CN115167501A - Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm - Google Patents

Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm Download PDF

Info

Publication number
CN115167501A
CN115167501A CN202210654295.9A CN202210654295A CN115167501A CN 115167501 A CN115167501 A CN 115167501A CN 202210654295 A CN202210654295 A CN 202210654295A CN 115167501 A CN115167501 A CN 115167501A
Authority
CN
China
Prior art keywords
antibody
node
unmanned aerial
aerial vehicle
candidate
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.)
Pending
Application number
CN202210654295.9A
Other languages
Chinese (zh)
Inventor
朱先强
郭园园
陆敏
朱承
梁伟
王骏
周鋆
刘斌
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.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
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 National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202210654295.9A priority Critical patent/CN115167501A/en
Publication of CN115167501A publication Critical patent/CN115167501A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10Simultaneous control of position or course in three dimensions
    • G05D1/107Simultaneous control of position or course in three dimensions specially adapted for missiles

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)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to an unmanned aerial vehicle flight path optimization method, device and equipment based on an immune clone algorithm. The method comprises the following steps: calculating the environmental threat cost of an area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight; dividing a region to be planned into grids by adopting a grid method, wherein all nodes in the grids form a node set; calculating and updating the antibody group of the node set according to an immune clone algorithm to obtain a final antibody group; optimizing the final antibody group according to a target function of unmanned aerial vehicle track planning to obtain an optimal antibody; the optimal antibody is the optimal track of the unmanned aerial vehicle. By adopting the method, the unmanned aerial vehicle trajectory planning efficiency can be improved.

