CN113325875B - Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles - Google Patents

Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles Download PDF

Info

Publication number
CN113325875B
CN113325875B CN202110684212.6A CN202110684212A CN113325875B CN 113325875 B CN113325875 B CN 113325875B CN 202110684212 A CN202110684212 A CN 202110684212A CN 113325875 B CN113325875 B CN 113325875B
Authority
CN
China
Prior art keywords
path
unmanned aerial
energy consumption
sensor
accessed
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110684212.6A
Other languages
Chinese (zh)
Other versions
CN113325875A (en
Inventor
赵林靖
霍小露
张岗山
马建鹏
李钊
刘勤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xidian University
Original Assignee
Xidian University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xidian University filed Critical Xidian University
Priority to CN202110684212.6A priority Critical patent/CN113325875B/en
Publication of CN113325875A publication Critical patent/CN113325875A/en
Application granted granted Critical
Publication of CN113325875B publication Critical patent/CN113325875B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention provides an unmanned aerial vehicle path planning method for minimizing the number of unmanned aerial vehicles, which mainly solves the problem of minimizing the number of unmanned aerial vehicles in the existing unmanned aerial vehicle path planning scheme and comprises the following steps: 1) initializing parameters; 2) constructing a sensor set to be accessed and initializing a local optimal path set; 3) calculating flight energy consumption, hovering energy consumption and communication energy consumption of the unmanned aerial vehicle; 4) planning flight paths for a given number of unmanned aerial vehicles by adopting an improved ant colony algorithm, and determining a local optimal path set; 5) and acquiring a path planning result of the unmanned aerial vehicle according to the characteristics of the local optimal path set. The invention ensures that the task is completed by using the minimum number of unmanned aerial vehicles on the basis of accessing all the sensors, reduces the system cost and simultaneously reduces the total energy consumption of the unmanned aerial vehicles.

