Intelligent multi-unmanned aerial vehicle data acquisition method based on ant colony algorithm excitation

Abstract

The invention discloses an intelligent multi-unmanned aerial vehicle data acquisition method based on ant colony algorithm excitation, and belongs to the technical field of communication. The invention provides an intelligent multi-unmanned aerial vehicle data acquisition method based on ant colony algorithm excitation, aiming at solving the problems that an unmanned aerial vehicle group cruise acquisition strategy based on sensor data freshness constraint may cause low energy efficiency of an unmanned aerial vehicle group and limited continuous working time of a system in a large-scale non-uniformly distributed sensor data acquisition scene. The method adopts a deep reinforcement learning method to establish an unmanned aerial vehicle group cruise acquisition optimization model, dynamically plans a cruise trajectory of an unmanned aerial vehicle group according to ground sensor position distribution, and utilizes an ant colony algorithm idea to construct a data acquisition excitation function according to a sensor data freshness state associated with each unmanned aerial vehicle. And the data acquisition efficiency of the unmanned aerial vehicles is maximized, so that the system energy consumption in the cruising process of the unmanned aerial vehicle group is effectively reduced.

Description

Technical Field

[0001] The present invention belongs to the field of communication technology, and in particular relates to an intelligent multi-UAV data collection method based on ant colony algorithm stimulation. Background Art

[0002] With the continuous development of drone swarm technology, the use of drone swarms to perform ground sensor data collection will be widely used in the field of information and communication. In particular, when collecting data from large-scale non-uniformly distributed ground sensors, a low-altitude drone swarm composed of multiple drones can significantly improve the efficiency of sensor data collection. However, in practical applications, the drone swarm cruising collection strategy for sensor data freshness constraints may cause low energy efficiency of drone swarms and limited continuous working time of the system. Among them, data freshness refers to the average delay from data generation to data collection, which represents the validity and reliability of system data.

[0003] In view of the above problems, the present invention proposes an intelligent multi-UAV data collection method based on ant colony algorithm incentive. The method adopts the idea of ​​double-delay deep deterministic policy gradient algorithm [1] to establish a UAV swarm cruise collection optimization model, dynamically plans the cruise trajectory of the UAV swarm according to the location distribution of ground sensors, and constructs a data collection incentive function based on the freshness status of the sensor data associated with each UAV using the idea of ​​ant colony algorithm to maximize the data collection efficiency of the UAV, thereby effectively reducing the system energy consumption during the cruise of the UAV swarm.

[0004] [1]F.Scott,VHHerke,M.David.Addressing Function Approximation Errorin Actor-Critic Methods[C].Proceedings of the 35th International Conference on Machine Learning,Stockholm,Sweden,2018:2587-2601. Summary of the invention

[0005] The present invention aims to solve the above problems of the prior art. An intelligent multi-UAV data collection method based on ant colony algorithm incentive is proposed. The technical solution of the present invention is as follows:

[0006] An intelligent multi-UAV data collection method based on ant colony algorithm motivation includes the following steps:

[0007] 101. A deep reinforcement learning model is constructed using a double-delay deep deterministic policy gradient algorithm, including a drone swarm action strategy generator, a drone swarm state-action value generator, a drone swarm data acquisition decision generator, an experience sample storage area, and a random sample set. The drone swarm is represented by a set N = {n}, where n is a drone. The cruise acquisition time of the drone swarm is divided into K equal-length time slots of length τ, and the system state remains unchanged in any time slot k;

[0008] 102. Establish system state vector [s k ,a k ,r k ,s k+1 ], where s k is the state vector of the drone swarm in time slot k, a k is the UAV group action vector of k time slot, r k is the system reward for time slot k, s k+1 is the state vector of the drone group in time slot k+1, and initializes the sensor set that has been collected in, I represents the set of all sensors in the system, and k is initialized to 0;

[0009] 103. If k<K, let k=k+1, the drone group data collection decision generator is based on the state vector s k , update the acquired sensor set I′, jump to step 104, otherwise, jump to step 107;

[0010] 104. Obtain s through the drone swarm action strategy generator k The action vector of the drone group in state a k , the incentive function is constructed using the ant colony algorithm, and the energy consumption of each drone n in the k time slot is Get system rewards k , according to s k with a k Calculate and obtain the k+1 time slot drone swarm state vector s k+1 , the system state vector [s k ,a k ,r k ,s k+1 ] Added experience sample storage area;

[0011] 105. Randomly sample a sample set from the experience sample storage area, and import the sample set into the drone swarm action strategy generator and the drone swarm state-action value generator for training;

[0012] 106. If |I′|<|I|, jump to step 107; otherwise, jump to step 103;

[0013] 107. The collection work is completed.