Description

Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm
Technical Field
The application relates to the technical field of unmanned aerial vehicle flight path planning, in particular to an unmanned aerial vehicle flight path optimization method and device based on an immune clone algorithm, computer equipment and a storage medium.
Background
With the development of unmanned aerial vehicle technology, unmanned Aerial Vehicles (UAVs) are widely used in life due to their safety, flexibility and reusability, and have an important role in delivering rescue goods and materials in disaster scenes, and with the improvement of rescue complexity, the flight safety of an unmanned aerial vehicle has become a key for successfully performing delivery of rescue goods and materials, and the core of safe flight is flight path planning. The unmanned aerial vehicle track planning is to design a flight path from an initial position to a target position under the condition of meeting the unmanned aerial vehicle performance constraint and the surrounding environment constraint, so that the damage cost is the lowest. Generally, the planned path in emergency of rescue helps to improve the rescue efficiency.
However, the existing method is easy to deviate from the optimal solution when the unmanned aerial vehicle trajectory planning is carried out, the calculation complexity is high, the convergence speed is limited, and the efficiency is low.
Disclosure of Invention
Therefore, it is necessary to provide an unmanned aerial vehicle trajectory optimization method, apparatus, computer device and storage medium based on an immune clone algorithm, which can improve the unmanned aerial vehicle trajectory planning efficiency.
An unmanned aerial vehicle flight path optimization method based on an immune clone algorithm, the method comprising:
acquiring a region to be planned;
calculating the environmental threat cost of an area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight;
dividing a region to be planned into grids by adopting a grid method, wherein all nodes in the grids form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicle in the area to be planned;
calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors, and taking the node with the maximum transition probability as the next transition node to obtain an initial antibody group; the antibody is an unmanned aerial vehicle track;
selecting an initial antibody population according to a clone selection algorithm selected by the championship to obtain a first candidate antibody population;
performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group;
combining the second candidate antibody group and the third candidate antibody group to carry out antibody modification to obtain a fourth candidate antibody group;
performing rapid non-dominated sorting on a fourth candidate antibody group, calculating a crowded distance, and updating the fourth candidate antibody group according to the non-dominated sorting and the crowded distance to obtain a final antibody group;
optimizing the final antibody group according to a target function of the unmanned aerial vehicle flight path planning to obtain an optimal antibody; the optimal antibody is the optimal track of the unmanned aerial vehicle.
In one embodiment, the method for setting the target function of the unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of the unmanned aerial vehicle flight comprises the following steps:
setting an objective function of the unmanned aerial vehicle flight path planning as
Figure BDA0003688617710000021
Wherein, J length Represents the fuel cost, w L Representing coefficient, L track length, J threat Represents a threat cost, w R ,w M ,w A ,w C ,w H And w T Threat weight coefficients of radar, missile, gun, climate, altitude and mountain range respectively; j. the design is a square R ,J M ,J A ,J C ,J H And J T Respectively, radar, missile, artillery, weather, altitude, and mountain threat costs.
In one embodiment, calculating the transition probability of each node in the node set according to the leading factor and the heuristic factor includes:
calculating the transition probability of each node in the node set according to the guide factor and the heuristic factor to obtain the transition probability of the node
Figure BDA0003688617710000022
Wherein i, j and s respectively represent any node in the node set, eta j Denotes a heuristic factor, λ j Denotes a lead factor, alpha denotes the importance of a elicitor, beta denotes the importance of a lead factor, B k,i Representing a set of nodes.
In one embodiment, selecting the initial population of antibodies according to a tournament-selected clone selection algorithm to obtain a first candidate population of antibodies comprises:
setting the scale of the championship as n, setting the scale of the initial antibody group as m, randomly selecting n antibodies from the initial antibody group for comparison, retaining the antibodies with the lowest non-dominance grade and the highest crowding distance, and repeating the process for m times to obtain m antibodies; the m antibodies are the first candidate antibody population.
In one embodiment, the step of subjecting the first candidate antibody population to an immunocloning procedure and an immunogenetic procedure to obtain a second candidate antibody population and a third candidate antibody population comprises:
performing an immunocoloration operation on the first candidate antibody to obtain a second candidate antibody population
P (2) (t)=P (1)1 (t)+P (1)2 (t)+…+P (1)mc (t)={p 1 (1)1 (t),…,
p m (1)1 (t)}+…+{p 1 (1)mc (t),…,p m (1)mc (t)}={p 1 (2) (t),p 2 (2) (t),…,p N(m) (2) (t)}
Wherein N (m) = m × m c M is the number of antibodies retained by the selection procedure, m c Is the cloning ratio, P (1) (t)={p 1 (1) (t),p 2 (1) (t),…,p m (1) (t) } is the first candidate antibody population.
In one embodiment, a first candidate antibody group is subjected to gene recombination and gene mutation, in the gene recombination, two antibodies are randomly selected from the first candidate antibody group, the starting points and the end points of the two antibodies are fixed, the node pairs closest to each other in the two antibodies are calculated, if there is only one pair, the two nodes are selected as an intersection, the two antibodies before and after the intersection are exchanged according to recombination probability, if there are multiple pairs, one of the two antibodies is randomly selected as the intersection, and the two antibodies before and after the two intersections are exchanged according to recombination probability to obtain an antibody group after the gene recombination;
fixing the starting point and the end node of each antibody in the antibody group after gene recombination, randomly selecting one node in the antibodies to mutate in a mutation range, and obtaining a third candidate antibody group; the mutation range is the intersection of the set of neighbor nodes of the ith node and the set of neighbor nodes of the (i + 1) th node.
In one embodiment, combining the second candidate antibody population with the third candidate antibody population for antibody modification to yield a fourth candidate antibody population comprises:
combining the second candidate antibody group and the third candidate antibody group, traversing all nodes of each antibody in the combined antibody group, if the ith node and the jth node are continuous on a flight path, and the jth node is not in the neighbor set Ne of the ith node i Then, the jth node is corrected, and the neighbor node set Ne of the ith node is selected i And neighbor node set Ne of jth node j As the insertion node set B insert If B is insert Null indicates more than two grids between the ith node and the jth node, the antibody is deleted if B insert If not, randomly selecting a node as an insertion node to obtain a modified fourth candidateA population of antibodies.
In one embodiment, updating the fourth candidate antibody population according to the non-dominated ranking and crowding distance, resulting in a final antibody population, comprises:
the method comprises the following steps: setting a =1, generating a renewed antibody population G;
step two: from the fourth candidate antibody group P (4) Selecting an antibody group F with non-dominant ordering a in (t), combining the antibody groups F and G to generate a combined group F + G = F ≧ G, performing non-dominant ordering on the combined group, and recording the non-dominant ordering value of the combined group F + G as length (F + G);
step three: if length (F + G) < N, N indicates the size of the final antibody population, F is added to G, a = a +1, go to step two; if length (F + G) > N, let NM = N-length (F + G), sort the antibodies in F according to the crowding distance, add the top NM antibodies to G; if length (F + G) = N, add F to G; g is the final antibody population.
An unmanned aerial vehicle collaborative flight path planning device based on an immune clone algorithm, the device comprises:
the unmanned aerial vehicle flight path planning target function building module is used for obtaining an area to be planned; calculating the environmental threat cost of an area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight;
the area dividing module is used for dividing an area to be planned into grids by adopting a grid method, and all nodes in the grids form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicle in the area to be planned;