Description

Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles
Technical Field
The invention belongs to the technical field of communication, relates to a path planning method for unmanned aerial vehicles, in particular to a path planning method for unmanned aerial vehicles, which can realize minimization of the number of unmanned aerial vehicles and can be used for data acquisition under the condition that the cost of the unmanned aerial vehicles is limited.
Background
In recent years, the unmanned aerial vehicle technology is rapidly developed and plays an important role in the fields of military and civil use. Light and handy fuselage, nimble motion mode make unmanned aerial vehicle can carry out data acquisition and transmission in the complex environment. In practical application, no matter fuel type unmanned aerial vehicle or charging type unmanned aerial vehicle, the energy is all limited to the economic cost of purchasing an unmanned aerial vehicle is not negligible, the selling price of a civilian type unmanned aerial vehicle can reach tens of thousands yuan, when using many unmanned aerial vehicles to visit the sensor node, the more unmanned aerial vehicles that use, the more the total cost of visiting the sensor node is also bigger. Therefore, in the unmanned aerial vehicle network, the minimum number of the used unmanned aerial vehicles needs to be determined under the condition of meeting the energy consumption constraint of the unmanned aerial vehicles, and the cost of the unmanned aerial vehicles is reduced.
In the network, the number of sensor nodes is constant, and in order to reduce the number of used drones, it is necessary to make each drone access to the sensor nodes as much as possible. Abdelhamid S. published UAV path planning for establishment management in IoT [ C ] in IEEE International Conference on Communications Workshops in 2018, and discloses a nearest neighbor policy-based unmanned aerial vehicle path planning method, which is based on the nearest neighbor policy and selects a next sensor node to be visited for an unmanned aerial vehicle according to the distance between the sensor nodes until all the sensor nodes in a network are visited, so that a path can be effectively planned for the unmanned aerial vehicle, and the number of the unmanned aerial vehicles required to be used is determined. In the scheme, the node closest to the current sensor node is selected as the next node to be visited by the unmanned aerial vehicle each time, the distance between the sensor node and the starting position of the unmanned aerial vehicle is not considered, the path is planned according to the optimal sensor node access mode of the unmanned aerial vehicle, the influence on other unmanned aerial vehicles cannot be avoided, and the number of the used unmanned aerial vehicles is not necessarily the minimum.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides the unmanned aerial vehicle path planning method for minimizing the number of unmanned aerial vehicles, and under the condition of meeting the energy consumption constraint of a single unmanned aerial vehicle, the distance between sensor nodes is considered globally, so that the influence between the unmanned aerial vehicles is avoided, and the number of the used unmanned aerial vehicles and the total energy consumption are reduced.
In order to achieve the purpose, the technical scheme adopted by the invention comprises the following steps:
(1) initializing parameters:
the central controller with the coordinate position (0,0) distributed on the ground is initialized to have K unmanned aerial vehicles U ═ U { U ═ at the position O1,U2,...,Uk,...,UK}; initializing I sensors distributed on the ground as A ═ A1,A2...Ai,...AII is more than or equal to 2, the ith sensor AiHas a position coordinate of (x)i,yi) (ii) a The maximum energy of all unmanned planes is EthThe flight speed is v, and the flight energy consumption, hovering energy consumption and communication energy consumption in unit time are ef、ehAnd etAt the i-th sensor AiThe time of the over-the-air hovering and the communication is ti，K≥1，UkRepresents the kth drone; k virtual sensors having the same coordinate position as that of the central controller O are initialized to B ═ B1,B2...Bk,...BKAnd the distance between any two virtual sensors is infinite, and all unmanned planes are at the kth virtual sensor BkThe time of the over-the-air hovering and the communication is tBk(ii) a Initializing an ant population S-S comprising M ants1,S2…Sm…SM}，M≥50，SmRepresents the mth ant; initializing path selection coefficients to q0The pheromone volatilization factor is rho, the iteration number is iter, the maximum iteration number is iter _ max, the iter _ max is not less than 2000,
Figure BDA0003123795030000021
let iter be 1, K be 1, let K be 1 the minimum total energy consumption E of unmanned aerial vehiclebest＝∞；
(2) Constructing a sensor set to be accessed and initializing a local optimal path set:
constructing a sensor set R to be accessed by a sensor A and a virtual sensor B, wherein the set R is { A, B } R }1,R2,...,Rn,...,RNAnd initializing a local optimal path set
Figure BDA0003123795030000022
Where N denotes the total number of sensors to be accessed, N ═ I + K, RnRepresents the nth sensor to be accessed, when n is equal to [1, I ∈]When R isnRepresents the sensor when n ∈ [ I +1, I + K]When R isnRepresenting a virtual sensor;
(3) calculating flight energy consumption, hovering energy consumption and communication energy consumption of the unmanned aerial vehicle:
(3a) calculating every two sensors R to be accessed in the sensor set R to be accessedaAnd RbEuropean distance between
Figure BDA0003123795030000023
And constructing an Euclidean distance matrix D corresponding to R through NxN Euclidean distances, wherein Ra,RbE.g. R when Ra＝RbWhen it is used, order
Figure BDA0003123795030000024
Expression of DThe formula is as follows:
Figure BDA0003123795030000025
(3b) calculating flight energy consumption of the unmanned aerial vehicle between any two sensors to be accessed through the Euclidean distance matrix D
Figure BDA0003123795030000031
Simultaneously calculating hovering energy consumption of the unmanned aerial vehicle when the unmanned aerial vehicle accesses any sensor to be accessed
Figure BDA0003123795030000032
Energy consumption of communication is
Figure BDA0003123795030000033
Figure BDA0003123795030000034
Figure BDA0003123795030000035
Figure BDA0003123795030000036
(4) Parameters for initializing the improved ant colony algorithm:
define every two sensors R to be accessedaAnd RbHas a pheromone concentration of
Figure BDA0003123795030000037
The path heuristic information is
Figure BDA0003123795030000038
Initialization
Figure BDA0003123795030000039
Wherein tau is0Represents anyTo the initial value of the concentration of pheromone between the two sensors to be accessed,
Figure BDA00031237950300000310
wherein the content of the first and second substances,
Figure BDA00031237950300000311
indicating that the drone is at the sensor R to be accessedaAnd RbThe energy consumption of the flying is reduced between the two modes,
Figure BDA00031237950300000312
indicating that the drone is at the sensor R to be accessedbAnd RNThe energy consumption of the flying is reduced between the two modes,
Figure BDA00031237950300000313
and
Figure BDA00031237950300000314
respectively indicate that the unmanned aerial vehicle is at the sensor R to be accessedbOverhead hover energy consumption and flight energy consumption,
Figure BDA00031237950300000315
indicating that the drone is at the sensor R to be accessedbTime of the over-the-air hover and communication;
(5) and (3) constructing a feasible solution set and an infeasible solution set of the iteration:
(5a) let m equal to 1, initialize the feasible solution set of this iteration
Figure BDA00031237950300000316
Set of infeasible solutions