[0014] Furthermore, in step 102, the system state vector [s k ,a k ,r k ,s k+1 ], where the state vector s of the drone swarm in time slot k is k , UAV swarm motion vector a k 、System Rewards k , drone swarms in s k Execute a in the state k After the action, the state vector s of the drone group entering the k+1 time slot is k+1 , as shown in formulas (1), (2), (3), and (4) respectively:

[0015]

[0016]

[0017] In formula (1), represents the coordinate vector of drone n in time slot k, Indicates whether sensor i in time slot k is within the coverage of drone n. If so, otherwise represents the ant colony pheromone of UAV n in time slot k, I represents the set of all sensors in the system, and N represents the set of all UAVs in the system; in formula (2), represents the horizontal flight angle of UAV n in time slot k, represents the vertical flight angle of UAV n in time slot k, represents the flight speed of UAV n in time slot k; in formula (3), represents the energy consumption of UAV n in time slot k.

[0018] Furthermore, the method for updating the collected sensor set I′ by the drone group data collection decision generator in step 103 is as follows:

[0019] 1) Initialize the temporary drone set N′=N, the temporary set of sensors within the coverage area of ​​any drone n in time slot k and data collection time

[0020] 2) Take the first drone n in the set N′ and calculate the state vector s k , obtain all sensors within the current drone n coverage area and add them to the collection And according to The Euclidean distance from each sensor i to drone n is Arrange the elements in ascending order;

[0021] 3) If Retrieve Collection The first sensor i in the image is added to the set of collected sensors I′. Where Δt is the data collection time, jump to step 4), otherwise, jump to step 6);

[0022] 4) Calculate the data freshness f of sensor i based on the data volume, data generation time and data reception time in sensor i i , data freshness refers to the average delay from data generation to data collection. If f i <f i max , where f i max is the data freshness threshold of sensor i, jump to step 5), otherwise, jump to step 7);

[0023] 5) If Where τ is the time slot length, jump to step 3), otherwise jump to step 6);

[0024] 6) If Jump to step 2), otherwise, jump to step 7);

[0025] 7) The step ends.

[0026] Furthermore, in step 104, the k-time slot system reward r is obtained. k and the k+1 time slot drone swarm state vector s k+1 The method is as follows:

[0027] 8) Initialize the temporary drone set N′=N, and the system rewards r k =0, binary variable γ = 0;

[0028] 9) Take out the first drone n in the set N′ and update the state vector s of the drone group in the k+1 time slot k+1 Ant colony pheromones in drone n

[0029] 10) According to the drone group motion vector a k The action vector of drone n in the k+1 time slot is used to update the state vector s of the drone group k+1 The coordinate vector of drone n and binary variables

[0030] 11) If Jump to step 9), otherwise, jump to step 12);

[0031] 12) According to the state vector s of the drone swarm in the k+1 time slot k+1 , determine whether the drone group exceeds the boundary of the data collection area, if so, jump to step 13), otherwise, jump to step 14);

[0032] 13) Let the state vector of the drone swarm at time slot k+1 be k+1 =s k , binary variable γ = 1;

[0033] 14) According to the energy consumption of the drone swarm and the state vector s of the drone swarm in the k+1 time slot k+1 , calculate the system reward r k ,make Among them, p is the penalty value for the drone group exceeding the boundary of the data collection area;

[0034] 15) Return the k-time slot system reward r k and the UAV swarm state vector s at time slot k+1 k+1 ;

[0035] 16) The steps are completed.

[0036] Furthermore, the energy consumption of each drone n in the k time slot is obtained in step 104. The method is shown in formula (5):

[0037]

[0038] In formula (5), and represents the weight factor related to the weight, wing area, and air density of the UAV n, τ represents the time slot length, represents the speed of drone n in time slot k.