the initial antibody cluster building module is used for calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors, and taking the node with the maximum transition probability as the next transition node to obtain an initial antibody cluster; the antibody is an unmanned aerial vehicle track;
the antibody population optimization module is used for selecting an initial antibody population according to a clone selection algorithm selected by the championship to obtain a first candidate antibody population; performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group; combining the second candidate antibody group and the third candidate antibody group to perform antibody modification to obtain a fourth candidate antibody group; performing rapid non-dominated sorting on the fourth candidate antibody group, calculating a crowded distance, and updating the fourth candidate antibody group according to the non-dominated sorting and the crowded distance to obtain a final antibody group;
the optimizing module is used for optimizing the final antibody group according to the target function of the unmanned aerial vehicle track planning to obtain an optimal antibody; the optimal antibody is the optimal track of the unmanned aerial vehicle.
A computer device comprising a memory storing a computer program and a processor implementing the following steps when the computer program is executed:
acquiring a region to be planned;
calculating the environmental threat cost of an area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight;
dividing a region to be planned into grids by adopting a grid method, wherein all nodes in the grids form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicle in the area to be planned;
calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors, and taking the node with the maximum transition probability as the next transition node to obtain an initial antibody group; the antibody is an unmanned aerial vehicle track;
selecting an initial antibody population according to a clone selection algorithm selected by a championship to obtain a first candidate antibody population;
performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group;
combining the second candidate antibody group and the third candidate antibody group to perform antibody modification to obtain a fourth candidate antibody group;
performing rapid non-dominated sorting on a fourth candidate antibody group, calculating a crowding distance, and updating the fourth candidate antibody group according to the non-dominated sorting and the crowding distance to obtain a final antibody group;
optimizing the final antibody group according to a target function of the unmanned aerial vehicle flight path planning to obtain an optimal antibody; the optimal antibody is the optimal track of the unmanned aerial vehicle.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a region to be planned;
calculating the environmental threat cost of an area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight;
dividing a region to be planned into grids by adopting a grid method, wherein all nodes in the grids form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicle in the area to be planned;
calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors, and taking the node with the maximum transition probability as the next transition node to obtain an initial antibody group; the antibody is an unmanned aerial vehicle track;
selecting an initial antibody population according to a clone selection algorithm selected by a championship to obtain a first candidate antibody population;
performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group;
combining the second candidate antibody group and the third candidate antibody group to carry out antibody modification to obtain a fourth candidate antibody group;
performing rapid non-dominated sorting on a fourth candidate antibody group, calculating a crowding distance, and updating the fourth candidate antibody group according to the non-dominated sorting and the crowding distance to obtain a final antibody group;
optimizing the final antibody group according to a target function of unmanned aerial vehicle track planning to obtain an optimal antibody; the optimal antibody is the optimal flight path of the unmanned aerial vehicle.
According to the unmanned aerial vehicle collaborative flight path planning method, the unmanned aerial vehicle collaborative flight path planning device, the computer equipment and the storage medium, threat cost and fuel cost in a to-be-planned area are set as target functions of unmanned aerial vehicle flight path planning, threat cost is favorably reduced when flight path selection is subsequently carried out, flight safety is improved, stable performance of the unmanned aerial vehicle is guaranteed, the to-be-planned area is divided into grids by adopting a grid method, a plurality of adjacent nodes in the grids form unmanned aerial vehicle flight paths, heuristic factors and guide factors are introduced in an initialization process to generate high-quality antibodies, node transfer is more effective, quality of initial antibodies is improved, convergence speed is accelerated, antibody groups are continuously optimized through immune clone operation and immune gene operation, infeasible antibodies are corrected, feasibility of the antibodies is improved, and then infeasible antibodies are modified to enhance diversity of the antibody groups, a plurality of optimized candidate flight paths of the unmanned aerial vehicle are finally obtained, final antibody groups are optimized according to the target functions of the unmanned aerial vehicle flight path planning, and the optimal flight path planning efficiency is further improved.
Drawings
Fig. 1 is a schematic flow chart of a method for planning a collaborative flight path of an unmanned aerial vehicle based on an immune clone algorithm in an embodiment;
FIG. 2 is a diagram of a reorganization operator in one embodiment;
FIG. 3 is a diagram of a mutation operator in one embodiment;
fig. 4 is a block diagram illustrating an architecture of an apparatus for planning a collaborative flight path of an unmanned aerial vehicle based on an immune clone algorithm according to an embodiment;
FIG. 5 is a diagram of the internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, there is provided a method for planning a collaborative flight path of an unmanned aerial vehicle based on an immune clone algorithm, including the following steps:
step 102, acquiring a region to be planned; and calculating the environmental threat cost of the area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight.
Unmanned aerial vehicles are mainly limited by environmental threats and performance constraints during flight. Therefore, the establishment of the objective function mainly takes into account the threat cost and the fuel cost. Threat sources in a battlefield environment comprise radars, missiles, artillery, climate, altitude or mountains, environment threat cost calculation is carried out on an area to be planned, and the threat cost is given by the following formula:
J threat =w R ·J R +w M ·J M +w A ·J A +w C ·J C +w H ·J H +w T ·J T
wherein, w R ,w M ,w A ,w C ,w H And w T Respectively, threat weight coefficients for radar, missile, artillery, climate, altitude, and mountains. J is a unit of R ,J M ,J A ,J C ,J H And J T Respectively, radar, missile, artillery, weather, altitude, and mountain threat costs.
Figure BDA0003688617710000081
In the above formula, N L Number of track nodes, N R For the number of radar threats,
Figure BDA0003688617710000082
the Euclidean distance between the ith node and the kth radar is obtained, and the radar detection probability is as follows:
Figure BDA0003688617710000083
Figure BDA0003688617710000084
is the minimum detection distance that the drone will be detected after entering this range,
Figure BDA0003688617710000085
the maximum detection distance that the unmanned aerial vehicle will not be threatened after being far away from the range.
Figure BDA0003688617710000086
In the above formula, N M Is the number of threats to the missile,
Figure BDA0003688617710000087
is the Euclidean distance between the ith node and the kth missile, and the damage probability of the missiles is as follows:
Figure BDA0003688617710000088
Figure BDA0003688617710000089
is the minimum injury range that the unmanned aerial vehicle will be destroyed after entering the range,
Figure BDA00036886177100000810
the maximum injury range that the unmanned aerial vehicle can not be threatened after being far away from the range is provided.
Figure BDA00036886177100000811
In the above formula, N A Is the number of artillery threats that,
Figure BDA00036886177100000812
is the euclidean distance between the ith node and the kth air defense weapon,the damage probability of the artillery is as follows:
Figure BDA0003688617710000091
Figure BDA0003688617710000092
is the minimum injury range that the unmanned aerial vehicle will be destroyed after entering the range,
Figure BDA0003688617710000093
the maximum injury range that unmanned aerial vehicle can not receive the threat after keeping away from this scope.
Figure BDA0003688617710000094
In the above formula, N C Is the number of weather threats that may be present,
Figure BDA0003688617710000095
is the euclidean distance between the ith node and the kth weather threat, and the influence probability of the weather is:
Figure BDA0003688617710000096
Figure BDA0003688617710000097