Figure BDA00031237950300000317
(5b) The mth ant SmN (m) R, the accessed sensor set
Figure BDA00031237950300000318
V (m) is an ordered set, and one sensor R to be accessed is randomly selected from N (m)nAs SmFirst sensor to be accessed, with RstartIs labeled, and R isnFrom N (m) into V (m);
(5c) generating a random number q, q ∈ (0, 1)]And judging q and the path selection coefficient q0Whether or not q > q is satisfied0If yes, calculate SmFrom RnTo any one of the sensors R to be accessed in N (m)w,RwTransition probability of ∈ N (m)
Figure BDA00031237950300000319
And using roulette rules based on transition probabilities
Figure BDA00031237950300000320
Selecting the next sensor R to be accessed in N (m)pOtherwise, directly selecting from R in N (m)nPoint out to make
Figure BDA00031237950300000321
The largest one of the sensors to be accessed is used as the sensor R to be accessed nextpWherein
Figure BDA0003123795030000041
Represents the current iteration RnAnd RwPheromone concentration between, alpha and beta respectively
Figure BDA0003123795030000042
And
Figure BDA0003123795030000043
the degree of importance of;
(5d) r is to bepMove from N (m) to V (m), judge
Figure BDA0003123795030000044
If true, then R is addedstartAdding into V (m) to obtain mth ant SmThe path of (A) is V (m), abbreviated as mth path, otherwise, let Rn＝RpAnd performing step (5 c);
(5e) according to each virtual sensor BkDividing the mth path v (m) into K sub-paths and allocating the K sub-paths to K drones, the start and end positions of each sub-path being the positions of the virtual sensors, and calculating the energy consumption of each sub-path, i.e., the kth drone
Figure BDA0003123795030000045
The energy consumption of each sub-path is the sum of the flight energy consumption of the unmanned aerial vehicle flying along the sub-path and the hovering energy consumption and communication energy consumption of all sensors accessing the sub-path, wherein the flight energy consumption of the unmanned aerial vehicle flying along the sub-path is the sum of the flight energy consumption of the unmanned aerial vehicle flying between two adjacent sensors on the sub-path, and the maximum sub-path energy consumption of the mth path is marked as
Figure BDA0003123795030000046
(5f) Determining the maximum sub-path energy consumption of the mth path
Figure BDA0003123795030000047
Whether or not to satisfy
Figure BDA0003123795030000048
If yes, V (m) is a feasible solution, putting V (m) into a feasible solution set Path ', otherwise, if the Path V (m) is an infeasible solution, putting V (m) into an infeasible solution set Path';
(5g) if M is less than M, making M equal to M +1, executing step (5b), otherwise, executing step (6);
(6) determining a local optimal solution generated by the iteration:
(6a) num ' is used for representing the size of the feasible solution set Path ', namely the number of feasible solutions, and the mth Path Path in the Path ' is calculatedm′Total energy consumption of last K drones
Figure BDA0003123795030000049
And to
Figure BDA00031237950300000410
Performing ascending sequence, and marking the minimum total energy consumption of the K unmanned aerial vehicles in the iteration as Ebest(iter) taking the Path corresponding to it as the local optimal Path Path of the K unmanned planesbest(iter) and adds it to the locally optimal Path set PathbestPerforming the following steps;
(6b) calculating the total energy consumption of K unmanned aerial vehicles on each Path in Path ″, and if K is 1, finding out the minimum total energy consumption E of the K unmanned aerial vehicles in the iterationmin(iter) if Emin(iter)＜EbestUpdate Ebest＝Emin(iter)；
(7) And (3) updating the pheromone concentration:
(7a) selecting L paths according to the numerical value of Num': if Num 'is more than or equal to L, and L is M/5, selecting the first L paths in Path'; if 0 < Num ' < L, randomly selecting F ═ L-Num ' paths in Path ' and Num ' paths in Path ' to form L paths together; if Num 'is 0, then randomly selecting L paths in Path';
(7b) updating the concentration of pheromones between two adjacent sensors on the selected path;
(8) judging whether the iteration is finished:
judging whether iter < iter _ max is true, if yes, iter is iter +1, executing the step (5), and if not, executing the step (9);
(9) obtaining a path planning result of the unmanned aerial vehicle:
determining a set of locally optimal paths
Figure BDA0003123795030000051
If yes, go to step (10), otherwise go to PathbestThe minimum total energy consumption mark in the unmanned aerial vehicles is E, the Path corresponding to the minimum total energy consumption mark is used as the global optimal Path of the K unmanned aerial vehicles, and the global optimal Path and the number K of the unmanned aerial vehicles are output;
(10) updating the unmanned plane set and the virtual sensor set:
judging whether K is equal to 1, if yes, making
Figure BDA0003123795030000052
Otherwise, let K be K +1, obtain the updated set U of drones and the corresponding set B of virtual sensors, and execute step (2).
Compared with the prior art, the invention has the following advantages:
firstly, the path heuristic information in the ant colony algorithm is improved, the improved ant colony algorithm is adopted, the information of the sensor and the distance from the sensor to the central controller are considered globally to select the sensor node to be accessed for the unmanned aerial vehicle, the diversity of the unmanned aerial vehicle for accessing the sensor is effectively expanded, the solution space in the ant colony algorithm is expanded, the path with smaller total energy consumption of the unmanned aerial vehicle is found, and compared with the prior art, the cost for planning the path of the unmanned aerial vehicle is effectively reduced.
Secondly, the population of the ant colony algorithm is improved through the virtual sensor, so that the diversity of the selection of the initial position of the unmanned aerial vehicle is increased; different paths are selected according to the characteristics of a solution space to update the concentration of the pheromone, so that the phenomenon that the concentration of the pheromone on the optimal path is too high to cause the algorithm to fall into local optimization is effectively avoided, the diversity of the unmanned aerial vehicle path selection is increased, the algorithm is easier to jump out of the local optimization, and compared with the prior art, the total energy consumption of unmanned aerial vehicle path planning is effectively reduced.
Thirdly, according to the invention, the number of the unmanned aerial vehicles is updated under the condition that one unmanned aerial vehicle cannot access all the sensors through the minimum energy consumption of all the sensor nodes accessed by one unmanned aerial vehicle and the maximum energy of the unmanned aerial vehicle, so that the number of the unmanned aerial vehicles is prevented from being increased by 1 each time, and compared with the prior art, the complexity of unmanned aerial vehicle path planning is reduced.
Drawings
FIG. 1 is a flow chart of an implementation of the present invention;
FIG. 2 is a diagram of a simulation scenario of the present invention;
FIG. 3 is a comparison of the minimum number of drones required to acquire data for sensor nodes in a given area in accordance with the present invention versus the prior art;
fig. 4 is a graph comparing the total energy consumption of drones required by the present invention and the prior art for data acquisition for sensor nodes in a given area.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
Referring to fig. 1, the present invention includes the steps of:
step 1, initializing parameters:
(1a) the central controller with the coordinate position (0,0) distributed on the ground is initialized to have K unmanned aerial vehicles U ═ U { U ═ at the position O1,U2,…,Uk,…,UK}; initializing I sensors distributed on the ground as A ═ A1,A2...Ai,...AII is more than or equal to 2, the ith sensor AiHas a position coordinate of (x)i,yi) (ii) a The maximum energy of all unmanned planes is EthThe flight speed is v, and the flight energy consumption, hovering energy consumption and communication energy consumption in unit time are ef、ehAnd etAt the i-th sensor AiThe time of the over-the-air hovering and the communication are
Figure BDA0003123795030000063
K is more than or equal to 1, in order to avoid wasting unmanned aerial vehicle resources, the number of unmanned aerial vehicles in the network should not exceed the number of sensors, namely K is less than or equal to I, U is usedkDenotes the kth drone, I-40, E in this exampleth＝100KJ，v＝10m/s，ef＝0.1KJ/s，eh＝0.1KJ/s，et＝0.05J/s；
(1b) K virtual sensors with the same coordinate position as the central controller O are initialized to be B ═ B1,B2...Bk,...BKAnd in order to avoid the situation that the unmanned aerial vehicle continuously accesses the virtual sensors, the distance between any two virtual sensors is set to be infinite, and all the unmanned aerial vehicles are positioned at the kth virtual sensor BkThe time of the over-the-air hovering and the communication are
Figure BDA0003123795030000061
In this example
Figure BDA0003123795030000062
(1c) Initializing ant population S ═ S containing M ants1,S2…Sm…SM}，M≥50，SmRepresents the mth ant; initializing path selection coefficients to q0The pheromone volatilization factor is rho, the iteration number is iter, the maximum iteration number is iter _ max, the iter _ max is more than or equal to 2000, K is equal to 1, and the minimum total energy consumption E of the unmanned aerial vehicle is realized when K is equal to 1bestInfinity, M in this example 50, q0＝0.9，ρ＝0.95，iter＝1，iter_max＝3000；
Step 2, constructing a sensor set to be accessed and initializing an optimal path set:
(2a) constructing a sensor set R to be accessed by a sensor A and a virtual sensor B, wherein the set R is { A, B } R }1,R2,...,Rn,...,RNAdding a virtual sensor set to expand the range of the first sensor to be accessed selected by ants when executing the improved ant colony algorithm, so as to expand the solution space of the improved ant colony algorithm and further reduce the complexity of unmanned aerial vehicle path planning, wherein N represents the total number of the sensors to be accessed, and N is equal to I + K, RnRepresents the nth sensor to be accessed, when n is equal to [1, I ∈]When R isnRepresents the sensor when n ∈ [ I +1, I + K]When R isnRepresenting a virtual sensor;
(2b) by using PathbestRepresenting a locally optimal path set, initialization
Figure BDA0003123795030000071
By PathminRepresenting a set of minimum energy consumption paths, initializing
Figure BDA0003123795030000072
Step 3, calculating flight energy consumption, hovering energy consumption and communication energy consumption of the unmanned aerial vehicle:
(3a) calculating every two sensors R to be accessed in the sensor set R to be accessedaAnd RbEuropean distance therebetween
Figure BDA0003123795030000073
The calculation formula is as follows:
Figure BDA0003123795030000074
wherein the content of the first and second substances,
Figure BDA0003123795030000075
and with
Figure BDA0003123795030000076
Respectively representing the sensor R to be accessedaAnd RbCoordinate of (A), Ra,RbE.g. R, and when Ra＝RbAt the time, set up
Figure BDA0003123795030000077
The method is used for avoiding data redundancy caused by repeated selection of the same sensor when ants select the sensor;
(3b) constructing an Euclidean distance matrix D corresponding to the R by NxN Euclidean distances, wherein the expression of the D is as follows:
Figure BDA0003123795030000078
(3c) calculating flight energy consumption of the unmanned aerial vehicle between any two sensors to be accessed through the Euclidean distance matrix D
Figure BDA0003123795030000079
Simultaneously calculating hovering energy consumption of the unmanned aerial vehicle when the unmanned aerial vehicle accesses any sensor to be accessed
Figure BDA00031237950300000710
Energy consumption of communication is
Figure BDA00031237950300000711
Figure BDA00031237950300000712
Figure BDA00031237950300000713
Figure BDA00031237950300000714
Step 4, initializing parameters of the improved ant colony algorithm:
define every two sensors R to be accessedaAnd RbHas a pheromone concentration of
Figure BDA0003123795030000081
The path heuristic information is
Figure BDA0003123795030000082
Initialization
Figure BDA0003123795030000083
τ0Initial value of pheromone concentration between any two sensors to be accessed, in this example, τ 01, path heuristic information
Figure BDA0003123795030000084
The calculation formula of (2) is as follows:
Figure BDA0003123795030000085
Figure BDA0003123795030000086
in the calculation process, the flying, hovering and communication energy consumption of the unmanned aerial vehicle between two sensors to be accessed are fully considered, so that a flight path with smaller total energy consumption is found for the unmanned aerial vehicle, wherein,
Figure BDA0003123795030000087
indicating that the drone is at the sensor R to be accessedaAnd RbThe energy consumption of the flying is reduced between the two modes,
Figure BDA0003123795030000088
indicating that the drone is at the sensor R to be accessedbAnd RNThe energy consumption of the flying is reduced between the two modes,
Figure BDA0003123795030000089
and
Figure BDA00031237950300000810
respectively indicate that the unmanned aerial vehicle is at the sensor R to be accessedbOverhead hover energy consumption and flight energy consumption,
Figure BDA00031237950300000811
indicating that the drone is at the sensor R to be accessedbTime of hovering over and communication, value thereof and sensor R to be accessedbThe traffic of the sensor to be accessed is divided into three types of high, medium and low in the present example, and the time required for the unmanned aerial vehicle to execute is 60s, 30s and 10s,
Figure BDA00031237950300000812
represents arbitrary;
step 5, establishing a feasible solution set and an infeasible solution set of the iteration:
(5a) let m equal to 1, initialize the feasible solution set of this iteration
Figure BDA00031237950300000813
Set of infeasible solutions
Figure BDA00031237950300000814
(5b) The mth ant SmThe set of sensors to be accessed is N (m) or N, and the set of sensors accessed is N
Figure BDA00031237950300000815
V (m) is an ordered set, and one sensor R to be accessed is randomly selected from N (m)nAs SmFirst sensor to be accessed, with RstartIs labeled, and R isnFrom N (m) into V (m);
(5c) generating a random number q, q ∈ (0, 1)]And judging q and the path selection coefficient q0Whether q > q is satisfied0If yes, calculate SmFrom RnTo any one of the sensors R to be accessed in N (m)w,RwTransition probability of epsilon N (m)
Figure BDA00031237950300000816
Figure BDA00031237950300000817
And using roulette rules based on transition probabilities
Figure BDA00031237950300000818
Selecting the next sensor R to be accessed in N (m)pOtherwise, directly selecting from R in N (m)nPoint out so that
Figure BDA00031237950300000819
The largest one of the sensors to be accessed is used as the sensor R to be accessed nextp，
Figure BDA0003123795030000091
Wherein the content of the first and second substances,
Figure BDA0003123795030000092
represents the current iteration RnAnd RwPheromone concentration between, alpha and beta respectively
Figure BDA0003123795030000093
And
Figure BDA0003123795030000094
in the present example, α ═ 1.5, β ═ 2.5;
(5d) r is to bepMoving from N (m) to V (m), judging
Figure BDA0003123795030000095
If true, R is appliedstartAdded into V (m), ensures that the first and the last sensor nodes in V (m) are the same sensor, and forms the mth ant SmPath V (m), abbreviated as mth path, is a closed path, otherwise let Rn＝RpAnd performing step (5 c);