[0039] Furthermore, in step 4), the method for calculating the freshness of a single sensor is as shown in formula (6):

[0040]

[0041] In formula (6), D i represents the data size generated by sensor i, represents the data generation time of sensor i, t i Indicates the data reception time of sensor i.

[0042] Furthermore, in step 9), the state vector s of the k+1 time slot is updated k+1 The method of ant colony pheromone of drone n is shown in formula (7):

[0043]

[0044] In formula (7), ρ represents the evaporation rate of ant colony pheromone, represents the sensor set collected by drone n in time slot k+1, Δξ represents the ant colony pheromone carried by a single sensor, and f i represents the data freshness of sensor i, f i max represents the data freshness threshold of sensor i.

[0045] Furthermore, in step 10), the coordinate vector of the drone n of the drone group in the k+1 time slot is obtained: The method is shown in formula (8):

[0046]

[0047] In formula (8), τ represents the time slot length, represents the horizontal flight angle of drone n, represents the vertical flight angle of UAV n, Represents the flight speed of UAV n.

[0048] The advantages and beneficial effects of the present invention are as follows:

[0049] The present invention discloses an intelligent multi-UAV data collection method based on ant colony algorithm incentive. In view of the problem that the drone swarm cruising collection strategy based on sensor data freshness constraint may cause low energy efficiency of the drone swarm and limited continuous working time of the system in the scenario of large-scale non-uniformly distributed sensor data collection, the present invention proposes an intelligent multi-UAV data collection method based on ant colony algorithm incentive. The method adopts deep reinforcement learning method to establish a drone swarm cruising collection optimization model, dynamically plans the cruising trajectory of the drone swarm according to the position distribution of ground sensors, and constructs a data collection incentive function according to the sensor data freshness status associated with each drone using the ant colony algorithm idea to maximize the data collection efficiency of the drone, thereby effectively reducing the system energy consumption during the drone swarm cruising process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The present invention provides a preferred embodiment of a flow chart of an intelligent multi-UAV data collection method based on ant colony algorithm stimulation. DETAILED DESCRIPTION

[0051] The following will describe the technical solutions in the embodiments of the present invention in detail in conjunction with the accompanying drawings in the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention.

[0052] The technical solution of the present invention to solve the above technical problems is:

[0053] The concepts and models involved in the present invention are as follows:

[0054] The present invention assumes that the area where the drone swarm collects data is within the effective communication range of the base. When the drone swarm collects sensor data, the data can be directly transmitted to the base through line-of-sight communication. The drone swarm-assisted data collection system model considered in the present invention consists of a drone set N = {n}, a data base and a large number of ground sensors. Assume that the sensor set I = {i} is in L × L m 2 The area is randomly distributed. During the data collection task of the drone group, the position of the sensor node is fixed, the sensor carries a specific amount of data, and each sensor has a data freshness constraint requirement. Initially, the data size and data freshness constraints of different sensors are different. In addition, the present invention assumes that the base has a central control unit responsible for collecting system information in the network. Based on this information, the central control unit will issue instructions to guide the movement and operation of the drone group.

[0055] The technical solution of the present invention is described as follows:

[0056] 1. System state vector [s k ,a k ,r k ,s k+1 ]

[0057] The state vector s of the drone swarm in k time slots k , UAV swarm motion vector a k 、System Rewards k , drone swarms in s k Execute a in the state k After the action, the state vector s of the drone group entering the k+1 time slot is k+1 , as shown in formulas (1), (2), (3), and (4) respectively:

[0058]

[0059] In formula (1), represents the coordinate vector of drone n in time slot k, Indicates whether sensor i in time slot k is within the coverage of drone n. If so, otherwise represents the ant colony pheromone of UAV n in time slot k, I represents the set of all sensors in the system, and N represents the set of all UAVs in the system; in formula (2), represents the horizontal flight angle of UAV n in time slot k, represents the vertical flight angle of UAV n in time slot k, represents the flight speed of UAV n in time slot k; in formula (3), represents the energy consumption of UAV n in time slot k;

[0060] 2. Energy consumption of each drone n in the drone swarm Calculation method

[0061] Energy consumption of UAV n in time slot k As shown in formula (5):

[0062]