is the minimum injury range that the drone will be destroyed once it enters this range,
Figure BDA0003688617710000098
is the maximum injury range that the drone will not be threatened once it is far from this range.
Figure BDA0003688617710000099
In the above formula, h i Is the height of node i.
Figure BDA00036886177100000910
Figure BDA00036886177100000911
Figure BDA00036886177100000912
Is the distance between the ith node and the central axis of the kth mountain,
Figure BDA00036886177100000913
is the radius of the cross section of the mountain of height h,
Figure BDA00036886177100000914
is the minimum damage range of the unmanned plane impacting the ground after entering the range,
Figure BDA00036886177100000915
the maximum damage range that the unmanned aerial vehicle is not threatened by the terrain after leaving the range.
The fuel cost associated with the flight path length is given by the following equation:
J length =w L ·L
wherein w L Representing the coefficient, L represents the track length,
Figure BDA0003688617710000101
N L representing the number of track nodes.
An objective function of unmanned aerial vehicle flight path planning is constructed according to the environment threat cost and the fuel cost of unmanned aerial vehicle flight, so that the threat cost is reduced, the flight safety is improved, and the stable performance is ensured.
Step 104, dividing the area to be planned into grids by adopting a grid method, wherein all nodes in the grids form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicles in the area to be planned.
The mesh method is adopted to divide the area to be planned into meshes, nodes in the meshes represent the flight point positions of the unmanned aerial vehicle in the area to be planned, namely the positions of the unmanned aerial vehicle passing through the flight path, so that the positions and the flight path of the unmanned aerial vehicle can be calculated and obtained more clearly and accurately, and the flight path planning is facilitated.
106, calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors, and taking the node with the maximum transition probability as the next transition node to obtain an initial antibody group; the antibody is an unmanned aerial vehicle track.
The key point of generating the initial antibody set is how the nodes are transmitted, the transfer rule is formed by introducing the guide factors and the heuristic factors, the heuristic factors are beneficial to node transfer to avoid threats as much as possible, the guide factors can provide direction information for the node transfer, the transfer probability of each node in the node set is calculated, the node with the maximum transfer probability is used as the next transfer node, the size of the initial antibody group is set, the starting point is continuously changed, and a plurality of tracks, namely candidate tracks, can be generated in the node transfer process, so that the initial antibody group is generated.
108, selecting an initial antibody population according to a clone selection algorithm selected by the championship to obtain a first candidate antibody population; performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group; combining the second candidate antibody group and the third candidate antibody group to perform antibody modification to obtain a fourth candidate antibody group; and performing rapid non-dominant sorting on the fourth candidate antibody group, calculating a crowded distance, and updating the fourth candidate antibody group according to the non-dominant sorting and the crowded distance to obtain a final antibody group.
Clonal selection may select for antibodies with higher affinity. The tournament selection method selects antibodies with higher affinity to ensure the quality and diversity of offspring populations, the immune clone operation is to generate more antibodies by copying a certain proportion of excellent antibodies, and then more genetic operations can be executed to expand the search space, the immune genetic operations comprise genetic recombination and genetic mutation, the diversity of the populations can be enhanced, but two infeasible antibodies can be generated in the recombination and mutation processes, and infeasible antibodies containing repeated nodes can be directly deleted, because the antibodies are likely to be closed loops; other feasible antibodies comprising two continuous nodes spanning multiple grids are possibly corrected, node pairs with small span can be supplemented by the nodes to enable the antibodies to be feasible, the antibodies are modified subsequently and some infeasible antibodies are corrected, the feasibility of the antibodies can be improved, the antibody group is optimized in multiple rounds, finally, redundant antibodies exceeding the size of the initial antibody group are removed according to non-dominated sorting and crowding distance, the size of the antibody group is enabled to be unchanged, the optimized final antibody group is obtained, the antibodies in the final antibody group represent candidate tracks of the unmanned aerial vehicle, and the candidate tracks of the unmanned aerial vehicle are optimized by optimizing the antibody group.
110, optimizing the final antibody group according to a target function of unmanned aerial vehicle track planning to obtain an optimal antibody; the optimal antibody is the optimal flight path of the unmanned aerial vehicle.
And optimizing the final antibody group according to a target function of unmanned aerial vehicle track planning, and selecting a track with the minimum track cost from the optimized multiple candidate tracks as an optimal track, thereby improving the unmanned aerial vehicle track planning efficiency.
According to the unmanned aerial vehicle collaborative flight path planning method based on the immune clone algorithm, threat cost and fuel cost in a region to be planned are set as target functions of unmanned aerial vehicle flight path planning, threat cost reduction is facilitated during subsequent flight path selection, flight safety is improved, stable performance of an unmanned aerial vehicle is guaranteed, the region to be planned is divided into grids by adopting a grid method, a plurality of adjacent nodes in the grids form the unmanned aerial vehicle flight path, heuristic factors and guide factors are introduced in an initialization process to generate high-quality antibodies, node transfer is more effective, quality of the initial antibodies is improved, convergence speed is accelerated, antibody groups are continuously optimized through immune clone operation and immune gene operation, infeasible antibodies are corrected, feasibility of the antibodies is improved, infeasible antibodies are modified to enhance diversity of the antibody groups, a plurality of candidate flight paths after optimization of the unmanned aerial vehicle are finally obtained, a final antibody group is optimized according to the target functions of the unmanned aerial vehicle flight path planning, the flight path with the lowest flight path cost is selected from the optimized candidate flight paths to serve as the optimal flight path, and planning efficiency of the unmanned aerial vehicle flight path planning is improved.
In one embodiment, the method for setting the target function of the unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of the unmanned aerial vehicle flight comprises the following steps:
setting an objective function of the unmanned aerial vehicle flight path planning to be according to the environmental threat cost and the fuel cost of the unmanned aerial vehicle flight
Figure BDA0003688617710000121
Wherein, J length Represents the fuel cost, w L Representing coefficient, L track length, J threat Represents a threat cost, w R ,w M ,w A ,w C ,w H And w T Threat weight coefficients of radar, missile, gun, climate, altitude and mountain range respectively; j. the design is a square R ,J M ,J A ,J C ,J H And J T Respectively, radar, missile, artillery, weather, altitude, and mountain threat costs.
In one embodiment, calculating the transition probability of each node in the node set according to the guidance factor and the heuristic factor includes:
calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors to obtain the transition probability of the node
Figure BDA0003688617710000122
Wherein i, j and s respectively represent any node in the node set, η j Denotes a heuristic factor, λ j Denotes a leading factor, alpha denotes the importance of a heuristic factorSex, beta indicates the importance of the leader, B k,i A set of nodes is represented.
In a particular embodiment, the key to generating the initial set of antibodies is how the nodes transmit. When one node i in the node set Bik is selected as the next node, a heuristic factor and a leading factor are introduced to form a transfer rule, the transfer probability of each node i in the node set is calculated, and then the node with the maximum transmission probability is selected as the next node. The heuristic factors are calculated as follows:
Figure BDA0003688617710000131
wherein w R ,w M ,w A ,w C ,w H And w T Respectively, threat weight coefficients for radar, missile, artillery, climate, altitude, and mountains. N is a radical of R ,N M ,N A ,N C And N T Respectively the number of radars, missiles, artillery, weather and mountains.
Figure BDA0003688617710000132
Representing the distance between the jth node and the nth radar threat,
Figure BDA0003688617710000133
representing the distance between the jth node and the nth missile threat,
Figure BDA0003688617710000134
representing the distance between the jth node and the nth gun.
Figure BDA0003688617710000135
Representing the distance between the jth node and the nth weather threat. As for the height of the jth node,
Figure BDA0003688617710000136
is the distance between the jth node and the nth mountain. The larger the heuristic factor, the greater the distance between the node and the threat sourceAnd (4) far away.
The guidance factor is calculated as follows:
Figure BDA0003688617710000137
wherein, d j,end Representing the jth node and the end node p k,end The distance between them. The larger the guidance factor, the smaller the distance between the node and the end node.
Heuristic factors help node migration to avoid threats as much as possible, and guidance factors can provide direction information for node migration. By introducing heuristic factors and guide factors, the node transfer is more effective, so that the quality of the initial antibody is improved, and the convergence speed of the method is accelerated.
With the determination of the transition rule, the initial antibody can be obtained by searching for a node from the start point to the end node. After performing the above operation N times, N antibodies were obtained to form an initial antibody population.
P(t)={p 1 (t),p 2 (t),…,p N (t)}
Wherein t represents the current generation, p i (t) represents an antibody, p i (t)={Start,p i1 ,p i2 ,…,p ik ,End},p ik Number of representation nodes, i k ∈{1,2,…,m×n}。
In one embodiment, selecting the initial population of antibodies according to a tournament-selected clone selection algorithm to obtain a first candidate population of antibodies comprises:
setting the scale of the championship as n, setting the scale of the initial antibody group as m, randomly selecting n antibodies from the initial antibody group for comparison, retaining the antibodies with the lowest non-dominance grade and the highest crowding distance, and repeating the process for m times to obtain m antibodies; m antibodies are the first candidate antibody population.
In a specific example, the tournament selection clone selection algorithm is shown in table 1:
Figure BDA0003688617710000141
first, the race scale was set to n and the size of the selected antibody population was set to m. N antibodies were then randomly selected from the antibody population for comparison, leaving antibodies with smaller non-dominant rank and larger crowding distance for the next generation. Repeating the above process m times to retain m kinds of antibodies in the next generation, and obtaining the first candidate antibody group P (1) (t)={p 1 (1) (t),p 2 (1) (t),…,p m (1) (t)}。
In one embodiment, the step of subjecting the first candidate antibody population to an immunocontoloration procedure and an immunogenetic procedure to obtain a second candidate antibody population and a third candidate antibody population comprises:
performing an immunocoloration operation on the first candidate antibody to obtain a second candidate antibody population
P (2) (t)=P (1)1 (t)+P (1)2 (t)+…+P (1)mc (t)={p 1 (1)1 (t),…,
p m (1)1 (t)}+…+{p 1 (1)mc (t),…,p m (1)mc (t)}={p 1 (2) (t),p 2 (2) (t),…,p N(m) (2) (t)}
Wherein N (m) = m × m c M is the number of antibodies retained by the selection procedure, m c Is the cloning ratio, P (1) (t)={p 1 (1) (t),p 2 (1) (t),…,p m (1) (t) } is the first candidate antibody population.
In one embodiment, a first candidate antibody group is subjected to gene recombination and gene mutation, in the gene recombination, two antibodies are randomly selected from the first candidate antibody group, the starting points and the end points of the two antibodies are fixed, the node pairs closest to each other in the two antibodies are calculated, if there is only one pair, the two nodes are selected as an intersection, the two antibodies before and after the intersection are exchanged according to recombination probability, if there are multiple pairs, one of the two antibodies is randomly selected as the intersection, and the two antibodies before and after the two intersections are exchanged according to recombination probability to obtain an antibody group after the gene recombination;
fixing the starting point and the end node of each antibody in the antibody group after gene recombination, randomly selecting one node in the antibodies to mutate in a mutation range, and obtaining a third candidate antibody group; the mutation range is the intersection of the set of neighbor nodes of the ith node and the set of neighbor nodes of the (i + 1) th node.
In particular embodiments, immunogenetic manipulation includes genetic recombination and genetic mutation, which can enhance population diversity. Random recombination and mutation readily produce antibodies that are not viable. Non-viable antibodies include: an antibody comprising a repeating node or an antibody comprising two adjacent nodes spanning multiple grids. Therefore, not only is it desirable to produce a population of antibodies with good diversity, but consideration is also given to improving the feasibility of antibodies during gene recombination and gene mutation.
In genetic recombination, two antibodies are randomly selected from the progeny population and their start and end points are fixed. Selecting the nearest two nodes as the crossover point may reduce the impracticability of generating antibodies. The pair of nodes that are closest to each other in the two antibodies is then calculated. The number of pairs may be one or more. If there is a pair, selecting the two nodes as a cross point, and exchanging two antibodies before and after the cross point according to recombination probability; if there are multiple pairs, one of them is randomly selected as a crossover point, and the two antibodies before and after the two crossover points are exchanged according to the recombination probability, as shown in FIG. 2.
For each antibody, when the start and end nodes were fixed, one node was randomly selected for mutation, and the mutation operator is shown in fig. 3. Randomly selecting the ith node as a mutation point, and searching the mutated range B mutation Is the intersection of the set of neighbor nodes of the ith node and the set of neighbor nodes of the (i + 1) th node, B insert =Ne i-1 ∩Ne +1
The antibody population obtained by the immune gene operator is as follows:
P (3) (t)={p 1 (3) (t),p 2 (3) (t),…,p N(m) (3) (t)}
the process of antibody population genetic manipulation is described in table 2:
Figure BDA0003688617710000161
in one embodiment, combining the second candidate antibody population and the third candidate antibody population for antibody modification to obtain a fourth candidate antibody population comprises:
combining the second candidate antibody group and the third candidate antibody group, traversing all nodes of each antibody in the combined antibody group, if the ith node and the jth node are continuous on a flight path, and the jth node is not in the neighbor set Ne of the ith node i Then, the jth node is corrected, and the neighbor node set Ne of the ith node is selected i And a set Ne of neighbor nodes of the jth node j As the insert node set B insert If B is insert Null indicates more than two grids between the ith node and the jth node, the antibody is deleted if B insert And if not, randomly selecting a node as an insertion node to obtain a modified fourth candidate antibody group.
In one embodiment, updating the fourth candidate antibody population according to the non-dominated ranking and crowding distance, resulting in a final antibody population, comprises:
the method comprises the following steps: setting a =1, generating a renewed antibody population G;
step two: from the fourth candidate antibody group P (4) Selecting an antibody group F with non-dominant ordering a in (t), combining the antibody groups F and G to generate a combined group F + G = F ≧ G, performing non-dominant ordering on the combined group, and recording the non-dominant ordering value of the combined group F + G as length (F + G);
step three: if length (F + G) < N, N indicates the size of the final antibody population, F is added to G, a = a +1, go to step two; if length (F + G) > N, let NM = N-length (F + G), sort the antibodies in F according to the crowding distance, add the top NM antibodies to G; if length (F + G) = N, add F to G; g is the final antibody population.
In a specific embodiment, the initial population of antibodies is N in size, and if the number of antibodies is greater than N, the antibodies are removed according to rank and crowding distance until the antibody size is N. The final antibody population is P (5) (t)={p 1 (5) (t),p 2 (5) (t),…,p N (5) (t) }. Excess antibodies that exceed the size of the initial antibody population are removed according to the non-dominated sorting and crowding distance, such that the size of the antibody population is unchanged, and antibody quality is optimized without changing the size of the antibody population.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided an unmanned aerial vehicle collaborative flight path planning apparatus based on an immune clone algorithm, including: an objective function construction module 402, an area division module 404, an initial antibody population construction module 406, an antibody population optimization module 408, and an optimization module 410 for unmanned aerial vehicle trajectory planning, wherein:
an objective function construction module 402 for unmanned aerial vehicle flight path planning, configured to obtain an area to be planned; calculating the environmental threat cost of an area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight;
a region dividing module 404, configured to divide a region to be planned into a grid by using a grid method, where all nodes in the grid form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicle in the area to be planned;
an initial antibody cluster construction module 406, configured to calculate a transition probability of each node in the node set according to the guidance factor and the heuristic factor, and use the node with the largest transition probability as a next transition node to obtain an initial antibody cluster; the antibody is an unmanned aerial vehicle track;
an antibody population optimization module 408 for selecting the initial antibody population according to a clone selection algorithm selected by a tournament to obtain a first candidate antibody population; performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group; combining the second candidate antibody group and the third candidate antibody group to carry out antibody modification to obtain a fourth candidate antibody group; performing rapid non-dominated sorting on the fourth candidate antibody group, calculating a crowded distance, and updating the fourth candidate antibody group according to the non-dominated sorting and the crowded distance to obtain a final antibody group;
the optimizing module 410 is configured to optimize the final antibody group according to a target function of the unmanned aerial vehicle flight path planning to obtain an optimal antibody; the optimal antibody is the optimal track of the unmanned aerial vehicle.
In one embodiment, the objective function construction module 402 for unmanned aerial vehicle flight path planning is further configured to set an objective function for unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight, including:
setting an objective function of the unmanned aerial vehicle flight path planning as
Figure BDA0003688617710000181
Wherein, J length Represents the fuel cost, w L Representing coefficient, L track length, J threat Represents a threat cost, w R ,w M ,w A ,w C ,w H And w T Threat weight coefficients of radar, missile, gun, climate, altitude and mountain range respectively; j. the design is a square R ,J M ,J A ,J C ,J H And J T Respectively, threat costs for radar, missile, artillery, weather, altitude, and mountain.
In one embodiment, the initial antibody population building module 406 is further configured to calculate a transition probability for each node in the set of nodes according to the bootstrap factor and the heuristic factor, including:
calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors to obtain the transition probability of the node
Figure BDA0003688617710000182
Wherein i, j and s respectively represent any node in the node set, eta j Denotes a heuristic factor, λ j Denotes a lead factor, alpha denotes the importance of a elicitor, beta denotes the importance of a lead factor, B k,i Representing a set of nodes.
In one embodiment, the antibody population optimization module 408 is further configured to select an initial antibody population according to a tournament-selected clone selection algorithm to obtain a first candidate antibody population, comprising:
setting the scale of the championship as n, setting the scale of the initial antibody group as m, randomly selecting n antibodies from the initial antibody group for comparison, reserving the antibodies with the lowest non-dominance grade and the highest crowding distance, and repeating the process for m times to obtain m antibodies; m antibodies are the first candidate antibody population.
In one embodiment, the antibody population optimization module 408 is further configured to perform an immune cloning operation and an immune gene operation on the first candidate antibody population to obtain a second candidate antibody population and a third candidate antibody population, including:
performing an immunocontraceal operation on the first candidate antibody to obtain a second candidate antibody population
P (2) (t)=P (1)1 (t)+P (1)2 (t)+…+P (1)mc (t)={p 1 (1)1 (t),…,
p m (1)1 (t)}+…+{p 1 (1)mc (t),…,p m (1)mc (t)}={p 1 (2) (t),p 2 (2) (t),…,p N(m) (2) (t)}
Wherein N (m) = m × m c M is the number of antibodies retained by the selection procedure, m c Is the cloning ratio, P (1) (t)={p 1 (1) (t),p 2 (1) (t),…,p m (1) (t) } is the first candidate antibody population.
In one embodiment, the antibody population optimizing module 408 is further configured to perform gene recombination and gene mutation on the first candidate antibody population, in the gene recombination, randomly select two antibodies from the first candidate antibody population, fix the start points and the end points of the two antibodies, calculate the node pairs closest to each other in the two antibodies, select the two nodes as intersections if there is only one pair, swap the two antibodies before and after the intersection according to recombination probability, and randomly select one of the two antibodies as an intersection if there are multiple pairs, swap the two antibodies before and after the two intersections according to recombination probability, so as to obtain an antibody population after the gene recombination;
fixing the starting point and the end node of each antibody in the antibody group after gene recombination, randomly selecting one node in the antibodies to mutate in a mutation range, and obtaining a third candidate antibody group; the mutation range is the intersection of the set of neighbor nodes of the ith node and the set of neighbor nodes of the (i + 1) th node.
In one embodiment, the antibody population optimization module 408 is further configured to combine the second candidate antibody population and the third candidate antibody population for antibody modification to obtain a fourth candidate antibody population, including:
combining the second candidate antibody group and the third candidate antibody group, traversing all nodes of each antibody in the combined antibody group if the ith node and the jth node are continuous on a flight path and the jth node is not on the ith nodeNeighbor set Ne of a node i In (3), the jth node is corrected, and the neighbor node set Ne of the ith node is selected i And a set Ne of neighbor nodes of the jth node j As the insert node set B insert If B is insert Null indicates more than two grids between the ith node and the jth node, the antibody is deleted if B insert And if not, randomly selecting a node as an insertion node to obtain a modified fourth candidate antibody group.
In one embodiment, the antibody population optimization module 408 is further configured to update the fourth candidate antibody population according to the non-dominated sorting and the crowding distance to obtain a final antibody population, comprising:
the method comprises the following steps: setting a =1, generating a renewed antibody population G;
step two: from the fourth candidate antibody group P (4) Selecting an antibody group F with non-dominant ordering a in (t), combining the antibody groups F and G to generate a combined group F + G = F ≧ G, performing non-dominant ordering on the combined group, and recording the non-dominant ordering value of the combined group F + G as length (F + G);
step three: if length (F + G) < N, N indicates the size of the final antibody population, F is added to G, a = a +1, go to step two; if length (F + G) > N, let NM = N-length (F + G), sort the antibodies in F according to the crowding distance, add the first NM antibodies to G; if length (F + G) = N, add F to G; g is the final antibody population.
For specific limitations of the unmanned aerial vehicle collaborative flight path planning apparatus based on the immune clone algorithm, reference may be made to the above limitations on the unmanned aerial vehicle collaborative flight path planning method based on the immune clone algorithm, which are not described herein again. All modules in the unmanned aerial vehicle collaborative flight path planning device based on the immune clone algorithm can be wholly or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize the unmanned aerial vehicle collaborative flight path planning method based on the immune clone algorithm. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is provided, comprising a memory storing a computer program and a processor implementing the steps of the method in the above embodiments when the processor executes the computer program.
In an embodiment, a computer storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method in the above-mentioned embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. An unmanned aerial vehicle flight path optimization method based on an immune clone algorithm is characterized by comprising the following steps:
acquiring a region to be planned;
calculating the environmental threat cost of the area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight;
dividing the area to be planned into grids by adopting a grid method, wherein all nodes in the grids form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicles in the area to be planned;
calculating the transition probability of each node in the node set according to the guide factors and the heuristic factors, and taking the node with the maximum transition probability as the next transition node to obtain an initial antibody group; the antibody is an unmanned aerial vehicle track;