(5e) since V (m) is a closed path, according to each virtual sensor BkThe m-th path v (m) is divided into K sub-paths and allocated to K drones, the start and end positions of each sub-path are the positions of the virtual sensors, and the energy consumption of each sub-path, that is, the K-th drone, is calculated
Figure BDA0003123795030000096
The energy consumption of each sub-path is the sum of the flight energy consumption of the unmanned aerial vehicle flying along the sub-path and the hovering energy consumption and communication energy consumption of all sensors accessing the sub-path, wherein the flight energy consumption of the unmanned aerial vehicle flying along the sub-path is the sum of the flight energy consumption of the unmanned aerial vehicle flying between two adjacent sensors on the sub-path, and the maximum sub-path energy consumption of the mth path is marked as
Figure BDA0003123795030000097
(5f) Determining the maximum sub-path energy consumption of the mth path
Figure BDA0003123795030000098
Whether or not to satisfy
Figure BDA0003123795030000099
If it explains that unmanned aerial vehicle when flying along this route, can be at energyAccessing the sensor under the constraint condition, and smoothly flying back to the central controller, namely V (m) is a feasible solution, putting V (m) into a feasible solution set Path ', otherwise, the Path V (m) is an infeasible solution, and putting V (m) into an infeasible solution set Path';
(5g) if M is less than M, making M equal to M +1, executing the step (5b), otherwise, executing the step (6);
step 6, determining a local optimal solution generated by the iteration:
(6a) num ' is used for representing the size of the feasible solution set Path ', namely the number of feasible solutions, and the mth Path Path in the Path ' is calculatedm′Total energy consumption of last K drones
Figure BDA00031237950300000910
m′∈[1,Num']Are combined with each other
Figure BDA00031237950300000911
Performing ascending sequence, and marking the minimum total energy consumption of the K unmanned aerial vehicles in the iteration as Ebest(iter) taking the Path corresponding to it as the local optimal Path Path of the K unmanned planesbest(iter) and adds it to the locally optimal Path set PathbestPerforming the following steps;
(6b) calculating the total energy consumption of K unmanned aerial vehicles on each Path in Path ″, and if K is 1, finding out the minimum total energy consumption E of the K unmanned aerial vehicles in the iterationmin(iter) if Emin(iter)＜EbestUpdate Ebest＝Emin(iter)；
And 7, updating the pheromone concentration:
(7a) selecting L paths according to the numerical value of Num': if Num 'is greater than or equal to L, and L is equal to M/5, selecting the first L paths in Path', wherein the L paths are feasible solutions, updating pheromone concentrations among sensors ranked on the first L feasible solutions, and helping the algorithm to find a feasible solution with lower total energy consumption for the unmanned aerial vehicle in the next iteration; if 0 < Num ' < L, randomly selecting F ═ L-Num ' paths in Path ' and Num ' paths in Path ' to form L paths together; if Num' is 0, randomly selecting L paths in Path ", wherein the random selection is to enlarge a solution space in the next iteration, thereby helping the algorithm to find a feasible solution;
(7b) updating the concentration of pheromone between two adjacent sensors on the selected path, wherein the updating formula is as follows:
Figure BDA0003123795030000101
according to the total energy consumption of K unmanned aerial vehicles on the selected Path, the pheromone concentration between the sensors is updated, the smaller the total energy consumption is, the larger the increment during pheromone updating is, the Path with the smaller total energy consumption can be found for the unmanned aerial vehicles while the algorithm convergence speed is accelerated, and Path is used for the unmanned aerial vehicleslRepresents the selected ith path, L ∈ [1, L]，
Figure BDA0003123795030000102
As a Path PathlThe total energy consumption of the last K drones,
Figure BDA0003123795030000103
show Path PathlUpper standby access sensor RcAnd RdConcentration of Mesopermonin
Figure BDA0003123795030000104
An updated value of (d);
step 8, judging whether the iteration is finished:
judging whether iter < iter _ max is true, if yes, iter is equal to iter +1, and executing the step (5), otherwise, executing the step (9);
step 9, obtaining a path planning result of the unmanned aerial vehicle:
judging local optimal path set
Figure BDA0003123795030000105
If yes, indicating that the unmanned aerial vehicles in the current number cannot access all sensors under the energy constraint condition, and executing the step (10) to update the number of the unmanned aerial vehicles, and if not, judging that the unmanned aerial vehicles in the current number cannot access all sensors under the energy constraint conditionWill PathbestThe minimum total energy consumption mark in the unmanned aerial vehicle is E, the Path corresponding to the minimum total energy consumption mark is used as the global optimal Path of the K unmanned aerial vehicles, and the Path and the K are output;
step 10, updating the unmanned aerial vehicle set and the virtual sensor set:
judging whether K is equal to 1, if yes, making
Figure BDA0003123795030000111
Avoids the increase of 1 for each time of the number of the unmanned aerial vehicles, reduces invalid calculation times, reduces the calculation complexity,
Figure BDA0003123795030000112
and (3) representing a lower limit, wherein the purpose is to ensure that the optimal solution cannot be skipped when the number of the unmanned aerial vehicles is updated, otherwise, making K equal to K +1, obtaining an updated unmanned aerial vehicle set U and a corresponding virtual sensor set B, and executing the step (2).
The technical effects of the invention are further explained by combining simulation experiments as follows:
1. simulation conditions and contents:
in a simulation experiment, the number of the sensors is respectively 30,40,50,60 and 70, the time of hovering the unmanned aerial vehicle above each sensor node is determined by the traffic of the sensor node, and the higher the traffic is, the longer the hovering time and the communication time are.
Simulation 1, comparing and simulating the minimum number of unmanned aerial vehicles required for data acquisition of different numbers of sensor nodes in a designated area in the prior art, and the result is shown in fig. 3.
Simulation 2, comparing and simulating the total energy consumption of the unmanned aerial vehicle required by the invention and the prior art when data acquisition is carried out on different numbers of sensor nodes in a specified area, and the result is shown in fig. 4.
2. And (3) simulation result analysis:
referring to fig. 3, when the present invention and the existing method for planning the path of the unmanned aerial vehicle based on the nearest neighbor policy are used to determine the number of the unmanned aerial vehicles to be used for accessing different numbers of sensors, the number of the unmanned aerial vehicles used in the present invention is less than the number of the unmanned aerial vehicles used in the prior art.
Referring to fig. 4, when the unmanned aerial vehicle path planning method based on the nearest neighbor strategy is adopted to plan the path for the unmanned aerial vehicle, the total energy consumption of the unmanned aerial vehicle is obviously lower than that of the unmanned aerial vehicle in the prior art, and compared with the prior art, the total energy consumption of the unmanned aerial vehicle is reduced, so that the cost of the unmanned aerial vehicle is reduced.

