Unmanned aerial vehicle cluster rendezvous method and system based on week number particle swarm optimization

Abstract

The invention discloses an unmanned aerial vehicle cluster rendezvous method and system based on week number particle swarm optimization, and the method comprises the steps: planning a non-rendezvous route from an initial position and state to an expected position and state for each unmanned aerial vehicle according to the current task requirement; in order to realize rendezvous and enable the path length of any unmanned aerial vehicle to be the longest air route, calculating the optimal circling cycle number of any unmanned aerial vehicle by utilizing a cycle number particle swarm optimization method; for any unmanned aerial vehicle, calculating a decimal circling cycle number according to the calculated optimal circling cycle number so as to calculate a transition waypoint position vector and a state vector after the unmanned aerial vehicle circles the optimal circling cycle; and determining an intersection route according to the calculated transition route point position vector and state vector. According to the invention, an efficient solution which is based on a single optimization variable and is low in calculation cost can be provided for an unmanned aerial vehicle cluster rendezvous problem.

Description

Technical Field

[0001] The present application relates to the field of UAV control technology, and in particular to a UAV cluster rendezvous method and system based on cycle number particle swarm optimization. Background Art

[0002] Various applications, including regional surveillance and formation escort, require that each member of the drone cluster arrive at its desired position at a set time with its desired posture to facilitate the execution of subsequent tasks.

[0003] How to plan a route for a drone swarm so that each drone in the swarm reaches its desired position at the same time with its desired posture? However, the existing technology has too high a computational cost. Summary of the invention

[0004] The embodiments of the present application provide a UAV cluster rendezvous method and system based on week-number particle swarm optimization, which is used to provide an efficient solution to the "UAV cluster rendezvous problem" based on a single optimization variable and with low computational cost.

[0005] The present application embodiment provides a UAV cluster rendezvous method based on cycle number particle swarm optimization, including:

[0006] According to the current mission requirements, plan a non-intersecting route for each UAV from its initial position and state to its desired position and state;

[0007] In order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated using the circling number particle swarm optimization method;

[0008] For any UAV, the fractional circling number is calculated according to the calculated optimal circling number, so as to calculate the transition waypoint position vector and state vector of any UAV after the optimal circling number;

[0009] The rendezvous route is determined based on the calculated transition waypoint position vector and state vector.

[0010] Optionally, according to the current mission requirements, a non-intersecting route is planned for each UAV from the initial position and state to the desired position and state, including:

[0011] For the nth UAV, the initial position and state as well as the expected position and state are eliminated, and its non-intersecting route consists of M waypoints and corresponding states. n ) waypoint position vector is denoted as p mn =[x mn ,y mn ,z mn ], the posture vector is denoted as s mn =[ψmn ,γ mn ], where x mn ,y m , n z m for n The waypoint is located at three coordinates, ψ mn is the heading angle corresponding to the waypoint, γ mn is the flight track angle corresponding to the waypoint;

[0012] The non-intersecting routes between every two adjacent waypoints are connected by Dubins routes;

[0013] For the nth UAV, the total length of its non-intersection route is recorded as L n , define the longest route of the drone as L max .

[0014] Optionally, in order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated by using the circling number particle swarm optimization method, including:

[0015] Select the circling direction and determine the number of circling cycles in the circling direction;

[0016] Set the upper and lower limits of particle position and velocity;

[0017] The absolute value of the difference between the total length of the current UAV route and the maximum route length is selected as the fitness function.

[0018] Optionally, in order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated by using the circling number particle swarm optimization method, and further includes:

[0019] Select K particles, and for each particle k, randomly generate its initial position q according to the position limit and speed limit 0k and initial velocity v 0k ;

[0020] According to the fitness function, calculate the initial fitness of each particle. For particle k, its initial fitness is recorded as w 0k , and according to the initial fitness of the particle, calculate the initial individual extreme value and the initial global extreme value, and record the individual extreme value of particle k as w p,0k , and the global extreme value is recorded as w g,0 ;

[0021] Update the velocity of the kth particle:

[0022] v j+1，k =ωv jk +c1u1(w p，jk -qjk )+c2u2(w g，j -q jk )

[0023] Among them, v jk is the velocity of particle k at time j (j = 0, 1, 2, L, J-1), J is the maximum number of iterations, v j+1,k is the velocity of particle k at time j+1 (j=0,1,2,L,J-1), q jk is the position of particle k at time j, w p,jk is the individual extreme value of particle k up to time j, w g,j is the global extreme value up to time j, ω is the inertia weight, c1 and c2 are the individual learning factor and the global learning factor respectively, and u1 and u2 are randomly generated numbers in the interval [0,1].