[0063] In formula (5), and represents the weight factor related to the weight, wing area, and air density of the UAV n, τ represents the time slot length, represents the speed of drone n in time slot k;

[0064] 3. Sensor data freshness f i Calculation method

[0065] The method for calculating the freshness of a single sensor is shown in formula (6):

[0066]

[0067] In formula (6), D i represents the data size generated by sensor i, represents the data generation time of sensor i, t i Indicates the data receiving time of sensor i;

[0068] 4. Method for updating the ant colony pheromone of drone n

[0069] Update the state vector s of time slot k+1 k+1 The method of ant colony pheromone of drone n is shown in formula (7):

[0070]

[0071] In formula (7), ρ represents the evaporation rate of ant colony pheromone, represents the sensor set collected by drone n in time slot k+1, Δξ represents the ant colony pheromone carried by a single sensor, and f i represents the data freshness of sensor i, f i max represents the data freshness threshold of sensor i;

[0072] 5. Obtain the coordinate vector of drone n in the drone group at the k+1 time slot Methods

[0073] Get the coordinate vector of drone n in the drone group at time slot k+1 The method is shown in formula (8):

[0074]

[0075] In formula (8), τ represents the time slot length, represents the horizontal flight angle of drone n, represents the vertical flight angle of UAV n, represents the flight speed of UAV n;

[0076] 6. Sub-algorithm 1: Update the collected sensor set I′

[0077] Step 1: Initialize the temporary drone set N′=N, the temporary set of sensors within the coverage area of ​​any drone n in time slot k and data collection time

[0078] Step 2: Take the first drone n in the set N′ and calculate the state vector s k , obtain all sensors within the current drone n coverage area and add them to the collection And according to The Euclidean distance from each sensor i to drone n is Arrange the elements in ascending order;

[0079] Step 3: If Retrieve Collection The first sensor i in the image is added to the set of collected sensors I′. Where Δt is the data collection time, jump to step 4, otherwise, jump to step 6;

[0080] Step 4: Calculate the data freshness f of sensor i based on the data volume, data generation time, and data reception time in sensor i i , data freshness refers to the average delay from data generation to data collection. If f i <f i max , where f i max is the data freshness threshold of sensor i, jump to step 5, otherwise, jump to step 7;

[0081] Step 5: If Where τ is the time slot length, jump to step 3, otherwise jump to step 6);

[0082] Step 6: If Jump to step 2, otherwise, jump to step 7;

[0083] Step 7: End of the step.

[0084] 7. Sub-algorithm 2: Obtaining the k-slot system reward r k and k+1 time slot drone state vector s k+1

[0085] Step 1: Initialize the temporary drone set N′=N, and the system reward r k =0, binary variable γ = 0;

[0086] Step 2: Take out the first drone n in the set N′ and update the state vector s of the drone group in the k+1 time slot k+1 Ant colony pheromones in drone n

[0087] Step 3: According to the drone group motion vector a k The action vector of drone n in the k+1 time slot is used to update the state vector s of the drone group k+1 The coordinate vector of drone n and binary variables

[0088] Step 4: If Jump to step 2, otherwise, jump to step 5;

[0089] Step 5: According to the drone swarm state vector s at time slot k+1 k+1 , determine whether the drone group exceeds the boundary of the data collection area. If so, jump to step 6, otherwise, jump to step 7;

[0090] Step 6: Let the state vector of the drone swarm at time slot k+1 be s k+1 =s k , binary variable γ = 1;

[0091] Step 7: Based on the energy consumption of the drone swarm and the drone swarm state vector s at time slot k+1 k+1 , calculate the system reward r k ,make Among them, p is the penalty value for the drone group exceeding the boundary of the data collection area;

[0092] Step 8: Return the k-slot system reward r k and the UAV swarm state vector s at time slot k+1 k+1 ;

[0093] Step 9: End of the step.