Claims (2)

1. An unmanned aerial vehicle path planning method for minimizing the number of unmanned aerial vehicles is characterized by comprising the following steps:
(1) initializing parameters:
the central controller with the coordinate position (0,0) distributed on the ground is initialized to have K unmanned aerial vehicles U ═ U { U ═ at the position O1,U2,...,Uk,...,UK}; initializing I sensors distributed on the ground as A ═ A1,A2,...,Ai,...,AII is more than or equal to 2, the ith sensor AiHas a position coordinate of (x)i,yi) (ii) a The maximum energy of all unmanned planes is EthThe flight speed is v, and the flight energy consumption, hovering energy consumption and communication energy consumption in unit time are ef、ehAnd etAt the i-th sensor AiThe time of the over-the-air hovering and the communication is ti，K≥1，UkRepresents the kth drone; k virtual sensors having the same coordinate position as that of the central controller O are initialized to B ═ B1,B2,...,Bk,...,BKThe distance between any two virtual sensors is ∞, allUnmanned aerial vehicle is at k virtual sensor BkThe time of the over-the-air hovering and the communication are
Figure FDA0003599902980000015
Initializing an ant population S-S comprising M ants1,S2,…,Sm,…,SM}，M≥50，SmRepresents the mth ant; initializing path selection coefficients to q0The pheromone volatilization factor is rho, the iteration number is iter, the maximum iteration number is iter _ max, the iter _ max is not less than 2000,
Figure FDA0003599902980000011
let iter be 1, K be 1, let K be 1 the minimum total energy consumption E of unmanned aerial vehiclebest＝∞；
(2) Constructing a sensor set to be accessed and initializing a local optimal path set:
constructing a sensor set R to be accessed by a sensor A and a virtual sensor B, wherein the set R is { A, B } R }1,R2,...,Rn,...,RNAnd initializing a local optimal path set
Figure FDA0003599902980000012
Where N denotes the total number of sensors to be accessed, N ═ I + K, RnRepresents the nth sensor to be accessed, when n is equal to [1, I ∈]When R isnRepresents the sensor when n ∈ [ I +1, I + K]When R isnRepresenting a virtual sensor;
(3) calculating flight energy consumption, hovering energy consumption and communication energy consumption of the unmanned aerial vehicle:
(3a) calculating every two sensors R to be accessed in the sensor set R to be accessedaAnd RbEuropean distance between
Figure FDA0003599902980000013
And constructing an Euclidean distance matrix D corresponding to R through NxN Euclidean distances, wherein Ra,RbE.g. R when Ra＝RbWhen it is used, order
Figure FDA0003599902980000014
The expression of D is:
Figure FDA0003599902980000021
(3b) calculating flight energy consumption of the unmanned aerial vehicle between any two sensors to be accessed through the Euclidean distance matrix D
Figure FDA0003599902980000022
Simultaneously calculating hovering energy consumption of the unmanned aerial vehicle when the unmanned aerial vehicle accesses any sensor to be accessed
Figure FDA0003599902980000023
Energy consumption of communication is
Figure FDA0003599902980000024
Figure FDA0003599902980000025
Figure FDA0003599902980000026
Figure FDA0003599902980000027
(4) Parameters for initializing the improved ant colony algorithm:
define every two sensors R to be accessedaAnd RbHas a pheromone concentration of
Figure FDA0003599902980000028
The path heuristic information is
Figure FDA0003599902980000029
Initialization
Figure FDA00035999029800000210
Wherein τ is0An initial value representing the concentration of pheromones between any two sensors to be accessed,
Figure FDA00035999029800000211
wherein the content of the first and second substances,
Figure FDA00035999029800000212
indicating that the drone is at the sensor R to be accessedaAnd RbThe energy consumption of the flying is reduced between the two modes,
Figure FDA00035999029800000213
indicating that the drone is at sensor R to be accessedbAnd RNThe energy consumption of the flying is reduced between the two modes,
Figure FDA00035999029800000214
and
Figure FDA00035999029800000215
respectively indicate that the unmanned aerial vehicle is at the sensor R to be accessedbOverhead hover energy consumption and flight energy consumption,
Figure FDA00035999029800000216
indicating that the drone is at the sensor R to be accessedbTime of the over-the-air hover and communication;
(5) and (3) constructing a feasible solution set and an infeasible solution set of the iteration:
(5a) let m be 1, initialize the feasible solution set of this iteration
Figure FDA00035999029800000217
Set of infeasible solutions
Figure FDA00035999029800000218
(5b) The mth ant SmN (m) R, the accessed sensor set
Figure FDA00035999029800000219
V (m) is an ordered set, and one sensor R to be accessed is randomly selected from N (m)nAs SmFirst sensor to be accessed, with RstartIs labeled, and R isnFrom N (m) into V (m);
(5c) generating a random number q, q ∈ (0, 1)]And judging q and the path selection coefficient q0Whether q > q is satisfied0If yes, calculate SmFrom RnTo any one of N (m) to-be-accessed sensor Rw,RwTransition probability of epsilon N (m)
Figure FDA0003599902980000031
And using roulette rules based on transition probabilities
Figure FDA0003599902980000032
Selecting the next sensor R to be accessed in N (m)pOtherwise, directly selecting from R in N (m)nPoint out so that
Figure FDA0003599902980000033
The largest one of the sensors to be accessed is used as the sensor R to be accessed nextpWherein
Figure FDA0003599902980000034
Represents the current iteration RnAnd RwPheromone concentration between, alpha and beta respectively
Figure FDA0003599902980000035
And
Figure FDA0003599902980000036
the degree of importance of;
(5d) r is to bepMoving from N (m) to V (m), judging
Figure FDA0003599902980000037
If true, R is appliedstartAdding into V (m) to obtain mth ant SmThe path of (A) is V (m), abbreviated as mth path, otherwise, let Rn＝RpAnd performing step (5 c);
(5e) according to each virtual sensor BkThe m-th path v (m) is divided into K sub-paths and allocated to K drones, the start and end positions of each sub-path are the positions of the virtual sensors, and the energy consumption of each sub-path, that is, the K-th drone, is calculated
Figure FDA0003599902980000038
The energy consumption of each sub-path is the sum of flight energy consumption of the unmanned aerial vehicle flying along the sub-path and hovering energy consumption and communication energy consumption for accessing all sensors on the sub-path, wherein the flight energy consumption of the unmanned aerial vehicle flying along the sub-path is the sum of flight energy consumption of the unmanned aerial vehicle flying between two adjacent sensors on the sub-path, and the maximum sub-path energy consumption of the mth path is marked as
Figure FDA0003599902980000039
(5f) Determining the maximum sub-path energy consumption of the mth path
Figure FDA00035999029800000310
Whether or not to satisfy
Figure FDA00035999029800000311
If yes, V (m) is a feasible solution, putting V (m) into a feasible solution set Path ', otherwise, if the Path V (m) is an infeasible solution, putting V (m) into an infeasible solution set Path';
(5g) if M is less than M, making M equal to M +1, executing the step (5b), otherwise, executing the step (6);
(6) determining a local optimal solution generated by the iteration:
(6a) num ' is used for representing the size of the feasible solution set Path ', namely the number of feasible solutions, and the mth Path Path in the Path ' is calculatedm′Total energy consumption of last K drones
Figure FDA00035999029800000312
And are aligned with
Figure FDA00035999029800000313
Performing ascending sequence, and marking the minimum total energy consumption of the K unmanned aerial vehicles in the iteration as Ebest(iter) taking the Path corresponding to it as the local optimal Path Path of the K unmanned planesbest(iter) and adds it to the locally optimal Path set PathbestPerforming the following steps;
(6b) calculating the total energy consumption of K unmanned aerial vehicles on each Path in Path ″, and if K is 1, finding out the minimum total energy consumption E of the K unmanned aerial vehicles in the iterationmin(iter) if Emin(iter)＜EbestUpdate Ebest＝Emin(iter)；
(7) And (3) updating the pheromone concentration:
(7a) selecting L paths according to the numerical value of Num': if Num 'is equal to or more than L, and L is equal to M/5, selecting the first L paths in Path'; if 0 < Num ' < L, randomly selecting F ═ L-Num ' paths in Path ' and Num ' paths in Path ' to form L paths together; if Num 'is 0, then randomly selecting L paths in Path';
(7b) updating the concentration of pheromones between two adjacent sensors on the selected path;
(8) judging whether the iteration is finished:
judging whether iter < iter _ max is true, if yes, iter is iter +1, executing the step (5), and if not, executing the step (9);
(9) obtaining a path planning result of the unmanned aerial vehicle:
judging local optimal path set
Figure FDA0003599902980000041
If yes, go to step (10), otherwise go to PathbestThe minimum total energy consumption mark in the Path is E, the Path corresponding to the minimum total energy consumption mark is used as the global optimal Path of the K unmanned aerial vehicles, and the global optimal Path and the number K of the unmanned aerial vehicles are output;
(10) updating the unmanned plane set and the virtual sensor set:
judging whether K is equal to 1, if yes, making
Figure FDA0003599902980000042
Otherwise, let K be K +1, obtain the updated set U of drones and the corresponding set B of virtual sensors, and execute step (2).
2. A method for planning a route for unmanned aerial vehicles to minimize the number of unmanned aerial vehicles according to claim 1, wherein the pheromone concentration between two adjacent sensors on the selected route is updated in step (7b) according to the following formula:
Figure FDA0003599902980000043
wherein, PathlRepresents the selected ith path, L ∈ [1, L ]]，
Figure FDA0003599902980000044
As a Path PathlThe total energy consumption of the last K drones,
Figure FDA0003599902980000045
show Path PathlUpper standby access sensor RcAnd RdConcentration of Mesopermonin
Figure FDA0003599902980000046
The update value of (2).
CN202110684212.6A 2021-06-21 2021-06-21 Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles Active CN113325875B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110684212.6A CN113325875B (en) 2021-06-21 2021-06-21 Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110684212.6A CN113325875B (en) 2021-06-21 2021-06-21 Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles

Publications (2)

Publication Number Publication Date
CN113325875A CN113325875A (en) 2021-08-31
CN113325875B true CN113325875B (en) 2022-06-07

Family

ID=77423906

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110684212.6A Active CN113325875B (en) 2021-06-21 2021-06-21 Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles

Country Status (1)

Country Link
CN (1) CN113325875B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114167898B (en) * 2021-12-15 2023-10-03 南京航空航天大学 Global path planning method and system for collecting data of unmanned aerial vehicle
CN114661063B (en) * 2022-03-22 2024-06-18 安徽工业大学 Unmanned aerial vehicle emergency communication flight control method
CN115755987B (en) * 2023-01-09 2023-06-30 南京邮电大学 Disaster data acquisition-oriented multi-unmanned aerial vehicle collaborative scheduling method

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109521794A (en) * 2018-12-07 2019-03-26 南京航空航天大学 A kind of multiple no-manned plane routeing and dynamic obstacle avoidance method
CN109547938A (en) * 2019-01-11 2019-03-29 西南大学 The method for planning track of unmanned plane in wireless sensor network
CN110324805A (en) * 2019-07-03 2019-10-11 东南大学 A kind of radio sensor network data collection method of unmanned plane auxiliary
CN110426039A (en) * 2019-07-04 2019-11-08 中国人民解放军陆军工程大学 The multiple no-manned plane paths planning method that the task based access control deadline minimizes
WO2021012584A1 (en) * 2019-07-25 2021-01-28 北京工业大学 Method for formulating single-task migration strategy in mobile edge computing scenario
CN112508369A (en) * 2020-11-27 2021-03-16 北京工商大学 Multi-unmanned aerial vehicle task allocation method based on improved ant colony algorithm
CN112859912A (en) * 2021-01-11 2021-05-28 中国人民解放军国防科技大学 Adaptive optimization method and system for unmanned aerial vehicle path planning in relay charging mode