selecting the initial antibody population according to a clone selection algorithm selected by the championship to obtain a first candidate antibody population;
performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group;
combining the second candidate antibody group and the third candidate antibody group to perform antibody modification to obtain a fourth candidate antibody group;
performing rapid non-dominant sorting on the fourth candidate antibody group, calculating a crowded distance, and updating the fourth candidate antibody group according to the non-dominant sorting and the crowded distance to obtain a final antibody group;
optimizing the final antibody group according to the objective function of the unmanned aerial vehicle track planning to obtain an optimal antibody; the optimal antibody is the optimal track of the unmanned aerial vehicle.
2. The method of claim 1, wherein setting an objective function for drone trajectory planning as a function of the environmental threat cost and a fuel cost for drone flight comprises:
setting an objective function of unmanned aerial vehicle flight path planning as
Figure FDA0003688617700000011
Wherein, J length Represents the fuel cost, w L Representing coefficient, L track length, J threat Represents a threat cost, w R ,w M ,w A ,w C ,w H And w T Threat weight coefficients of radar, missile, artillery, climate, altitude and mountain, respectively; j. the design is a square R ,J M ,J A ,J C ,J H And J T Respectively, radar, missile, artillery, weather, altitude, and mountain threat costs.
3. The method of claim 1, wherein calculating the transition probability for each node in the set of nodes based on the bootstrap factor and the heuristic factor comprises:
calculating the transition probability of each node in the node set according to the guide factor and the heuristic factor to obtain the transition probability of the node
Figure FDA0003688617700000021
Wherein i, j and s respectively represent any node in the node set, eta j Denotes a heuristic factor, λ j Denotes a lead factor, alpha denotes the importance of a elicitor, beta denotes the importance of a lead factor, B k,i Representing a set of nodes.
4. A method as claimed in any one of claims 1 to 3 wherein selecting said initial population of antibodies according to a tournament-selected clone selection algorithm to obtain a first candidate population of antibodies comprises:
setting the scale of the championship as n, setting the scale of the initial antibody group as m, randomly selecting n antibodies from the initial antibody group for comparison, retaining the antibodies with the lowest non-dominance grade and the highest crowding distance, and repeating the process for m times to obtain m antibodies; the m antibodies are a first candidate antibody population.
5. The method of claim 4, wherein performing an immunocontoloration and immunogenetic manipulation of the first population of candidate antibodies to obtain a second population of candidate antibodies and a third population of candidate antibodies comprises:
performing an immunocoloclone operation on the first candidate antibody to obtain a second candidate antibody population
P (2) (t)=P (1)1 (t)+P (1)2 (t)+…+P (1)mc (t)={p 1 (1)1 (t),…,p m (1)1 (t)}+…+{p 1 (1)mc (t),…,p m (1)mc (t)}={p 1 (2) (t),p 2 (2) (t),…,p N(m) (2) (t)}
Wherein N (m) = m × m c M is the number of antibodies retained by the selection procedure, m c Is the cloning ratio, P (1) (t)={p 1 (1) (t),p 2 (1) (t),…,p m (1) (t) } is the first candidate antibody population.
6. The method of claim 5, further comprising:
performing gene recombination and gene mutation on the first candidate antibody group, in the gene recombination, randomly selecting two antibodies from the first candidate antibody group, fixing the starting point and the end point of the two antibodies, calculating the node pair which is closest to each other in the two antibodies, if only one pair exists, selecting the two nodes as an intersection, exchanging the two antibodies before and after the intersection according to recombination probability, if multiple pairs exist, randomly selecting one of the two antibodies as the intersection, and exchanging the two antibodies before and after the two intersections according to the recombination probability to obtain an antibody group after the gene recombination;
fixing the starting point and the end node of each antibody in the antibody population after gene recombination, and randomly selecting one node in the antibodies to mutate in a mutation range to obtain a third candidate antibody population; the mutation range is an intersection of the neighbor node set of the ith node and the neighbor node set of the (i + 1) th node.
7. The method of claim 6, wherein combining the second candidate antibody population and the third candidate antibody population to perform antibody modification to obtain a fourth candidate antibody population comprises:
combining the second candidate antibody group and the third candidate antibody group, traversing all nodes of each antibody in the combined antibody group, if the ith node and the jth node are continuous on a flight path, and the jth node is not in the neighbor set Ne of the ith node i Then, the jth node is corrected, and the neighbor node set Ne of the ith node is selected i And neighbor node set Ne of jth node j As the insert node set B insert If B is insert Null indicates more than two grids between the ith node and the jth node, the antibody is deleted if B insert And if not, randomly selecting a node as an insertion node to obtain a modified fourth candidate antibody group.
8. The method of claim 6, wherein updating the fourth candidate antibody population according to the non-dominated sorting and crowding distance to obtain a final antibody population comprises:
the method comprises the following steps: setting a =1, generating a renewed antibody population G;
step two: from the fourth candidate antibody group P (4) Selecting an antibody group F with non-dominant ordering a in (t), combining the antibody groups F and G to generate a combined group F + G = F ≧ G, performing non-dominant ordering on the combined group, and recording the non-dominant ordering value of the combined group F + G as length (F + G);
step three: if length (F + G) < N, N indicates the size of the final antibody population, F is added to G, a = a +1, go to step two; if length (F + G) > N, let NM = N-length (F + G), sort the antibodies in F according to the crowding distance, add the first NM antibodies to G; if length (F + G) = N, add F to G; g is the final antibody population.
9. An unmanned aerial vehicle flight path optimization device based on an immune clone algorithm, which is characterized by comprising:
the unmanned aerial vehicle flight path planning target function building module is used for obtaining an area to be planned; calculating the environmental threat cost of the area to be planned, and constructing an objective function of unmanned aerial vehicle flight path planning according to the environmental threat cost and the fuel cost of unmanned aerial vehicle flight;
the area dividing module is used for dividing the area to be planned into grids by adopting a grid method, and all nodes in the grids form a node set; the nodes are concentrated into a plurality of adjacent nodes to form an unmanned aerial vehicle track; the nodes represent flight point positions of the unmanned aerial vehicle in the area to be planned;
the initial antibody cluster construction module is used for calculating the transition probability of each node in the node set according to the guide factor and the heuristic factor, and taking the node with the maximum transition probability as the next transition node to obtain an initial antibody cluster; the antibody is an unmanned aerial vehicle track;
the antibody population optimization module is used for selecting the initial antibody population according to a clone selection algorithm selected by championship to obtain a first candidate antibody population; performing immune clone operation and immune gene operation on the first candidate antibody group to obtain a second candidate antibody group and a third candidate antibody group; combining the second candidate antibody group and the third candidate antibody group to perform antibody modification to obtain a fourth candidate antibody group; performing rapid non-dominant sorting on the fourth candidate antibody group, calculating a crowded distance, and updating the fourth candidate antibody group according to the non-dominant sorting and the crowded distance to obtain a final antibody group;
the optimizing module is used for optimizing the final antibody group according to the target function of the unmanned aerial vehicle track planning to obtain an optimal antibody; the optimal antibody is the optimal track of the unmanned aerial vehicle.
10. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 8 when executing the computer program.
CN202210654295.9A 2022-06-10 2022-06-10 Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm Pending CN115167501A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210654295.9A CN115167501A (en) 2022-06-10 2022-06-10 Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210654295.9A CN115167501A (en) 2022-06-10 2022-06-10 Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm

Publications (1)

Publication Number Publication Date
CN115167501A true CN115167501A (en) 2022-10-11

Family

ID=83485870

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210654295.9A Pending CN115167501A (en) 2022-06-10 2022-06-10 Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm

Country Status (1)

Country Link
CN (1) CN115167501A (en)

Similar Documents

Publication Publication Date Title
CN111352417B (en) Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path
CN107977743B (en) Multi-unmanned aerial vehicle cooperative task allocation method and device
Edison et al. Integrated task assignment and path optimization for cooperating uninhabited aerial vehicles using genetic algorithms
CN103279793B (en) A kind of unmanned vehicle formation method for allocating tasks determined under environment
CN107886201B (en) Multi-objective optimization method and device for multi-unmanned aerial vehicle task allocation
Chen et al. Unmanned aerial vehicle route planning method based on a star algorithm
CN111240211B (en) Dynamic recovery method for unmanned aerial vehicle group
CN110986960B (en) Unmanned aerial vehicle flight path planning method based on improved clustering algorithm
CN113885555A (en) Multi-machine task allocation method and system for power transmission line dense channel routing inspection
CN115755954B (en) Routing inspection path planning method, system, computer equipment and storage medium
CN111880561A (en) Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment
CN112484732B (en) IB-ABC algorithm-based unmanned aerial vehicle flight path planning method
CN113051815A (en) Agile imaging satellite task planning method based on independent pointer network
CN110851662A (en) Heterogeneous information network link prediction method based on meta path
CN110609572A (en) Heuristic optimization method and device for unmanned aerial vehicle formation information interaction topology
CN115494873A (en) Heterogeneous multi-unmanned aerial vehicle cooperative task allocation method based on Monte Carlo tree search architecture under time sequence constraint
CN115167502A (en) Unmanned aerial vehicle collaborative flight path planning method and device based on immune clone algorithm
CN112363532A (en) Multi-unmanned aerial vehicle simultaneous take-off aggregation method based on QUATRE algorithm
CN115829230A (en) Heterogeneous unmanned aerial vehicle group cooperative attack task allocation method
Wang et al. UAV online path planning based on improved genetic algorithm
CN113805609A (en) Unmanned aerial vehicle group target searching method based on chaos lost pigeon group optimization mechanism
CN115167501A (en) Unmanned aerial vehicle flight path optimization method, device and equipment based on immune clone algorithm
CN116258357B (en) Heterogeneous unmanned aerial vehicle cooperative target distribution method based on polygene genetic algorithm
CN116088586A (en) Method for planning on-line tasks in unmanned aerial vehicle combat process
Fu et al. Improved genetic and ant colony optimization algorithm for regional air defense wta problem

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