[0094] An intelligent multi-UAV data collection method based on ant colony algorithm stimulation, the specific implementation method of which includes the following steps:

[0095] Step 1: A double-delay deep deterministic policy gradient algorithm is used to construct a deep reinforcement learning model, including a drone swarm action strategy generator, a drone swarm state-action value generator, a drone swarm data acquisition decision generator, an experience sample storage area, and a random sample set. The drone swarm is represented by a set N = {n}, where n is a drone. The cruise acquisition time of the drone swarm is divided into K equal-length time slots of length τ, and the system state remains unchanged in any time slot k;

[0096] Step 2: Establish the system state vector [s k ,a k ,r k ,s k+1 ], where s k is the state vector of the drone swarm in time slot k, a k is the UAV group action vector of k time slot, r k is the system reward for time slot k, s k+1 is the state vector of the drone group in time slot k+1, and initializes the sensor set that has been collected in, I represents the set of all sensors in the system, and k is initialized to 0;

[0097] Step 3: If k < K, let k = k + 1, the drone swarm data collection decision generator is based on the state vector s k , call sub-algorithm 1, update the acquired sensor set I′, and jump to step 104, otherwise, jump to step 107;

[0098] Step 4: Obtain s through the drone swarm action strategy generator k The action vector of the drone group in state a k , the incentive function is constructed using the ant colony algorithm, and the energy consumption of each drone n in the k time slot is Call sub-algorithm 2 to obtain system reward r k , according to s k with a k Calculate the k+1 time slot drone swarm state vector s k+1 , the system state vector [s k ,a k ,r k ,s k+1 ] Added experience sample storage area;

[0099] Step 5: Randomly sample a sample set from the experience sample storage area, and import the sample set into the drone swarm action strategy generator and the drone swarm state-action value generator for training;

[0100] Step 6: If |I′|<|I|, jump to step 107, otherwise, jump to step 103;

[0101] Step 7: The collection work is completed.

[0102] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0103] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0104] The above embodiments should be understood to be only used to illustrate the present invention and not to limit the protection scope of the present invention. After reading the contents of the present invention, technicians can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. An intelligent multi-UAV data collection method based on ant colony algorithm stimulation, characterized in that: The following steps are involved:

101. A deep reinforcement learning model is constructed using a double-delay deep deterministic policy gradient algorithm, including a drone swarm action strategy generator, a drone swarm state-action value generator, a drone swarm data acquisition decision generator, an experience sample storage area, and a random sample set. The drone swarm is represented by a set N = {n}, where n is a drone. The cruise acquisition time of the drone swarm is divided into K equal-length time slots of length τ, and the system state remains unchanged in any time slot k; 102. Establish system state vector [s k ,a k ,r k ,s k+1 ], where s k is the state vector of the drone swarm in time slot k, a k is the UAV group action vector of k time slot, r k is the system reward for time slot k, s k+1 is the state vector of the drone group in time slot k+1, and initializes the sensor set that has been collected in, I represents the set of all sensors in the system, and k is initialized to 0; 103. If k<K, let k=k+1, the drone group data collection decision generator is based on the state vector s k , update the acquired sensor set I′, jump to step 104, otherwise, jump to step 107; 104. Obtain s through the drone swarm action strategy generator k The action vector of the drone group in state a k , the incentive function is constructed using the ant colony algorithm, and the energy consumption of each drone n in the k time slot is Get system rewards k , according to s k with a k Calculate and obtain the k+1 time slot drone swarm state vector s k+1 , the system state vector [s k ,a k ,r k ,s k+1 ] Added experience sample storage area; 105. Randomly sample a sample set from the experience sample storage area, and import the sample set into the drone swarm action strategy generator and the drone swarm state-action value generator for training; 106. If |I′|<|I|, jump to step 107; otherwise, jump to step 103; 107. The collection work is completed.

2. The intelligent multi-UAV data collection method based on ant colony algorithm stimulation according to claim 1 is characterized in that: In step 102, a system state vector [s k ,a k ,r k ,s k+1 ], where the state vector s of the drone swarm in time slot k is k , UAV swarm motion vector a k 、System Rewards k , drone swarms in s k Execute a in the state k After the action, the state vector s of the drone group entering the k+1 time slot is k+1 , as shown in formulas (1), (2), (3), and (4) respectively: In formula (1), represents the coordinate vector of drone n in time slot k, Indicates whether sensor i in time slot k is within the coverage of drone n. If so, otherwise represents the ant colony pheromone of UAV n in time slot k, I represents the set of all sensors in the system, and N represents the set of all UAVs in the system; in formula (2), represents the horizontal flight angle of UAV n in time slot k, represents the vertical flight angle of UAV n in time slot k, represents the flight speed of UAV n in time slot k; in formula (3), represents the energy consumption of UAV n in time slot k.