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105717926A (en) * 2015-11-09 2016-06-29 江苏理工学院 Mobile robot traveler optimization method based on improved ant colony algorithm
CN109682380B (en) * 2019-01-16 2020-01-10 北京邮电大学 Communication unmanned aerial vehicle path optimization method and device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109521794A (en) * 2018-12-07 2019-03-26 南京航空航天大学 A kind of multiple no-manned plane routeing and dynamic obstacle avoidance method
CN109547938A (en) * 2019-01-11 2019-03-29 西南大学 The method for planning track of unmanned plane in wireless sensor network
CN110324805A (en) * 2019-07-03 2019-10-11 东南大学 A kind of radio sensor network data collection method of unmanned plane auxiliary
CN110426039A (en) * 2019-07-04 2019-11-08 中国人民解放军陆军工程大学 The multiple no-manned plane paths planning method that the task based access control deadline minimizes
WO2021012584A1 (en) * 2019-07-25 2021-01-28 北京工业大学 Method for formulating single-task migration strategy in mobile edge computing scenario
CN112508369A (en) * 2020-11-27 2021-03-16 北京工商大学 Multi-unmanned aerial vehicle task allocation method based on improved ant colony algorithm
CN112859912A (en) * 2021-01-11 2021-05-28 中国人民解放军国防科技大学 Adaptive optimization method and system for unmanned aerial vehicle path planning in relay charging mode

Non-Patent Citations (8)

* Cited by examiner, † Cited by third party
Title
An intelligent cooperative mission planning scheme of UAV swarm in uncertain dynamic environment;Ziyang Zhen；Yan Chen；Liangdong Wen；Bing Han;《Aerospace Science and Technology》;20200320;全文 *
Chen Gao ; Huajun Gong ; Ziyang Zhen ; Qiannan Zhao ; Yili Sun.Three dimensions formation flight path planning under radar threatening environment.《Proceedings of the 33rd Chinese Control Conference》.2014, *
Jilei Yan ; Jiandong Li ; Linjing Zhao ; Rui Chen.Robust Joint Transmit Beamforming With QoS Guarantees in Time-Asynchronous DAS.《IEEE Transactions on Vehicular Technology》.2014, *
Mingmeng Luo ; Jiandong Li ; Jianpeng Ma ; Hongyan Li ; Min Sheng.Energy-Efficient Flow Routing and Scheduling in Hybrid Data Center Networks.《2019 IEEE Global Communications Conference (GLOBECOM)》.2020, *
Modeling and simulation of dynamic ant colony’s labor division for task allocation of UAV swarm;Husheng Wu；Hao Li；Renbin Xiao；Jie Liu;《Physica A: Statistical Mechanics and its Applications》;20171003;全文 *
Momena Monwar ; Omid Semiari ; Walid Saad.Optimized Path Planning for Inspection by Unmanned Aerial Vehicles Swarm with Energy Constraints.《2018 IEEE Global Communications Conference (GLOBECOM)》.2019, *
Xing Chen ; Rong Xu ; Jiabao Zhao.Multi-Objective Route Planning for UAV.《2017 4th International Conference on Information Science and Control Engineering (ICISCE)》.2017, *
无人机辅助的大规模机器类通信网络能效优化;朱恺誉;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20210415;全文 *

Also Published As

Publication number Publication date
CN113325875A (en) 2021-08-31

Similar Documents

Publication Publication Date Title
CN113325875B (en) Unmanned aerial vehicle path planning method for minimizing number of unmanned aerial vehicles
Liu et al. Energy-efficient UAV crowdsensing with multiple charging stations by deep learning
CN111352417B (en) Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path
Kumar et al. Federated control with hierarchical multi-agent deep reinforcement learning
Wei et al. Computation offloading over multi-UAV MEC network: A distributed deep reinforcement learning approach
CN110375761A (en) Automatic driving vehicle paths planning method based on enhancing ant colony optimization algorithm
CN112269382B (en) Robot multi-target path planning method
CN116451934B (en) Multi-unmanned aerial vehicle edge calculation path optimization and dependent task scheduling optimization method and system
CN112508369A (en) Multi-unmanned aerial vehicle task allocation method based on improved ant colony algorithm
Mousa et al. Efficient UAV-based mobile edge computing using differential evolution and ant colony optimization
CN113098714A (en) Low-delay network slicing method based on deep reinforcement learning
CN113188547A (en) Unmanned aerial vehicle path planning method and device, controller and storage medium
CN108712335A (en) Network access scheduling method, system, device and storage medium
Khodaparast et al. Deep reinforcement learning based energy efficient multi-UAV data collection for IoT networks
CN113485409A (en) Unmanned aerial vehicle path planning and distribution method and system for geographic fairness
CN112965527A (en) Unmanned aerial vehicle formation topology generation optimization method based on improved artificial bee colony algorithm
CN114828146A (en) Routing method for geographical position of unmanned cluster based on neural network and iterative learning
CN114020024B (en) Unmanned aerial vehicle path planning method based on Monte Carlo tree search
Pan et al. Fresh data collection for UAV-assisted IoTs based on proximity-remote region collaboration
CN113382060B (en) Unmanned aerial vehicle track optimization method and system in Internet of things data collection
CN110986954A (en) Military transport plane route planning method based on wolf optimization algorithm
CN113283827B (en) Two-stage unmanned aerial vehicle logistics path planning method based on deep reinforcement learning
CN115545106A (en) AoI sensitive data collection method and system in multiple unmanned aerial vehicles
CN113554215A (en) Helicopter scheduling route planning method based on ant colony-genetic fusion algorithm
Liu Shortest path selection algorithm for cold chain logistics transportation based on improved artificial bee colony

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant