial UAV chromosome using the tournament selection method to obtain offspring individuals; The optimal UAV access order optimization unit is used to iteratively calculate the fitness of each parent individual and offspring individual to use the sequence order corresponding to the UAV chromosome with the optimal fitness function as the optimal UAV access order, where the fitness function is determined by the path energy consumption of the UAV flying in the wind field.

Images