[0024] Optionally, in order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated by using the circling number particle swarm optimization method, and further includes:

[0025] Adjust the particle speed according to the particle speed limit to limit the particle speed to the interval [v p,min ,v p,max ], where v p,min 、v p,max are the lower and upper bounds of the particle velocity, respectively.

[0026] Update the position of the kth particle:

[0027] q j+1,k =q jk +v j+1,k

[0028] Among them, q j+1,k is the position of particle k at time j+1 (j=0,1,2,L,J-1);

[0029] Adjust the particle position according to the particle position limit to limit the particle position to the interval [0,r n,max ], where r n,max is the upper bound of the particle position;

[0030] According to the fitness function, calculate the fitness of each particle at the current moment. For particle k, its fitness is recorded as w j+1,k , and according to the particle fitness, calculate the individual extreme value and global extreme value at the current moment, and for particle k, record its individual extreme value as w p,j+1,k ; Let the global extreme value be w g,j+1 ;

[0031] Determine whether the maximum number of iterations has been reached, or whether the global extreme value at the current moment is less than the set threshold ε. If the threshold condition is met, the current global extreme value is selected as the optimal number of circling cycles. If the threshold condition is not met, the number of circling cycles in another circling direction is selected as the optimization variable and recalculated.

[0032] Optionally, for any UAV, the fractional circling number is calculated according to the calculated optimal circling number to calculate the transition waypoint position vector and state vector after any UAV has circled the optimal circling number, including:

[0033] For the nth drone, calculate the integer number of circling cycles in is the floor function, and calculates the number of decimal circles b n =r n,opt -a n ;

[0034] Calculate the number of times the nth drone hovers r n,opt The transition waypoint position vector p after one week tn =[x tn ,y tn ,z tn ] and the state vector s tn =[ψ tn ,γ tn ], where x tn ,y tn 、z tn is the position of the transition waypoint in three coordinates, ψ tn is the heading angle of the transition waypoint, γ tn is the flight track angle of the transition waypoint.

[0035] Optionally, for the nth UAV, the rendezvous route is:

[0036]

[0037] Every two adjacent waypoints are connected by a Dubins path, and if two adjacent waypoints are the same, it means a circle has been circled.

[0038] An embodiment of the present application also proposes a drone cluster rendezvous system based on cycle number particle swarm optimization, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the drone cluster rendezvous method based on cycle number particle swarm optimization as described above are implemented.

[0039] The embodiments of the present application can provide an efficient solution to the "UAV cluster rendezvous problem" based on a single optimization variable and with low computational cost.

[0040] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0042] Figure 1 The basic process diagram of the UAV cluster rendezvous method based on the cycle number particle swarm optimization of the embodiment of the present application is shown;

[0043] Figure 2 A schematic diagram of a rendezvous route (herringbone) for an implementation example of a UAV cluster rendezvous method based on cycle number particle swarm optimization in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of a rendezvous route (circular) for implementing a calculation example of a UAV cluster rendezvous method based on week-number particle swarm optimization in an embodiment of the present application;

[0045] Figure 4 A schematic diagram of a rendezvous route (obstacle environment) for an implementation example of a UAV cluster rendezvous method based on week-number particle swarm optimization according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0047] In the embodiment of the present application, the drone cluster is composed of N fixed-wing drones, and the cruising speed of each drone in the cluster is V uav , and keep the speed constant during the mission. The initial position vector of the nth UAV is p 0n =[x 0n ,y 0n ,z 0n ], the initial posture vector is s 0n =[ψ 0n ,γ 0n ], where x 0n ,y 0n、z 0n is the position of the nth UAV in three coordinates, ψ 0n is the heading angle of the nth UAV, γ 0n is the flight track angle of the nth UAV. The expected position vector of the nth UAV is p dn =[x dn ,y dn ,z dn ], the expected posture vector is s dn =[ψ dn ,γ dn ], where x dn ,y dn 、z dn is the expected position of the nth UAV in three coordinates, ψ dn is the expected heading angle of the nth UAV, γ dn is the expected flight path angle of the nth UAV.

[0048] UAV cluster rendezvous refers to planning a route for a UAV cluster so that at a certain moment, each UAV arrives at its desired position with its desired posture. The present application embodiment provides a UAV cluster rendezvous method based on week-number particle swarm optimization, such as Figure 1 As shown, the following steps are included:

[0049] In step S101, according to the current mission requirements, a non-intersecting route is planned for each UAV from the initial position and state to the desired position and state, that is, a route that does not consider arrival simultaneity.

[0050] In step S102, in order to achieve the intersection, the path length of any UAV is the longest route, and the optimal circling number of any UAV is calculated using the circling number particle swarm optimization method. For example, in some embodiments, in order to make each UAV reach the desired position and state at the same time, the path length of all UAVs can be L max To this end, let the nth (n = 1, 2, L, N) drone circle a certain number of times r at the initial position. n ≥0, then fly along the remaining waypoints.

[0051] In step S103, for any UAV, the fractional circling number is calculated according to the calculated optimal circling number, so as to calculate the transition waypoint position vector and state vector of any UAV after circling the optimal circling number. In some embodiments, for any UAV, the fractional circling number is calculated according to the calculated optimal circling number, so as to calculate the transition waypoint position vector and state vector of any UAV after circling the optimal circling number, including:

[0052] For the nth drone, calculate the integer number of circling cycles in is the floor function, and calculates the number of decimal circles b n =r n,opt -a n ;

[0053] Then calculate the number of times the nth drone hovers r n,opt The transition waypoint position vector p after one week tn =[x tn ,y tn ,z tn ] and the state vector s tn =[ψ tn ,γ tn ], where x tn ,y tn 、z tn is the position of the transition waypoint in three coordinates, ψ tn is the heading angle of the transition waypoint, γ tn is the flight track angle of the transition waypoint.

[0054] In step S104, the intersection route is determined according to the calculated transition waypoint position vector and state vector.

[0055] The embodiments of the present application can provide an efficient solution to the "UAV cluster rendezvous problem" based on a single optimization variable and with low computational cost.

[0056] In some embodiments, according to current mission requirements, planning a non-intersecting route for each drone from an initial position and state to a desired position and state includes:

[0057] For the nth UAV, the initial position and state as well as the expected position and state are eliminated, and its non-intersecting route consists of M waypoints and corresponding states. n ) waypoint position vector is denoted as p mn =[x mn ,y mn ,z mn ], the posture vector is denoted as s mn =[ψ mn ,γ mn ], where x mn ,y mn 、z mn is the position of the waypoint in three coordinates, ψ mn is the heading angle corresponding to the waypoint, γ mn is the flight track angle corresponding to the waypoint;

[0058] The non-intersecting routes between every two adjacent waypoints (including the initial position and the first waypoint and the last waypoint and the desired position) are connected by Dubins routes;

[0059] For the nth UAV, the total length of its non-intersection route is recorded as L n , define the longest route of the drone as L max Without loss of generality, we can assume that the first UAV has the longest route and record it as L max =L1.

[0060] In some embodiments, in order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated by using the circling number particle swarm optimization method, including:

[0061] Select a circling direction, and determine the number of circling turns when circling in the circling direction. For example, you can first select the number of circling turns when circling counterclockwise as the optimization variable.

[0062] Set the upper and lower limits of the particle position and the upper and lower limits of the speed. For example, set the particle position limit to the lower and upper limits of the number of revolutions. The lower limit is 0, and the upper limit is set to r. n,max =2(L max -L n ), set the lower and upper bounds of the particle velocity to v p,min 、v p,max .

[0063] The absolute value of the difference between the total length of the current UAV route and the maximum route length is selected as the fitness function.

[0064] In some embodiments, in order to achieve the intersection and make the path length of any UAV the longest route, using the particle swarm optimization method to calculate the optimal circling number of any UAV also includes:

[0065] Select K particles, and for each particle k, randomly generate its initial position q according to the position limit and speed limit 0k and initial velocity v 0k ;

[0066] According to the fitness function, calculate the initial fitness of each particle. For particle k, its initial fitness is recorded as w 0k , and according to the initial fitness of the particle, calculate the initial individual extreme value (the optimal fitness of each particle so far) and the initial global extreme value (the optimal fitness of all particles so far), record the individual extreme value of particle k as wp,0k, and the global extreme value as wg,0;

[0067] Update the velocity of the kth particle:

[0068] v j+1，k =ωv jk +c1u1(w p，jk -q jk)+c2u2(w g，j -q jk )

[0069] Among them, v jk is the velocity of particle k at time j (j = 0, 1, 2, L, J-1), J is the maximum number of iterations, v j+1,k is the velocity of particle k at time j+1 (j=0,1,2,L,J-1), q jk is the position of particle k at time j, w p,jk is the individual extreme value of particle k up to time j, w g,j is the global extreme value up to time j, ω is the inertia weight, c1 and c2 are the individual learning factor and the global learning factor respectively, and u1 and u2 are randomly generated numbers in the interval [0,1].

[0070] In some embodiments, in order to achieve the intersection and make the path length of any UAV the longest route, using the particle swarm optimization method to calculate the optimal circling number of any UAV also includes:

[0071] Adjust the particle speed according to the particle speed limit to limit the particle speed to the interval [v p,min ,v p,max ]Inside.

[0072] Update the position of the kth particle:

[0073] q j+1,k =q jk +v j+1,k

[0074] Among them, q j+1,k is the position of particle k at time j+1 (j=0,1,2,L,J-1);

[0075] Adjust the particle position according to the particle position limit to limit the particle position to the interval [0,r n,max ]Inside;

[0076] According to the fitness function, calculate the fitness of each particle at the current moment. For particle k, its fitness is recorded as w j+1,k , and according to the particle fitness, calculate the individual extreme value and global extreme value at the current moment, and for particle k, record its individual extreme value as w p,j+1,k ; Let the global extreme value be w g,j+1 ;

[0077] Determine whether the maximum number of iterations has been reached, or whether the global extremum at the current moment is less than the set threshold ε. If the threshold condition is met, the current global extremum is selected as the optimal number of circling cycles. If the threshold condition is not met, the number of circling cycles in another circling direction is selected as the optimization variable and recalculated. In the specific example, determine whether the maximum number of iterations has been reached, or whether the global extremum at the current moment is less than the set threshold. If both termination conditions are not met, repeat the update of the particle speed and position; otherwise, jump out of the loop, that is, the threshold condition is met, and the current global extremum is selected as the optimal number of circling cycles r n,opt , output the result. If the threshold condition is not met, select the number of circling cycles when circling clockwise as the optimization variable and re-execute the number of circling particle swarm optimization steps.

[0078] In some embodiments, for the nth UAV, the rendezvous route is:

[0079]

[0080] Every two adjacent waypoints are connected by a Dubins path, and if two adjacent waypoints are the same, it means a circle has been circled.

[0081] like Figure 2-Figure 4 The implementation case of the UAV cluster rendezvous method based on the weekly particle swarm optimization of this application is shown, such as Figure 2-Figure 4 As shown, in multiple rendezvous scenarios, each UAV can reach the desired rendezvous point at the same time in the desired rendezvous state after a certain number of initial circling.

[0082] The method of the present application selects only one variable, and can quickly calculate the optimal number of circling cycles when performing particle swarm optimization, thereby providing an efficient solution based on a single optimization variable and with low computational cost for the "UAV cluster rendezvous problem".

[0083] The embodiment of the present application also proposes a drone cluster rendezvous system based on week-number particle swarm optimization, including a processor and a memory, wherein a computer program is stored on the memory, and when the computer program is executed by the processor, the steps of the drone cluster rendezvous method based on week-number particle swarm optimization as described above are implemented. It should be noted that in the embodiments of the present application, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or device including the element.

[0084] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0085] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0086] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A UAV cluster rendezvous method based on week-number particle swarm optimization, characterized in that: include: According to the current mission requirements, plan a non-intersecting route for each UAV from its initial position and state to its desired position and state; In order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated using the circling number particle swarm optimization method; For any UAV, the fractional circling number is calculated according to the calculated optimal circling number, so as to calculate the transition waypoint position vector and state vector of any UAV after the optimal circling number; The intersection route is determined based on the calculated transition waypoint position vector and state vector.

2. The UAV cluster rendezvous method based on cycle number particle swarm optimization as claimed in claim 1, characterized in that: According to the current mission requirements, planning a non-intersecting route for each UAV from the initial position and state to the desired position and state includes: For the nth UAV, the initial position and state as well as the expected position and state are eliminated, and its non-intersecting route consists of M waypoints and corresponding states. n ) waypoint position vector is denoted as p mn =[x mn ,y mn ,z mn ], the posture vector is denoted as s mn =[ψ mn ,γ mn ], where x mn ,y mn 、z mn is the position of the waypoint in three coordinates, ψ mn is the heading angle corresponding to the waypoint, γ mn is the flight track angle corresponding to the waypoint; The non-intersecting routes between every two adjacent waypoints are connected by Dubins routes; For the nth UAV, the total length of its non-intersection route is recorded as L n , define the longest route of the drone as L max .

3. The UAV cluster rendezvous method based on cycle number particle swarm optimization as claimed in claim 2, characterized in that: In order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated by using the circling number particle swarm optimization method, including: Select the circling direction and determine the number of circling cycles in the circling direction; Set the upper and lower limits of particle position and velocity; The absolute value of the difference between the total length of the current UAV route and the maximum route length is selected as the fitness function.

4. The UAV cluster rendezvous method based on cycle number particle swarm optimization as claimed in claim 3, characterized in that: In order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated by using the circling number particle swarm optimization method, which also includes: Select K particles, and for each particle k, randomly generate its initial position q according to the position limit and speed limit 0k and initial velocity v 0k ; According to the fitness function, calculate the initial fitness of each particle. For particle k, its initial fitness is recorded as w 0k , and according to the initial fitness of the particle, calculate the initial individual extreme value and the initial global extreme value, and record the individual extreme value of particle k as w p,0k , and the global extreme value is recorded as w g,0 ; Update the velocity of the kth particle: v j+1，k =ωv jk +c1u1(w p，jk -q jk )+c2u2(w g，j -q jk ) Among them, v jk is the velocity of particle k at time j (j = 0, 1, 2, L, J-1), J is the maximum number of iterations, v j+1,k is the velocity of particle k at time j+1 (j=0,1,2,L,J-1), q jk is the position of particle k at time j, w p,jk is the individual extreme value of particle k up to time j, w g,j is the global extreme value up to time j, ω is the inertia weight, c1 and c2 are the individual learning factor and the global learning factor respectively, and u1 and u2 are randomly generated numbers in the interval [0,1].

5. The UAV cluster rendezvous method based on cycle number particle swarm optimization as claimed in claim 4, characterized in that: In order to achieve the rendezvous and make the path length of any UAV the longest route, the optimal circling number of any UAV is calculated by using the circling number particle swarm optimization method, which also includes: Adjust the particle speed according to the particle speed limit to limit the particle speed to the interval [v p,min ,v p,max ], where v p,min 、v p,max are the lower and upper bounds of the particle velocity, respectively. Update the position of the kth particle: q j+1,k =q jk +v j+1,k Among them, q j+1,k is the position of particle k at time j+1 (j=0,1,2,L,J-1); Adjust the particle position according to the particle position limit to limit the particle position to the interval [0,r n,max ], where r n,max is the upper bound of the particle position; According to the fitness function, calculate the fitness of each particle at the current moment. For particle k, its fitness is recorded as w j+1,k , and according to the particle fitness, calculate the individual extreme value and global extreme value at the current moment, and for particle k, record its individual extreme value as w p,j+1,k ; Let the global extreme value be w g,j+1 ; Determine whether the maximum number of iterations has been reached, or whether the global extreme value at the current moment is less than the set threshold ε. If the threshold condition is met, the current global extreme value is selected as the optimal number of circling cycles. If the threshold condition is not met, the number of circling cycles in another circling direction is selected as the optimization variable and recalculated.

6. The UAV cluster rendezvous method based on cycle number particle swarm optimization as claimed in claim 5, characterized in that: For any UAV, the fractional circling number is calculated according to the calculated optimal circling number, so as to calculate the transition waypoint position vector and state vector after any UAV has circled the optimal circling number, including: For the nth drone, calculate the integer number of circling cycles in is the floor function, and calculates the number of decimal circles b n =r n,opt -a n ; Calculate the number of times the nth drone hovers r n,opt The transition waypoint position vector p after one week tn =[x tn ,y tn ,z tn ] and state vector s tn =[ψ tn ,γ tn ], where x tn ,y tn 、z tn is the position of the transition waypoint in three coordinates, ψ tn is the heading angle of the transition waypoint, γ tn is the flight track angle of the transition waypoint.

7. The UAV cluster rendezvous method based on cycle number particle swarm optimization as claimed in claim 5, characterized in that: Based on the calculated transition waypoint position vector and state vector, the intersection route is determined to include: For the nth UAV, its rendezvous route is: Every two adjacent waypoints are connected by a Dubins path, and if two adjacent waypoints are the same, it means a circle has been circled.

8. A UAV cluster rendezvous system based on week-number particle swarm optimization, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the drone cluster rendezvous method based on week-number particle swarm optimization as described in any one of claims 1 to 7 are implemented.

Images