3. The intelligent multi-UAV data collection method based on ant colony algorithm stimulation according to claim 1 is characterized in that: The method for updating the collected sensor set I′ by the drone group data collection decision generator in step 103 is as follows: 1) Initialize the temporary drone set N′=N, the temporary set of sensors within the coverage area of ​​any drone n in time slot k and data collection time 2) Take the first drone n in the set N′ and calculate the state vector s k , obtain all sensors within the current drone n coverage area and add them to the collection And according to The Euclidean distance from each sensor i to drone n is Arrange the elements in ascending order; 3) If Retrieve Collection The first sensor i in the image is added to the set of collected sensors I′. Where Δt is the data collection time, jump to step 4), otherwise, jump to step 6); 4) Calculate the data freshness f of sensor i based on the data volume, data generation time and data reception time in sensor i i , data freshness refers to the average delay from data generation to data collection. If in, is the data freshness threshold of sensor i, jump to step 5), otherwise, jump to step 7); 5) If Where τ is the time slot length, jump to step 3), otherwise jump to step 6); 6) If Jump to step 2), otherwise, jump to step 7); 7) The step ends.

4. The intelligent multi-UAV data collection method based on ant colony algorithm stimulation according to claim 1 is characterized in that: In step 104, the k-time slot system reward r is obtained. k and the k+1 time slot drone swarm state vector s k+1 The method is as follows: 8) Initialize the temporary drone set N′=N, and the system rewards r k =0, binary variable γ=0; 9) Take out the first drone n in the set N′ and update the state vector s of the drone group in the k+1 time slot k+1 Ant colony pheromones in drone n 10) According to the drone group motion vector a k The action vector of drone n in the k+1 time slot is used to update the state vector s of the drone group k+1 The coordinate vector of drone n and binary variables 11) If Jump to step 9), otherwise, jump to step 12); 12) According to the state vector s of the drone swarm in the k+1 time slot k+1 , determine whether the drone group exceeds the boundary of the data collection area, if so, jump to step 13), otherwise, jump to step 14); 13) Let the state vector of the drone swarm at time slot k+1 be k+1 =s k , binary variable γ = 1; 14) According to the energy consumption of the drone swarm and the state vector s of the drone swarm in the k+1 time slot k+1 , calculate the system reward r k ,make Among them, p is the penalty value for the drone group exceeding the boundary of the data collection area; 15) Return the k-time slot system reward r k and the UAV swarm state vector s at time slot k+1 k+1 ; 16) The steps are completed.

5. The intelligent multi-UAV data collection method based on ant colony algorithm stimulation according to claim 1 is characterized in that: In step 104, the energy consumption of each drone n in the k time slot is obtained. The method is shown in formula (5): In formula (5), and represents the weight factor related to the weight, wing area, and air density of the UAV n, τ represents the time slot length, represents the speed of drone n in time slot k.

6. The intelligent multi-UAV data collection method based on ant colony algorithm stimulation according to claim 3 is characterized in that: In step 4), the method for calculating the freshness of a single sensor is shown in formula (6): In formula (6), D i represents the data size generated by sensor i, represents the data generation time of sensor i, t i Indicates the data reception time of sensor i.

7. The intelligent multi-UAV data collection method based on ant colony algorithm stimulation according to claim 4 is characterized in that: In step 9), the state vector s of the k+1 time slot is updated. k+1 The method of ant colony pheromone of drone n is shown in formula (7): In formula (7), ρ represents the evaporation rate of ant colony pheromone, represents the sensor set collected by drone n in time slot k+1, Δξ represents the ant colony pheromone carried by a single sensor, and f i represents the data freshness of sensor i, represents the data freshness threshold of sensor i.

8. The intelligent multi-UAV data collection method based on ant colony algorithm stimulation according to claim 4 is characterized in that: In the step 10), the coordinate vector of the drone n in the drone group in the k+1 time slot is obtained. The method is shown in formula (8): In formula (8), τ represents the time slot length, represents the horizontal flight angle of drone n, represents the vertical flight angle of UAV n, Represents the flight speed of UAV n.

Images